login
Login
/
Register
Search
Search this site:
Forums
News
Blogs
Features
Site
Home
»
Mailing list archives
»
linux-kernel
»
2007
»
April
»
2
Re: drm + 4GB RAM + swiotlb = drm craps out
view
thread
Previous message: [
thread
] [
date
] [
author
]
Next message: [
thread
] [
date
] [
author
]
[view in full thread]
From: David Miller
Subject:
Re: drm + 4GB RAM + swiotlb = drm craps out
Date: Sunday, April 1, 2007 - 10:24 pm
From: "Dave Airlie" <airlied@gmail.com> Date: Mon, 2 Apr 2007 15:15:48 +1000
quoted text
> > Perhaps we'll have to create something ugly like vmalloc_nobounce(). > > > > Remind me again why you're ending up with swiotlb'd pages? > > vmalloc_32() uses GFP_KERNEL which should use entirely lowmem and thus > > RAM below 4GB and not anything which should need bounce buffering. > > On a 64-bit machine GFP_KERNEL can give me any memory... it all works > fine on 32-bit highmem kernel as I don't get highmem... I really need > __GFP_DMA32 memory but we don't have a generic allocator that gives > this out that I can see..
That clears things up thanks. Perhaps the other uses of vmalloc_32() want GFP_32 semantics too, although I didn't check. -
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to
majordomo@vger.kernel.org
More majordomo info at
http://vger.kernel.org/majordomo-info.html
Please read the FAQ at
http://www.tux.org/lkml/
Previous message: [
thread
] [
date
] [
author
]
Next message: [
thread
] [
date
] [
author
]
Messages in current thread:
drm + 4GB RAM + swiotlb = drm craps out
, Dave Airlie
, (Sun Apr 1, 4:44 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, David Miller
, (Sun Apr 1, 8:11 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Dave Airlie
, (Sun Apr 1, 9:08 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, David Miller
, (Sun Apr 1, 10:08 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Dave Airlie
, (Sun Apr 1, 10:15 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, David Miller
, (Sun Apr 1, 10:24 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Dave Airlie
, (Sun Apr 1, 10:38 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Andi Kleen
, (Sun Apr 1, 11:27 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Andi Kleen
, (Sun Apr 1, 11:40 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Dave Airlie
, (Sun Apr 1, 11:52 pm)
Re: drm + 4GB RAM + swiotlb = drm craps out
, Andi Kleen
, (Sun Apr 1, 11:55 pm)
Navigation
Mailing list archives
Recent posts
Popular discussions
linux-kernel
:
David Lang
Re: [patch] MTD: fix DOC2000/2001/2001PLUS build error
Steven Rostedt
Re: [PATCH] input: Fix interrupt enable in i8042_ctr when enabling interrupt fails
Linus Torvalds
Re: [patch] epoll use a single inode ...
David Miller
Re: tg3: unable to handle null pointer dereference
Frank Seidel
Re: [RFC 13/13] Char: nozomi, cleanup read and write
git-commits-head
:
Linux Kernel Mailing List
amba: struct device - replace bus_id with dev_name(), dev_set_name()
Linux Kernel Mailing List
cpumask: make irq_set_affinity() take a const struct cpumask
Linux Kernel Mailing List
cgroups: fix probable race with put_css_set[_taskexit] and find_css_set
Linux Kernel Mailing List
[libata] Export ata_pio_queue_task() so that it can be used from sata_mv.
Linux Kernel Mailing List
[ARM] 5209/1: metronomefb: changes to use platform framebuffer
git
:
Junio C Hamano
Re: mingw, windows, crlf/lf, and git
Junio C Hamano
Re: [PATCH 1/2] Teach git-describe to display distances from tags.
Daniel Barkalow
Re: git and mtime
Linus Torvalds
Re: [PATCH] Teach 'git pull' the '--rebase' option
Alex Riesen
Re: Easy shell question: how to make a script killing all his childs when killed?
freebsd-current
:
Mark Linimon
Why the FreeBSD license will not be changing
Michael Moll
Re: Unable to boot on ECS K7S5A
FreeBSD Tinderbox
[head tinderbox] failure on ia64/ia64
Jille Timmermans
Re: svn commit: r185482 - head/sys/dev/ath/ath_rate/sample
Hayer, Sukhjinder
8_CURRENT boot problem
linux-netdev
:
Timo Teräs
ip xfrm policy semantics
Andi Kleen
Re: [ANNOUNCE]: First release of nftables
John P Poet
Realtek 8111C transmit timed out
Jeff Garzik
Re: [PATCH] fix netxen_pci_tbl[] breakage
Jesper Dangaard Brouer
[PATCH] iputils: arping fails to set correct broadcast address
Colocation donated by:
Syndicate