linux/drivers/pci/controller/pci-hyperv.c

4194 lines
116 KiB

x86: Don't include linux/irq.h from asm/hardirq.h The next patch in this series will have to make the definition of irq_cpustat_t available to entering_irq(). Inclusion of asm/hardirq.h into asm/apic.h would cause circular header dependencies like asm/smp.h asm/apic.h asm/hardirq.h linux/irq.h linux/topology.h linux/smp.h asm/smp.h or linux/gfp.h linux/mmzone.h asm/mmzone.h asm/mmzone_64.h asm/smp.h asm/apic.h asm/hardirq.h linux/irq.h linux/irqdesc.h linux/kobject.h linux/sysfs.h linux/kernfs.h linux/idr.h linux/gfp.h and others. This causes compilation errors because of the header guards becoming effective in the second inclusion: symbols/macros that had been defined before wouldn't be available to intermediate headers in the #include chain anymore. A possible workaround would be to move the definition of irq_cpustat_t into its own header and include that from both, asm/hardirq.h and asm/apic.h. However, this wouldn't solve the real problem, namely asm/harirq.h unnecessarily pulling in all the linux/irq.h cruft: nothing in asm/hardirq.h itself requires it. Also, note that there are some other archs, like e.g. arm64, which don't have that #include in their asm/hardirq.h. Remove the linux/irq.h #include from x86' asm/hardirq.h. Fix resulting compilation errors by adding appropriate #includes to *.c files as needed. Note that some of these *.c files could be cleaned up a bit wrt. to their set of #includes, but that should better be done from separate patches, if at all. Signed-off-by: Nicolai Stange <nstange@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2018-07-29 12:15:33 +02:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI In the multi-MSI case, hv_arch_irq_unmask() will only operate on the first MSI of the N allocated. This is because only the first msi_desc is cached and it is shared by all the MSIs of the multi-MSI block. This means that hv_arch_irq_unmask() gets the correct address, but the wrong data (always 0). This can break MSIs. Lets assume MSI0 is vector 34 on CPU0, and MSI1 is vector 33 on CPU0. hv_arch_irq_unmask() is called on MSI0. It uses a hypercall to configure the MSI address and data (0) to vector 34 of CPU0. This is correct. Then hv_arch_irq_unmask is called on MSI1. It uses another hypercall to configure the MSI address and data (0) to vector 33 of CPU0. This is wrong, and results in both MSI0 and MSI1 being routed to vector 33. Linux will observe extra instances of MSI1 and no instances of MSI0 despite the endpoint device behaving correctly. For the multi-MSI case, we need unique address and data info for each MSI, but the cached msi_desc does not provide that. However, that information can be gotten from the int_desc cached in the chip_data by compose_msi_msg(). Fix the multi-MSI case to use that cached information instead. Since hv_set_msi_entry_from_desc() is no longer applicable, remove it. Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/1651068453-29588-1-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-27 08:07:33 -06:00
PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI In the multi-MSI case, hv_arch_irq_unmask() will only operate on the first MSI of the N allocated. This is because only the first msi_desc is cached and it is shared by all the MSIs of the multi-MSI block. This means that hv_arch_irq_unmask() gets the correct address, but the wrong data (always 0). This can break MSIs. Lets assume MSI0 is vector 34 on CPU0, and MSI1 is vector 33 on CPU0. hv_arch_irq_unmask() is called on MSI0. It uses a hypercall to configure the MSI address and data (0) to vector 34 of CPU0. This is correct. Then hv_arch_irq_unmask is called on MSI1. It uses another hypercall to configure the MSI address and data (0) to vector 33 of CPU0. This is wrong, and results in both MSI0 and MSI1 being routed to vector 33. Linux will observe extra instances of MSI1 and no instances of MSI0 despite the endpoint device behaving correctly. For the multi-MSI case, we need unique address and data info for each MSI, but the cached msi_desc does not provide that. However, that information can be gotten from the int_desc cached in the chip_data by compose_msi_msg(). Fix the multi-MSI case to use that cached information instead. Since hv_set_msi_entry_from_desc() is no longer applicable, remove it. Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/1651068453-29588-1-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-27 08:07:33 -06:00
