On Fri, Sep 04, 2020 at 08:38:13AM +0200, Christoph Hellwig wrote:
> > Wait a sec... how is that supposed to build with X86_5LEVEL? Do you mean
> >
> > #define LOAD_TASK_SIZE_MINUS_N(n) \
> > ALTERNATIVE __stringify(mov $((1 << 47) - 4096 - (n)),%rdx), \
>
On Fri, Sep 04, 2020 at 03:55:10AM +0100, Al Viro wrote:
> On Thu, Sep 03, 2020 at 04:22:40PM +0200, Christoph Hellwig wrote:
>
> > diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
> > index c8a85b512796e1..94f7be4971ed04 100644
> > --- a/arch/x86/lib/getuser.
Applied with the recommendation from Michael folded in.
On Thu, Sep 03, 2020 at 01:57:39PM +0300, Andy Shevchenko wrote:
> > +{
> > + if (!dev)
> > + return (U32_MAX >> page_shift) + 1;
> > + return (dma_get_seg_boundary(dev) >> page_shift) + 1;
>
> Can it be better to do something like
> unsigned long boundary = dev ? dma_g
On Thu, Sep 03, 2020 at 05:49:09PM +0200, Christoph Hellwig wrote:
> On Thu, Sep 03, 2020 at 05:43:25PM +0200, Christophe Leroy wrote:
> >
> >
> > Le 03/09/2020 à 16:22, Christoph Hellwig a écrit :
> >> Stop providing the possibility to override the address space usin
On Thu, Sep 03, 2020 at 05:43:25PM +0200, Christophe Leroy wrote:
>
>
> Le 03/09/2020 à 16:22, Christoph Hellwig a écrit :
>> Stop providing the possibility to override the address space using
>> set_fs() now that there is no need for that any more.
>>
>>
On Thu, Sep 03, 2020 at 03:36:29PM +0100, Al Viro wrote:
> FWIW, vfs.git#for-next is always a merge of independent branches; I don't
> put stuff directly into #for-next - too easy to lose that way.
>
> IOW, that would be something like #base.set_fs, included into #for-next
> merge set. And I've n
On Thu, Sep 03, 2020 at 03:28:03PM +0100, Al Viro wrote:
> On Thu, Sep 03, 2020 at 04:22:28PM +0200, Christoph Hellwig wrote:
>
> > Besides x86 and powerpc I plan to eventually convert all other
> > architectures, although this will be a slow process, starting with the
> &
Stop providing the possibility to override the address space using
set_fs() now that there is no need for that any more.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/processor.h | 7
arch/powerpc/include/asm/thread_info.h
Provide __get_kernel_nofault and __put_kernel_nofault routines to
implement the maccess routines without messing with set_fs and without
opening up access to user space.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/include/asm/uaccess.h | 16
1 file changed, 16 insertions
: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/Kconfig| 3 +++
arch/alpha/Kconfig | 1 +
arch/arc/Kconfig| 1 +
arch/arm/Kconfig| 1 +
arch/arm64/Kconfig | 1 +
arch/c6x/Kconfig| 1 +
arch/csky/Kconfig | 1 +
arch/h8300/Kconfig | 1
hardcoded virtual address bits to escape
the fact that TASK_SIZE_MAX isn't actually a constant when 5-level
page tables are enabled.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/x86/Kconfig | 1 -
arch/x86/ia32/ia32_aout.c | 1 -
arch/x86/includ
.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/x86/include/asm/page_32_types.h | 4 ++--
arch/x86/include/asm/page_64_types.h | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/page_32_types.h
b/arch/x86/include/asm/page_32_types.h
At least for 64-bit this moves them closer to some of the defines
they are based on, and it prepares for using the TASK_SIZE_MAX
definition from assembly.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/x86/include/asm/page_32_types.h | 11 +++
arch/x86/include/asm
Once we can't manipulate the address limit, we also can't test what
happens when the manipulation is abused.
