Re: [PATCH RFC] schedutil: Address the r/w ordering race in kthread

From: Joel Fernandes
Date: Tue May 22 2018 - 19:24:20 EST

Next message: Dexuan Cui: "[PATCH] PCI: hv: Fix a __local_bh_enable_ip warning in hv_compose_msi_msg()"
Previous message: Bo Chen: "[PATCH] e1000: check the return of pci_get_drvdata() in e1000_remove()"
In reply to: Joel Fernandes (Google): "[PATCH RFC] schedutil: Address the r/w ordering race in kthread"
Next in thread: Juri Lelli: "Re: [PATCH RFC] schedutil: Address the r/w ordering race in kthread"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Tue, May 22, 2018 at 04:50:28PM -0700, Joel Fernandes (Google) wrote:
> Currently there is a race in schedutil code for slow-switch single-CPU
> systems. Fix it by enforcing ordering the write to work_in_progress to
> happen before the read of next_freq.

Aargh, s/before/after/.

Commit log has above issue but code is Ok. Should I resend this patch or
are there any additional comments? thanks!

- Joel

[..]

Next message: Dexuan Cui: "[PATCH] PCI: hv: Fix a __local_bh_enable_ip warning in hv_compose_msi_msg()"
Previous message: Bo Chen: "[PATCH] e1000: check the return of pci_get_drvdata() in e1000_remove()"
In reply to: Joel Fernandes (Google): "[PATCH RFC] schedutil: Address the r/w ordering race in kthread"
Next in thread: Juri Lelli: "Re: [PATCH RFC] schedutil: Address the r/w ordering race in kthread"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]