PCI: hv: Fix a race condition in hv_irq_unmask() that can cause panic When the host tries to remove a PCI device, the host first sends a PCI_EJECT message to the guest, and the guest is supposed to gracefully remove the PCI device and send a PCI_EJECTION_COMPLETE message to the host; the host then sends a VMBus message CHANNELMSG_RESCIND_CHANNELOFFER to the guest (when the guest receives this message, the device is already unassigned from the guest) and the guest can do some final cleanup work; if the guest fails to respond to the PCI_EJECT message within one minute, the host sends the VMBus message CHANNELMSG_RESCIND_CHANNELOFFER and removes the PCI device forcibly. In the case of fast device addition/removal, it's possible that the PCI device driver is still configuring MSI-X interrupts when the guest receives the PCI_EJECT message; the channel callback calls hv_pci_eject_device(), which sets hpdev->state to hv_pcichild_ejecting, and schedules a work hv_eject_device_work(); if the PCI device driver is calling pci_alloc_irq_vectors() -> ... -> hv_compose_msi_msg(), we can break the while loop in hv_compose_msi_msg() due to the updated hpdev->state, and leave data->chip_data with its default value of NULL; later, when the PCI device driver calls request_irq() -> ... -> hv_irq_unmask(), the guest crashes in hv_arch_irq_unmask() due to data->chip_data being NULL. Fix the issue by not testing hpdev->state in the while loop: when the guest receives PCI_EJECT, the device is still assigned to the guest, and the guest has one minute to finish the device removal gracefully. We don't really need to (and we should not) test hpdev->state in the loop. Fixes: de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-3-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:48 -07:00
PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI In the multi-MSI case, hv_arch_irq_unmask() will only operate on the first MSI of the N allocated. This is because only the first msi_desc is cached and it is shared by all the MSIs of the multi-MSI block. This means that hv_arch_irq_unmask() gets the correct address, but the wrong data (always 0). This can break MSIs. Lets assume MSI0 is vector 34 on CPU0, and MSI1 is vector 33 on CPU0. hv_arch_irq_unmask() is called on MSI0. It uses a hypercall to configure the MSI address and data (0) to vector 34 of CPU0. This is correct. Then hv_arch_irq_unmask is called on MSI1. It uses another hypercall to configure the MSI address and data (0) to vector 33 of CPU0. This is wrong, and results in both MSI0 and MSI1 being routed to vector 33. Linux will observe extra instances of MSI1 and no instances of MSI0 despite the endpoint device behaving correctly. For the multi-MSI case, we need unique address and data info for each MSI, but the cached msi_desc does not provide that. However, that information can be gotten from the int_desc cached in the chip_data by compose_msi_msg(). Fix the multi-MSI case to use that cached information instead. Since hv_set_msi_entry_from_desc() is no longer applicable, remove it. Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/1651068453-29588-1-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-27 08:07:33 -06:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Only reuse existing IRTE allocation for Multi-MSI Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI") It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/ Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts. Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt. The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU. The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported). Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-11-04 15:29:53 -07:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Fix 2 hang issues in hv_compose_msi_msg() 1. With the patch "x86/vector/msi: Switch to global reservation mode", the recent v4.15 and newer kernels always hang for 1-vCPU Hyper-V VM with SR-IOV. This is because when we reach hv_compose_msi_msg() by request_irq() -> request_threaded_irq() ->__setup_irq()->irq_startup() -> __irq_startup() -> irq_domain_activate_irq() -> ... -> msi_domain_activate() -> ... -> hv_compose_msi_msg(), local irq is disabled in __setup_irq(). Note: when we reach hv_compose_msi_msg() by another code path: pci_enable_msix_range() -> ... -> irq_domain_activate_irq() -> ... -> hv_compose_msi_msg(), local irq is not disabled. hv_compose_msi_msg() depends on an interrupt from the host. With interrupts disabled, a UP VM always hangs in the busy loop in the function, because the interrupt callback hv_pci_onchannelcallback() can not be called. We can do nothing but work it around by polling the channel. This is ugly, but we don't have any other choice. 