Signed-off-by: Christoph Hellwig
---
drivers/misc/lkdtm/bugs.c | 10 --
drivers/misc/lkdtm/core.c | 2 --
drivers/misc/lkd
We can't run the tests for userspace bitmap parsing if set_fs() doesn't
exist, and it is about to go away for x86, powerpc with other major
architectures to follow.
Signed-off-by: Christoph Hellwig
---
lib/test_bitmap.c | 91 +++
1 file c
bandwidth instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files. If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.
Signed-off-
ent semantics for messed up enough
drivers. Also fails the kernel access to them in that case.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
fs/read_write.c | 67 +++--
1 file changed, 42 insertions(+), 25 deletions(-)
diff --git a/fs/
This will allow proc files to implement iter read semantics.
Signed-off-by: Christoph Hellwig
---
fs/proc/inode.c | 53 ++---
include/linux/proc_fs.h | 1 +
2 files changed, 51 insertions(+), 3 deletions(-)
diff --git a/fs/proc/inode.c b/fs/proc
Hi all,
this series removes the last set_fs() used to force a kernel address
space for the uaccess code in the kernel read/write/splice code, and then
stops implementing the address space overrides entirely for x86 and
powerpc.
[Note to Linus: I'd like to get this into linux-next rather earlier
t
From: "Matthew Wilcox (Oracle)"
Using the read_iter/write_iter interfaces allows for in-kernel users
to set sysctls without using set_fs(). Also, the buffer is a string,
so give it the real type of 'char *', not void *.
Signed-off-by: Matthew Wilcox (Oracle)
Signed-off-b
Just return early on inode allocation failure.
Signed-off-by: Christoph Hellwig
---
fs/proc/inode.c | 72 +
1 file changed, 37 insertions(+), 35 deletions(-)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 28d6105e908e4c..016b1302cbabc0
Instead of providing a special no-compat version provide a special
compat version for operations with ->compat_ioctl.
Signed-off-by: Christoph Hellwig
---
fs/proc/inode.c | 10 --
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
in
On Wed, Sep 02, 2020 at 11:02:22AM -0700, Linus Torvalds wrote:
> I don't see why this change would make any difference.
Me neither, but while looking at a different project I did spot places
that actually do an access_ok with len 0, that's why I wanted him to
try.
That being said: Christophe are
On Wed, Sep 02, 2020 at 08:15:12AM +0200, Christophe Leroy wrote:
>> -return 0;
>> -return (size == 0 || size - 1 <= seg.seg - addr);
>> +if (addr >= TASK_SIZE_MAX)
>> +return false;
>> +if (size == 0)
>> +return false;
>
> __access_ok() was returning
On Tue, Sep 01, 2020 at 06:25:12PM +0100, Al Viro wrote:
> On Tue, Sep 01, 2020 at 07:13:00PM +0200, Christophe Leroy wrote:
>
> > 10.92% dd [kernel.kallsyms] [k] iov_iter_zero
>
> Interesting... Could you get an instruction-level profile inside
> iov_iter_zero(),
> along with the d
On Tue, Sep 01, 2020 at 11:57:37AM -0700, Kees Cook wrote:
> On Sat, Aug 29, 2020 at 11:24:06AM +0200, Christoph Hellwig wrote:
> > On Thu, Aug 27, 2020 at 11:06:28AM -0700, Linus Torvalds wrote:
> > > On Thu, Aug 27, 2020 at 8:00 AM Christoph Hellwig wrote:
> > &
On Tue, Sep 01, 2020 at 12:54:01AM -0700, Nicolin Chen wrote:
> Hi Christoph,
>
> On Tue, Sep 01, 2020 at 09:36:23AM +0200, Christoph Hellwig wrote:
> > I really don't like all the open coded smarts in the various drivers.
> > What do you think about a helper like the
I really don't like all the open coded smarts in the various drivers.
What do you think about a helper like the one in the untested patch
below (on top of your series). Also please include the original
segment boundary patch with the next resend so that the series has
the full context.
diff --git
Looks like since the start of this series we've grown new code to
use kernel_write on sysctl files based on boot parameters. The good
news is that this just means I need to resurrect the sysctl series
as all that work was done already.
