Re: [PATCH] hw/nvme: Add iothread support

2022-08-26 Thread Klaus Jensen
On Aug 26 16:15, Jinhao Fan wrote: > Sure. I’ve already reworked this iothread patch upon the new irqfd > patch. I think I can post a v2 patch today. Do you mean I include > irqfd v3 in the new iothread patch series? > Yes, please include irqfd-v3 in the series. signature.asc Description: PGP s

Re: [PATCH] hw/nvme: Add iothread support

2022-08-26 Thread Jinhao Fan
Sure. I’ve already reworked this iothread patch upon the new irqfd patch. I think I can post a v2 patch today. Do you mean I include irqfd v3 in the new iothread patch series? 发自我的iPhone > 在 2022年8月26日,15:12,Klaus Jensen 写道: > > On Jul 20 17:00, Jinhao Fan wrote: >> Add an option "iothread=x

Re: [PATCH] hw/nvme: Add iothread support

2022-08-26 Thread Klaus Jensen
On Jul 20 17:00, Jinhao Fan wrote: > Add an option "iothread=x" to do emulation in a seperate iothread. > This improves the performance because QEMU's main loop is responsible > for a lot of other work while iothread is dedicated to NVMe emulation. > Moreover, emulating in iothread brings the poten

Re: [PATCH] hw/nvme: Add iothread support

2022-07-27 Thread Klaus Jensen
On Jul 26 16:55, Jinhao Fan wrote: > > Hi Klaus and Keith, > > I just added support for interrupt masking. How can I test interrupt > masking? > I wondered if this might be possible to test this with a user-space VFIO-based driver, but VFIO does not export masking/unmasking on MSI/MSI-X through

Re: [PATCH] hw/nvme: Add iothread support

2022-07-26 Thread Jinhao Fan
at 10:56 AM, Jinhao Fan wrote: > at 2:07 AM, Keith Busch wrote: > >> MSI-x uses MMIO for masking, so there's no need for an NVMe specific way to >> mask these interrupts. You can just use the generic PCIe methods to clear the >> vector's enable bit. But no NVMe driver that I know of is making u

Re: [PATCH] hw/nvme: Add iothread support

2022-07-26 Thread Jinhao Fan
at 2:07 AM, Keith Busch wrote: > MSI-x uses MMIO for masking, so there's no need for an NVMe specific way to > mask these interrupts. You can just use the generic PCIe methods to clear the > vector's enable bit. But no NVMe driver that I know of is making use of these > either, though it should b

Re: [PATCH] hw/nvme: Add iothread support

2022-07-26 Thread Keith Busch
On Tue, Jul 26, 2022 at 11:32:57PM +0800, Jinhao Fan wrote: > at 10:45 PM, Keith Busch wrote: > > > On Tue, Jul 26, 2022 at 04:55:54PM +0800, Jinhao Fan wrote: > >> Hi Klaus and Keith, > >> > >> I just added support for interrupt masking. How can I test interrupt > >> masking? > > > > Are you a

Re: [PATCH] hw/nvme: Add iothread support

2022-07-26 Thread Jinhao Fan
at 10:45 PM, Keith Busch wrote: > On Tue, Jul 26, 2022 at 04:55:54PM +0800, Jinhao Fan wrote: >> Hi Klaus and Keith, >> >> I just added support for interrupt masking. How can I test interrupt >> masking? > > Are you asking about MSI masking? I don't think any drivers are using the > feature, so

Re: [PATCH] hw/nvme: Add iothread support

2022-07-26 Thread Keith Busch
On Tue, Jul 26, 2022 at 04:55:54PM +0800, Jinhao Fan wrote: > > Hi Klaus and Keith, > > I just added support for interrupt masking. How can I test interrupt > masking? Are you asking about MSI masking? I don't think any drivers are using the feature, so you'd need to modify one to test it. I can

Re: [PATCH] hw/nvme: Add iothread support

2022-07-26 Thread Jinhao Fan
at 5:00 PM, Jinhao Fan wrote: > Add an option "iothread=x" to do emulation in a seperate iothread. > This improves the performance because QEMU's main loop is responsible > for a lot of other work while iothread is dedicated to NVMe emulation. > Moreover, emulating in iothread brings the potentia

[PATCH] hw/nvme: Add iothread support

2022-07-20 Thread Jinhao Fan
Add an option "iothread=x" to do emulation in a seperate iothread. This improves the performance because QEMU's main loop is responsible for a lot of other work while iothread is dedicated to NVMe emulation. Moreover, emulating in iothread brings the potential of polling on SQ/CQ doorbells, which I