2. If the host is ejecting the VF device before we reach hv_compose_msi_msg(), in a UP VM, we can hang in hv_compose_msi_msg() forever, because at this time the host doesn't respond to the CREATE_INTERRUPT request. This issue exists the first day the pci-hyperv driver appears in the kernel. Luckily, this can also by worked around by polling the channel for the PCI_EJECT message and hpdev->state, and by checking the PCI vendor ID. Note: actually the above 2 issues also happen to a SMP VM, if "hbus->hdev->channel->target_cpu == smp_processor_id()" is true. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Tested-by: Adrian Suhov <v-adsuho@microsoft.com> Tested-by: Chris Valean <v-chvale@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Haiyang Zhang <haiyangz@microsoft.com> Cc: <stable@vger.kernel.org> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Jack Morgenstein <jackm@mellanox.com>
2018-03-15 14:21:08 +00:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality The current implementation of hv_compose_msi_msg() is incompatible with the new functionality that allows changing the vCPU a VMBus channel will interrupt: if this function always calls hv_pci_onchannelcallback() in the polling loop, the interrupt going to a different CPU could cause hv_pci_onchannelcallback() to be running simultaneously in a tasklet, which will break. The current code also has a problem in that it is not synchronized with vmbus_reset_channel_cb(): hv_compose_msi_msg() could be accessing the ring buffer via the call of hv_pci_onchannelcallback() well after the time that vmbus_reset_channel_cb() has finished. Fix these issues as follows. Disable the channel tasklet before entering the polling loop in hv_compose_msi_msg() and re-enable it when done. This will prevent hv_pci_onchannelcallback() from running in a tasklet on a different CPU. Moreover, poll by always calling hv_pci_onchannelcallback(), but check the channel callback function for NULL and invoke the callback within a sched_lock critical section. This will prevent hv_compose_msi_msg() from accessing the ring buffer after vmbus_reset_channel_cb() has acquired the sched_lock spinlock. Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Andrew Murray <amurray@thegoodpenguin.co.uk> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: <linux-pci@vger.kernel.org> Link: https://lore.kernel.org/r/20200406001514.19876-8-parri.andrea@gmail.com Reviewed-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-06 02:15:10 +02:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add pci_destroy_slot() in pci_devices_present_work(), if necessary When we hot-remove a device, usually the host sends us a PCI_EJECT message, and a PCI_BUS_RELATIONS message with bus_rel->device_count == 0. When we execute the quick hot-add/hot-remove test, the host may not send us the PCI_EJECT message if the guest has not fully finished the initialization by sending the PCI_RESOURCES_ASSIGNED* message to the host, so it's potentially unsafe to only depend on the pci_destroy_slot() in hv_eject_device_work() because the code path create_root_hv_pci_bus() -> hv_pci_assign_slots() is not called in this case. Note: in this case, the host still sends the guest a PCI_BUS_RELATIONS message with bus_rel->device_count == 0. In the quick hot-add/hot-remove test, we can have such a race before the code path pci_devices_present_work() -> new_pcichild_device() adds the new device into the hbus->children list, we may have already received the PCI_EJECT message, and since the tasklet handler hv_pci_onchannelcallback() may fail to find the "hpdev" by calling get_pcichild_wslot(hbus, dev_message->wslot.slot) hv_pci_eject_device() is not called; Later, by continuing execution create_root_hv_pci_bus() -> hv_pci_assign_slots() creates the slot and the PCI_BUS_RELATIONS message with bus_rel->device_count == 0 removes the device from hbus->children, and we end up being unable to remove the slot in hv_pci_remove() -> hv_pci_remove_slots() Remove the slot in pci_devices_present_work() when the device is removed to address this race. pci_devices_present_work() and hv_eject_device_work() run in the singled-threaded hbus->wq, so there is not a double-remove issue for the slot. We cannot offload hv_pci_eject_device() from hv_pci_onchannelcallback() to the workqueue, because we need the hv_pci_onchannelcallback() synchronously call hv_pci_eject_device() to poll the channel ringbuffer to work around the "hangs in hv_compose_msi_msg()" issue fixed in commit de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()") Fixes: a15f2c08c708 ("PCI: hv: support reporting serial number as slot information") Signed-off-by: Dexuan Cui <decui@microsoft.com> [lorenzo.pieralisi@arm.com: rewritten commit log] Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Cc: stable@vger.kernel.org