On Sun, Aug 30, 2020 at 11:04:21AM +0200, Cédric Le Goater wrote:
> Hello,
>
> On 7/8/20 5:24 PM, Christoph Hellwig wrote:
> > Use the DMA API bypass mechanism for direct window mappings. This uses
> > common code and speed up the direct mapping case by avoiding indirect
&g
On Thu, Aug 27, 2020 at 11:15:12AM -0700, Linus Torvalds wrote:
> > SYM_FUNC_START(__put_user_2)
> > - ENTER
> > - mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
> > + LOAD_TASK_SIZE_MAX
> > sub $1,%_ASM_BX
>
> It's even more obvious here. We load a constant and then immediately
On Thu, Aug 27, 2020 at 11:06:28AM -0700, Linus Torvalds wrote:
> On Thu, Aug 27, 2020 at 8:00 AM Christoph Hellwig wrote:
> >
> > Once we can't manipulate the address limit, we also can't test what
> > happens when the manipulation is abused.
>
> Just r
On Thu, Aug 27, 2020 at 03:58:02PM +, David Laight wrote:
> Is there a real justification for that?
> For system calls supplying both methods makes sense to avoid
> the extra code paths for a simple read/write.
Al asked for it as two of our four in-tree instances do have weird
semantics, and w
> Diffstat:
Actually no diffstat here as David Howells pointed out. Here we go:
arch/Kconfig |3
arch/alpha/Kconfig |1
arch/arc/Kconfig |1
arch/arm/Kconfig |1
arch/arm64/Kconfig
Stop providing the possibility to override the address space using
set_fs() now that there is no need for that any more.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/processor.h | 7 ---
arch/powerpc/include/asm/thread_info.h
hardcoded virtual address bits to escape
the fact that TASK_SIZE_MAX isn't actually a constant when 5-level
page tables are enabled.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/x86/Kconfig | 1 -
arch/x86/ia32/ia32_aout.c | 1 -
arch/x86/includ
Provide __get_kernel_nofault and __put_kernel_nofault routines to
implement the maccess routines without messing with set_fs and without
opening up access to user space.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/include/asm/uaccess.h | 16
1 file changed, 16 insertions
.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/x86/include/asm/page_32_types.h | 4 ++--
arch/x86/include/asm/page_64_types.h | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/page_32_types.h
b/arch/x86/include/asm/page_32_types.h
At least for 64-bit this moves them closer to some of the defines
they are based on, and it prepares for using the TASK_SIZE_MAX
definition from assembly.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/x86/include/asm/page_32_types.h | 11 +++
arch/x86/include/asm
We can't run the tests for userspace bitmap parsing if set_fs() doesn't
exist.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
lib/test_bitmap.c | 10 --
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index df90
h bandwith instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files. If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.
Signed-off-
Once we can't manipulate the address limit, we also can't test what
happens when the manipulation is abused.
Signed-off-by: Christoph Hellwig
---
drivers/misc/lkdtm/bugs.c | 4
drivers/misc/lkdtm/usercopy.c | 4
2 files changed, 8 insertions(+)
diff --git a/drivers/
: Christoph Hellwig
Reviewed-by: Kees Cook
---
arch/Kconfig| 3 +++
arch/alpha/Kconfig | 1 +
arch/arc/Kconfig| 1 +
arch/arm/Kconfig| 1 +
arch/arm64/Kconfig | 1 +
arch/c6x/Kconfig| 1 +
arch/csky/Kconfig | 1 +
arch/h8300/Kconfig | 1
Hi all,
this series removes the last set_fs() used to force a kernel address
space for the uaccess code in the kernel read/write/splice code, and then
stops implementing the address space overrides entirely for x86 and
powerpc.
The file system part has been posted a few times, and the read/write
ent semantics for messed up enough
drivers. Also fails the kernel access to them in that case.
