Re: [PATCH] x86: enable swiotlb for > 4GiG ram on 32-bit kernels

[Ingo Molnar <mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>]

* tedheadster <tedheadster-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:

> On Sun, Oct 14, 2018 at 3:52 AM Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org> wrote:
> >
> > We already build the swiotlb code for 32b-t kernels with PAE support,
> > but the code to actually use swiotlb has only been enabled for 64-bit
> > kernel for an unknown reason.
> >
> > Before Linux 4.18 we papers over this fact because the networking code,
> > the scsi layer and some random block drivers implenented their own
> > bounce buffering scheme.
> >
> > Fixes: 21e07dba ("scsi: reduce use of block bounce buffers")
> > Fixes: ab74cfeb ("net: remove the PCI_DMA_BUS_IS_PHYS check in illegal_highdma")
> > Reported-by: tedheadster <tedheadster-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> > Tested-by: tedheadster <tedheadster-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> > ---
> >
> 
> Christoph,
>   this fix has causes performance to decrease dramatically. Kernel
> builds that used to take 10-15 minutes are now taking 45-60 minutes on
> the same machine.

Ok, this is way too severe regression, and because the two offending 
commits:

 Fixes: 21e07dba9fb1 ("scsi: reduce use of block bounce buffers")
 Fixes: ab74cfebafa3 ("net: remove the PCI_DMA_BUS_IS_PHYS check in illegal_highdma")

... are from half a year ago and are in v4.18 already. Fixes should not 
cause new regressions in any case.

So I've removed this patch from tip:x86/urgent for now, could you please 
re-apply it when you do your testing? I've attached it below.

Thanks,

	Ingo

===================>
>From 6f3bc8028570e4c326030e8795dbcd57c561b723 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Date: Sun, 14 Oct 2018 09:52:08 +0200
Subject: [PATCH] x86/swiotlb: Enable swiotlb for > 4GiG ram on 32-bit kernels

We already build the swiotlb code for 32b-t kernels with PAE support,
but the code to actually use swiotlb has only been enabled for 64-bit
kernel for an unknown reason.

Before Linux 4.18 we paper over this fact because the networking code,
the scsi layer and some random block drivers implemented their own
bounce buffering scheme.

Fixes: 21e07dba9fb1 ("scsi: reduce use of block bounce buffers")
Fixes: ab74cfebafa3 ("net: remove the PCI_DMA_BUS_IS_PHYS check in illegal_highdma")
Reported-by: Matthew Whitehead <tedheadster-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Signed-off-by: Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
Tested-by: Matthew Whitehead <tedheadster-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Cc: konrad.wilk-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org
Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
Cc: stable-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Link: https://lkml.kernel.org/r/20181014075208.2715-1-hch-jcswGhMUV9g@public.gmane.org
---
 arch/x86/kernel/pci-swiotlb.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 661583662430..71c0b01d93b1 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -42,10 +42,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
 int __init pci_swiotlb_detect_4gb(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-#ifdef CONFIG_X86_64
 	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
 		swiotlb = 1;
-#endif
 
 	/*
 	 * If SME is active then swiotlb will be set to 1 so that bounce