2019-03-04 21:34:49 +00:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Fix synchronization between channel callback and hv_compose_msi_msg() Dexuan wrote: "[...] when we disable AccelNet, the host PCI VSP driver sends a PCI_EJECT message first, and the channel callback may set hpdev->state to hv_pcichild_ejecting on a different CPU. This can cause hv_compose_msi_msg() to exit from the loop and 'return', and the on-stack variable 'ctxt' is invalid. Now, if the response message from the host arrives, the channel callback will try to access the invalid 'ctxt' variable, and this may cause a crash." Schematically: Hyper-V sends PCI_EJECT msg hv_pci_onchannelcallback() state = hv_pcichild_ejecting hv_compose_msi_msg() alloc and init comp_pkt state == hv_pcichild_ejecting Hyper-V sends VM_PKT_COMP msg hv_pci_onchannelcallback() retrieve address of comp_pkt 'free' comp_pkt and return comp_pkt->completion_func() Dexuan also showed how the crash can be triggered after introducing suitable delays in the driver code, thus validating the 'assumption' that the host can still normally respond to the guest's compose_msi request after the host has started to eject the PCI device. Fix the synchronization by leveraging the requestor lock as follows: - Before 'return'-ing in hv_compose_msi_msg(), remove the ID (while holding the requestor lock) associated to the completion packet. - Retrieve the address *and call ->completion_func() within a same (requestor) critical section in hv_pci_onchannelcallback(). Reported-by: Wei Hu <weh@microsoft.com> Reported-by: Dexuan Cui <decui@microsoft.com> Suggested-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220419122325.10078-7-parri.andrea@gmail.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2022-04-19 14:23:25 +02:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins <jakeo@microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-22 05:05:37 +00:00
PCI: Enable host bridge emulation for PCI_DOMAINS_GENERIC platforms The ability to emulate a host bridge is useful not only for hardware PCI controllers like CONFIG_VMD, or virtual PCI controllers like CONFIG_PCI_HYPERV, but also for test and development scenarios like CONFIG_SAMPLES_DEVSEC [1]. One stumbling block for defining CONFIG_SAMPLES_DEVSEC, a sample implementation of a platform TSM for PCI Device Security, is the need to accommodate PCI_DOMAINS_GENERIC architectures alongside x86 [2]. In support of supplementing the existing CONFIG_PCI_BRIDGE_EMUL infrastructure for host bridges: * Introduce pci_bus_find_emul_domain_nr() as a common way to find a free PCI domain number whether that is to reuse the existing dynamic allocation code in the !ACPI case, or to assign an unused domain above the last ACPI segment. * Convert pci-hyperv to the new allocator so that the PCI core can unconditionally assume that bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET is the dynamically allocated case. A follow on patch can also convert vmd to the new scheme. Currently vmd is limited to CONFIG_PCI_DOMAINS_GENERIC=n (x86) so, unlike pci-hyperv, it does not immediately conflict with this new pci_bus_find_emul_domain_nr() mechanism. Link: http://lore.kernel.org/174107249038.1288555.12362100502109498455.stgit@dwillia2-xfh.jf.intel.com [1] Reported-by: Suzuki K Poulose <suzuki.poulose@arm.com> Closes: http://lore.kernel.org/20250311144601.145736-3-suzuki.poulose@arm.com [2] Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com> Tested-by: Michael Kelley <mhklinux@outlook.com> Reviewed-by: Michael Kelley <mhklinux@outlook.com> Cc: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> Cc: Rob Herring <robh@kernel.org> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Wei Liu <wei.liu@kernel.org> Cc: Dexuan Cui <decui@microsoft.com> Link: https://patch.msgid.link/20251024224622.1470555-2-dan.j.williams@intel.com