Signed-off-by: Christoph Hellwig
Reviewed-by: Kees Cook
---
fs/read_write.c | 67 +++--
1 file changed, 42 insertions(+), 25 deletions(-)
diff --git a/fs/
On Mon, Aug 17, 2020 at 08:23:11AM +, David Laight wrote:
> From: Christoph Hellwig
> > Sent: 17 August 2020 08:32
> >
> > Stop providing the possibility to override the address space using
> > set_fs() now that there is no need for that any more. To properly
&
On Fri, Aug 21, 2020 at 02:44:25PM +1000, Nicholas Piggin wrote:
> This is a generic kernel virtual memory mapper, not specific to ioremap.
lib/ioremap doesn't exist any more.
>
> Signed-off-by: Nicholas Piggin
> ---
> include/linux/vmalloc.h | 2 +
> mm/ioremap.c| 192 --
> static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long
> end,
> - phys_addr_t phys_addr, pgprot_t prot)
> + phys_addr_t phys_addr, pgprot_t prot, unsigned int
> max_page_shift)
> {
... and here.
On Fri, Aug 21, 2020 at 02:44:23PM +1000, Nicholas Piggin wrote:
> This will be moved to mm/ and used as a generic kernel virtual mapping
> function, so re-name it in preparation.
>
> Signed-off-by: Nicholas Piggin
> ---
> mm/ioremap.c | 55 ++--
>
On Fri, Aug 21, 2020 at 02:44:22PM +1000, Nicholas Piggin wrote:
> The vmalloc mapper operates on a struct page * array rather than a
> linear physical address, re-name it to make this distinction clear.
>
> Signed-off-by: Nicholas Piggin
> ---
> mm/vmalloc.c | 28
>
On Wed, Aug 19, 2020 at 09:16:59AM +0200, Christophe Leroy wrote:
> I made a test with only the first patch of your series: That's definitely
> the culprit. With only that patch applies, the duration is 6.64 seconds,
> that's a 25% degradation.
For the record: the first patch is:
mem: remo
On Tue, Aug 18, 2020 at 07:11:26PM -0300, Thiago Jung Bauermann wrote:
> POWER secure guests (i.e., guests which use the Protection Execution
> Facility) need to use SWIOTLB to be able to do I/O with the hypervisor, but
> they don't need the SWIOTLB memory to be in low addresses since the
> hypervi
On Tue, Aug 18, 2020 at 12:58:07PM -0700, Kees Cook wrote:
> On Tue, Aug 18, 2020 at 09:54:46PM +0200, Christoph Hellwig wrote:
> > On Tue, Aug 18, 2020 at 12:39:34PM -0700, Kees Cook wrote:
> > > On Mon, Aug 17, 2020 at 09:32:04AM +0200, Christoph Hellwig wrote:
> > >
On Tue, Aug 18, 2020 at 12:59:05PM -0700, Kees Cook wrote:
> > I didn't see a problem bisecting, do you have something particular in
> > mind?
>
> Oh, I misunderstood this patch to be a fix for compilation. Is this just
> a correctness fix?
It prepares for using the definition from assembly, whic
On Tue, Aug 18, 2020 at 12:44:49PM -0700, Kees Cook wrote:
> On Mon, Aug 17, 2020 at 09:32:09AM +0200, Christoph Hellwig wrote:
> > For 64-bit the only hing missing was a strategic _AC, and for 32-bit we
>
> typo: thing
>
> > need to use __PAGE_OFFSET instead of PAGE
On Tue, Aug 18, 2020 at 12:39:34PM -0700, Kees Cook wrote:
> On Mon, Aug 17, 2020 at 09:32:04AM +0200, Christoph Hellwig wrote:
> > default_file_splice_write is the last piece of generic code that uses
> > set_fs to make the uaccess routines operate on kernel pointers. It
&
On Tue, Aug 18, 2020 at 07:46:22PM +0200, Christophe Leroy wrote:
> I gave it a go on my powerpc mpc832x. I tested it on top of my newest
> series that reworks the 32 bits signal handlers (see
> https://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=196278) with
> the microbenchmark test
On Mon, Aug 17, 2020 at 06:46:58PM -0300, Thiago Jung Bauermann wrote:
> POWER secure guests (i.e., guests which use the Protection Execution
> Facility) need to use SWIOTLB to be able to do I/O with the hypervisor, but
> they don't need the SWIOTLB memory to be in low addresses since the
> hypervi
On Sat, Aug 15, 2020 at 05:45:36PM -0300, Thiago Jung Bauermann wrote:
> POWER secure guests (i.e., guests which use the Protection Execution
> Facility) need to use SWIOTLB to be able to do I/O with the hypervisor, but
> they don't need the SWIOTLB memory to be in low addresses since the
> hypervi
On Mon, Aug 17, 2020 at 09:50:05AM +0200, Christophe Leroy wrote:
>
>
> Le 17/08/2020 à 09:32, Christoph Hellwig a écrit :
>> We can't run the tests for userspace bitmap parsing if set_fs() doesn't
>> exist.
>>
>> Signed-off-by: Christoph
Adding Linus as I forgot to add him to the patch bomb, sorry..
On Mon, Aug 17, 2020 at 09:32:01AM +0200, Christoph Hellwig wrote:
> Hi all,
>
> this series removes the last set_fs() used to force a kernel address
> space for the uaccess code in the kernel read/write/splice code, and
Stop providing the possibility to override the address space using
set_fs() now that there is no need for that any more.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/Kconfig | 1 -
arch/powerpc/include/asm/processor.h | 7 ---
arch/powerpc/include/asm/thread_info.h
Provide __get_kernel_nofault and __put_kernel_nofault routines to
implement the maccess routines without messing with set_fs and without
opening up access to user space.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/include/asm/uaccess.h | 16
1 file changed, 16 insertions
hardcoded virtual address bits to escape
the fact that TASK_SIZE_MAX isn't actually a constant when 5-level
page tables are enabled.
Signed-off-by: Christoph Hellwig
---
arch/x86/Kconfig | 1 -
arch/x86/ia32/ia32_aout.c | 1 -
arch/x86/include/asm/processor.h
.
Signed-off-by: Christoph Hellwig
---
arch/x86/include/asm/page_32_types.h | 4 ++--
arch/x86/include/asm/page_64_types.h | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/page_32_types.h
b/arch/x86/include/asm/page_32_types.h
index 26236925fb2c36
Hi all,
this series removes the last set_fs() used to force a kernel address
space for the uaccess code in the kernel read/write/splice code, and then
stops implementing the address space overrides entirely for x86 and
powerpc.
The file system part has been posted a few times, and the read/write
At least for 64-bit this moves them closer to some of the defines
they are based on, and it prepares for using the TASK_SIZE_MAX
definition from assembly.
Signed-off-by: Christoph Hellwig
---
arch/x86/include/asm/page_32_types.h | 11 +++
arch/x86/include/asm/page_64_types.h | 38
There is no good reason to implement both the traditional ->read and
->write as well as the iter based ops. So implement just the iter
based ones.
Suggested-by: Al Viro
Signed-off-by: Christoph Hellwig
---
drivers/char/mem.c | 16
1 file changed, 16 deletions(-)
diff -
: Christoph Hellwig
---
arch/Kconfig| 3 +++
arch/alpha/Kconfig | 1 +
arch/arc/Kconfig| 1 +
arch/arm/Kconfig| 1 +
arch/arm64/Kconfig | 1 +
arch/c6x/Kconfig| 1 +
arch/csky/Kconfig | 1 +
arch/h8300/Kconfig | 1 +
arch/hexagon/Kconfig
Once we can't manipulate the address limit, we also can't test what
happens when the manipulation is abused.
Signed-off-by: Christoph Hellwig
---
drivers/misc/lkdtm/bugs.c | 2 ++
drivers/misc/lkdtm/core.c | 4
drivers/misc/lkdtm/usercopy.c | 2 ++
3 files changed, 8
ent semantics for messed up enough
drivers. Also fails the kernel access to them in that case.