2025-10-24 15:46:21 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: Enable host bridge emulation for PCI_DOMAINS_GENERIC platforms The ability to emulate a host bridge is useful not only for hardware PCI controllers like CONFIG_VMD, or virtual PCI controllers like CONFIG_PCI_HYPERV, but also for test and development scenarios like CONFIG_SAMPLES_DEVSEC [1]. One stumbling block for defining CONFIG_SAMPLES_DEVSEC, a sample implementation of a platform TSM for PCI Device Security, is the need to accommodate PCI_DOMAINS_GENERIC architectures alongside x86 [2]. In support of supplementing the existing CONFIG_PCI_BRIDGE_EMUL infrastructure for host bridges: * Introduce pci_bus_find_emul_domain_nr() as a common way to find a free PCI domain number whether that is to reuse the existing dynamic allocation code in the !ACPI case, or to assign an unused domain above the last ACPI segment. * Convert pci-hyperv to the new allocator so that the PCI core can unconditionally assume that bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET is the dynamically allocated case. A follow on patch can also convert vmd to the new scheme. Currently vmd is limited to CONFIG_PCI_DOMAINS_GENERIC=n (x86) so, unlike pci-hyperv, it does not immediately conflict with this new pci_bus_find_emul_domain_nr() mechanism. Link: http://lore.kernel.org/174107249038.1288555.12362100502109498455.stgit@dwillia2-xfh.jf.intel.com [1] Reported-by: Suzuki K Poulose <suzuki.poulose@arm.com> Closes: http://lore.kernel.org/20250311144601.145736-3-suzuki.poulose@arm.com [2] Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com> Tested-by: Michael Kelley <mhklinux@outlook.com> Reviewed-by: Michael Kelley <mhklinux@outlook.com> Cc: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> Cc: Rob Herring <robh@kernel.org> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Wei Liu <wei.liu@kernel.org> Cc: Dexuan Cui <decui@microsoft.com> Link: https://patch.msgid.link/20251024224622.1470555-2-dan.j.williams@intel.com
2025-10-24 15:46:21 -07:00
PCI: Enable host bridge emulation for PCI_DOMAINS_GENERIC platforms The ability to emulate a host bridge is useful not only for hardware PCI controllers like CONFIG_VMD, or virtual PCI controllers like CONFIG_PCI_HYPERV, but also for test and development scenarios like CONFIG_SAMPLES_DEVSEC [1]. One stumbling block for defining CONFIG_SAMPLES_DEVSEC, a sample implementation of a platform TSM for PCI Device Security, is the need to accommodate PCI_DOMAINS_GENERIC architectures alongside x86 [2]. In support of supplementing the existing CONFIG_PCI_BRIDGE_EMUL infrastructure for host bridges: * Introduce pci_bus_find_emul_domain_nr() as a common way to find a free PCI domain number whether that is to reuse the existing dynamic allocation code in the !ACPI case, or to assign an unused domain above the last ACPI segment. * Convert pci-hyperv to the new allocator so that the PCI core can unconditionally assume that bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET is the dynamically allocated case. A follow on patch can also convert vmd to the new scheme. Currently vmd is limited to CONFIG_PCI_DOMAINS_GENERIC=n (x86) so, unlike pci-hyperv, it does not immediately conflict with this new pci_bus_find_emul_domain_nr() mechanism. Link: http://lore.kernel.org/174107249038.1288555.12362100502109498455.stgit@dwillia2-xfh.jf.intel.com [1] Reported-by: Suzuki K Poulose <suzuki.poulose@arm.com> Closes: http://lore.kernel.org/20250311144601.145736-3-suzuki.poulose@arm.com [2] Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Suzuki K Poulose <suzuki.poulose@arm.com> Tested-by: Michael Kelley <mhklinux@outlook.com> Reviewed-by: Michael Kelley <mhklinux@outlook.com> Cc: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> Cc: Rob Herring <robh@kernel.org> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Wei Liu <wei.liu@kernel.org> Cc: Dexuan Cui <decui@microsoft.com> Link: https://patch.msgid.link/20251024224622.1470555-2-dan.j.williams@intel.com
2025-10-24 15:46:21 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Fix hibernation in case interrupts are not re-created pci_restore_msi_state() directly writes the MSI/MSI-X related registers via MMIO. On a physical machine, this works perfectly; for a Linux VM running on a hypervisor, which typically enables IOMMU interrupt remapping, the hypervisor usually should trap and emulate the MMIO accesses in order to re-create the necessary interrupt remapping table entries in the IOMMU, otherwise the interrupts can not work in the VM after hibernation. Hyper-V is different from other hypervisors in that it does not trap and emulate the MMIO accesses, and instead it uses a para-virtualized method, which requires the