Signed-off-by: Christoph Hellwig
---
fs/read_write.c | 67 +++--
1 file changed, 42 insertions(+), 25 deletions(-)
diff --git a/fs/read_write.c b/fs/r
h bandwith instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files. If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.
Signed-off-
We can't run the tests for userspace bitmap parsing if set_fs() doesn't
exist.
Signed-off-by: Christoph Hellwig
---
lib/test_bitmap.c | 10 --
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index df903c53952bb9..49b1d25fbaf
On Thu, Aug 13, 2020 at 01:13:08PM +0100, Christoph Hellwig wrote:
> On Thu, Aug 13, 2020 at 10:12:00AM +, Christophe Leroy wrote:
> > -#ifndef CONFIG_PPC_8xx
> > +#if !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC_BOOK3S_32)
> > _GLOBAL(flush_instruction_cache
On Thu, Aug 13, 2020 at 10:12:00AM +, Christophe Leroy wrote:
> -#ifndef CONFIG_PPC_8xx
> +#if !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC_BOOK3S_32)
> _GLOBAL(flush_instruction_cache)
> #if defined(CONFIG_4xx)
> lis r3, KERNELBASE@h
> @@ -290,18 +289,11 @@ _GLOBAL(flush_instruc
Hi Stephen,
please drop my set_fs tree from linux-next. It is not going to be
merged for 5.9 in this form.
Thanks!
On Thu, Aug 06, 2020 at 08:50:20AM +, Christophe Leroy wrote:
> get_clean_sp() is only used in kernel/signal.c . Move it there.
>
> And GCC is smart enough to reduce the function when on PPC32, no
> need of a special PPC32 simple version.
What about just open coding it in the only caller, whi
Do you urgently need this? My plan for 5.10 is to rebased and submit
the remaining bits of this branch:
http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/set_fs-removal
which will kill off set_fs/get_fs entirely.
er memblock.memory with a call to memblock_phys_mem_size().
>
> Signed-off-by: Mike Rapoport
Looks good:
Reviewed-by: Christoph Hellwig
On Sat, Jul 18, 2020 at 10:17:14AM -0700, Guenter Roeck wrote:
> On Wed, Jul 08, 2020 at 05:24:47PM +0200, Christoph Hellwig wrote:
> > Avoid the overhead of the dma ops support for tiny builds that only
> > use the direct mapping.
> >
> > Signed-off-by:
On Mon, Jul 13, 2020 at 02:59:39PM +1000, Alexey Kardashevskiy wrote:
>
>
> On 09/07/2020 01:24, Christoph Hellwig wrote:
> > Several IOMMU drivers have a bypass mode where they can use a direct
> > mapping if the devices DMA mask is large enough. Add generic support
> &
On Fri, Jul 10, 2020 at 03:23:25PM +1000, Oliver O'Halloran wrote:
> This is largely prep work for supporting VFs in the 32bit MMIO window.
> This is an unfortunate necessity due to how the Linux BAR allocator
> handles BARs marked as non-prefetchable. The distinction
> between prefetch and non-pre
werpc/pseries/dma: Allow SWIOTLB")
Signed-off-by: Christoph Hellwig
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/device.h | 5 --
arch/powerpc/kernel/dma-iommu.c | 90 ---
3 files changed, 10 insertions(+), 86 deletions(-)
diff --git a/ar
Several IOMMU drivers have a bypass mode where they can use a direct
mapping if the devices DMA mask is large enough. Add generic support
to the core dma-mapping code to do that to switch those drivers to
a common solution.
Signed-off-by: Christoph Hellwig
---
include/linux/device.h | 8
Avoid the overhead of the dma ops support for tiny builds that only
use the direct mapping.
Signed-off-by: Christoph Hellwig
---
arch/alpha/Kconfig | 1 +
arch/arm/Kconfig| 1 +
arch/ia64/Kconfig | 1 +
arch/mips/Kconfig | 1 +
arch/parisc/Kconfig
bypass mode, and more of those are going to be
switched to the generic bypass soon.
Signed-off-by: Christoph Hellwig
---
include/linux/dma-direct.h | 92 --
kernel/dma/direct.c| 65 ---
2 files changed, 69 insertions(+), 88
: Christoph Hellwig
---
include/linux/dma-direct.h | 58 +
include/linux/dma-mapping.h | 247
kernel/dma/direct.c | 9 --
kernel/dma/mapping.c| 164
4 files changed, 244 insertions(+), 234 deletions(-)
diff
Hi all,
I've recently beeing chatting with Lu about using dma-iommu and
per-device DMA ops in the intel IOMMU driver, and one missing feature
in dma-iommu is a bypass mode where the direct mapping is used even
when an iommu is attached to improve performance. The powerpc
code already has a simila
On Tue, Jul 07, 2020 at 10:43:10AM +1000, Alexey Kardashevskiy wrote:
> Any luck there? I'd really like to cross this off my todo list :) Thanks,
We had another incident with new net code poking into dma internals
blocking this series. That is now sorted out, so the series is back
on track.
On Thu, Jul 02, 2020 at 10:10:10AM -0400, Qian Cai wrote:
> On Mon, Jun 29, 2020 at 09:39:45PM +0200, Christoph Hellwig wrote:
> > Split out a __submit_bio_noacct helper for the actual de-recursion
> > algorithm, and simplify the loop by using a continue when we can't
> >
Now that submit_bio_noacct has a decent blk-mq fast path there is no
more need for this bypass.
Signed-off-by: Christoph Hellwig
---
block/blk-core.c | 28
drivers/md/dm.c | 5 +
drivers/nvme/host/multipath.c | 2 +-
include/linux
For blk-mq drivers bios can only be inserted for the same queue. So
bypass the complicated sorting logic in __submit_bio_noacct with
a blk-mq simpler submission helper.
Signed-off-by: Christoph Hellwig
---
block/blk-core.c | 30 ++
1 file changed, 30 insertions
generic_make_request has always been very confusingly misnamed, so rename
it to submit_bio_noacct to make it clear that it is submit_bio minus
accounting and a few checks.
Signed-off-by: Christoph Hellwig
---
Documentation/block/biodoc.rst| 2 +-
.../fault-injection/fault
Split out a __submit_bio_noacct helper for the actual de-recursion
algorithm, and simplify the loop by using a continue when we can't
enter the queue for a bio.
Signed-off-by: Christoph Hellwig
---
block/blk-core.c | 143 +--
1 file change
derived pretty trivially from the bio.
Signed-off-by: Christoph Hellwig
---
Documentation/block/biodoc.rst| 2 +-
.../block/writeback_cache_control.rst | 2 +-
arch/m68k/emu/nfblock.c | 5 +-
arch/xtensa/platforms/iss/simdisk.c | 5
The variable is only used once, so just open code the bio_sector()
there.
Signed-off-by: Christoph Hellwig
---
block/blk-core.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 37435d0d433564..28f60985dc75cc 100644
--- a/block/blk
The queue can be trivially derived from the bio, so pass one less
argument.
Signed-off-by: Christoph Hellwig
---
block/blk-merge.c | 21 ++---
block/blk-mq.c| 2 +-
block/blk.h | 3 +--
drivers/block/drbd/drbd_req.c | 2
All registers disks must have a valid queue pointer, so don't bother to
log a warning for that case.
Signed-off-by: Christoph Hellwig
---
block/blk-core.c | 12 +---
1 file changed, 1 insertion(+), 11 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 95dca7453
The "generic_make_request: " prefix has no value, and will soon become
stale.
Signed-off-by: Christoph Hellwig
---
block/blk-core.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 76cfd5709f66cd..95dca74534ff73 100644
-
901 - 1000 of 2761 matches
Mail list logo