VM to call hv_compose_msi_msg() to notify the hypervisor of the info that would be passed to the hypervisor in the case of the trap-and-emulate method. This is not an issue to a lot of PCI device drivers, which destroy and re-create the interrupts across hibernation, so hv_compose_msi_msg() is called automatically. However, some PCI device drivers (e.g. the in-tree GPU driver nouveau and the out-of-tree Nvidia proprietary GPU driver) do not destroy and re-create MSI/MSI-X interrupts across hibernation, so hv_pci_resume() has to call hv_compose_msi_msg(), otherwise the PCI device drivers can no longer receive interrupts after the VM resumes from hibernation. Hyper-V is also different in that chip->irq_unmask() may fail in a Linux VM running on Hyper-V (on a physical machine, chip->irq_unmask() can not fail because unmasking an MSI/MSI-X register just means an MMIO write): during hibernation, when a CPU is offlined, the kernel tries to move the interrupt to the remaining CPUs that haven't been offlined yet. In this case, hv_irq_unmask() -> hv_do_hypercall() always fails because the vmbus channel has been closed: here the early "return" in hv_irq_unmask() means the pci_msi_unmask_irq() is not called, i.e. the desc->masked remains "true", so later after hibernation, the MSI interrupt always remains masked, which is incorrect. Refer to cpu_disable_common() -> fixup_irqs() -> irq_migrate_all_off_this_cpu() -> migrate_one_irq(): static bool migrate_one_irq(struct irq_desc *desc) { ... if (maskchip && chip->irq_mask) chip->irq_mask(d); ... err = irq_do_set_affinity(d, affinity, false); ... if (maskchip && chip->irq_unmask) chip->irq_unmask(d); Fix the issue by calling pci_msi_unmask_irq() unconditionally in hv_irq_unmask(). Also suppress the error message for hibernation because the hypercall failure during hibernation does not matter (at this time all the devices have been frozen). Note: the correct affinity info is still updated into the irqdata data structure in migrate_one_irq() -> irq_do_set_affinity() -> hv_set_affinity(), so later when the VM resumes, hv_pci_restore_msi_state() is able to correctly restore the interrupt with the correct affinity. Link: https://lore.kernel.org/r/20201002085158.9168-1-decui@microsoft.com Fixes: ac82fc832708 ("PCI: hv: Add hibernation support") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Jake Oshins <jakeo@microsoft.com>
2020-10-02 01:51:58 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Acked-by: Lorenzo Pieralisi <lpieralisi@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2023-06-14 21:44:51 -07:00
Drivers: hv: vmbus: Export hv_vmbus_exists() and use it in pci-hyperv With commit f84b21da3624 ("PCI: hv: Don't load the driver for baremetal root partition"), the bare metal Linux root partition won't use the pci-hyperv driver, but when a Linux VM runs on the Linux root partition, pci-hyperv's module_init function init_hv_pci_drv() can still run, e.g. in the case of CONFIG_PCI_HYPERV=y, even if the VMBus driver is not used in such a VM (i.e. the hv_vmbus driver's init function returns -ENODEV due to vmbus_root_device being NULL). In such a Linux VM, init_hv_pci_drv() runs with a side effect: the 3 hvpci_block_ops callbacks are set to functions that depend on hv_vmbus. Later, when the MLX driver in such a VM invokes the callbacks, e.g. in drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c: mlx5_hv_register_invalidate(), hvpci_block_ops.reg_blk_invalidate() is hv_register_block_invalidate() rather than a NULL function pointer, and hv_register_block_invalidate() assumes that it can find a struct hv_pcibus_device from pdev->bus->sysdata, which is false in such a VM. Consequently, hv_register_block_invalidate() -> get_pcichild_wslot() -> spin_lock_irqsave() may hang since it can be accessing an invalid spinlock pointer. Fix the issue by exporting hv_vmbus_exists() and using it in pci-hyperv: hv_root_partition() is true and hv_nested is false ==> hv_vmbus_exists() is false. hv_root_partition() is true and hv_nested is true ==> hv_vmbus_exists() is true. hv_root_partition() is false ==> hv_vmbus_exists() is true. While at it, rename vmbus_exists() to hv_vmbus_exists() to follow the convention that all public functions have the hv_ prefix; also change the return value's type from int to bool to make the code more readable; also move the two pr_info() calls. Reported-by: Mukesh Rathor <mrathor@linux.microsoft.com> Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Wei Liu <wei.liu@kernel.org>
2026-04-09 14:52:32 -07:00