All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Earlier in this function we set the last byte of "buf" to NULL so we
always hit the break statement and "i" is never equal to NAME_MAX_LEN.
This patch doesn't change how the driver works but it silences a Smatch
warning and it makes it clearer that we don't write past the end of the
array.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
warning: symbol 'filter_fops' was not declared. Should it be static?
Signed-off-by: Thiago Farina <tfransosi@gmail.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
There is no need to perform full BIDIR sync (copying the buffers in case
of swiotlb and similar schemes) if we know that the owner (CPU or device)
hasn't altered the data.
Addresses the false-positive reported at
http://bugzilla.kernel.org/show_bug.cgi?id=14169
Signed-off-by: Krzysztof Halasa <khc@pm.waw.pl>
Cc: David Miller <davem@davemloft.net>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Stephen Rothwell reported the following build warning:
lib/dma-debug.c: In function 'dma_debug_device_change':
lib/dma-debug.c:680: warning: 'return' with no value, in function returning non-void
Introduced by commit f797d9881b
("dma-debug: Do not add notifier when dma debugging is disabled").
Return 0 [notify-done] when disabled. (this is standard bus notifier behavior.)
Signed-off-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@kernel.org>
LKML-Reference: <20091231125624.GA14666@liondog.tnic>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If CONFIG_HAVE_DMA_API_DEBUG is defined and "dma_debug=off" is
specified on the kernel command line, when you detach a driver from a
device you can cause the following NULL pointer dereference:
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<c0580d35>] dma_debug_device_change+0x5d/0x117
The problem is that the dma_debug_device_change notifier function is
added to the bus notifier chain even though the dma_entry_hash array
was never initialized. If dma debugging is disabled, this patch both
prevents dma_debug_device_change notifiers from being added to the
chain, and additionally ensures that the dma_debug_device_change
notifier function is a no-op.
Cc: stable@kernel.org
Signed-off-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
When PAE is enabled in the kernel configuration the size of
phys_addr_t differs from the size of a void pointer. The gcc
prints a warning about that in dma-debug code.
This patch fixes the warning by converting the output to
unsigned long long instead of a pointer.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
While it's debatable whether or not a NULL device argument to
the DMA API functions is valid... since it certainly isn't
valid on devices with an IOMMU... dma-debug really shouldn't be
dereferencing null pointers either.
Guard against that in err_printk and the driver_filter
functions. A Fedora rawhide user was seeing this in one of the
dvb drivers resulting in an oops on boot.
[ A patch has been sent for testing to the driver, but I feel
the dma debugging support should be fixed as well. (There's
still a pile of legacy garbage in the kernel passing null
pointers to dma_{alloc,free}_*. :( ]
Signed-off-by: Kyle McMartin <kyle@redhat.com>
Cc: mchehab@infradead.org
Cc: Joerg Roedel <joerg.roedel@amd.com>
LKML-Reference: <20090820011708.GP25206@bombadil.infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Linus noticed how unclean and buggy the overlap() function is:
- It uses convoluted (and bug-causing) positive checks for
range overlap - instead of using a more natural negative
check.
- Even the positive checks are buggy: a positive intersection
check has four natural cases while we checked only for three,
missing the (addr < start && addr2 == end) case for example.
- The variables are mis-named, making it non-obvious how the
check was done.
- It needlessly uses u64 instead of unsigned long. Since these
are kernel memory pointers and we explicitly exclude highmem
ranges anyway we cannot ever overflow 32 bits, even if we
could. (and on 64-bit it doesnt matter anyway)
All in one, this function needs a total revamp. I used Linus's
suggestions minus the paranoid checks (we cannot overflow really
because if we get totally bad DMA ranges passed far more things
break in the systems than just DMA debugging). I also fixed a
few other small details i noticed.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Alan Cox reported that lockdep runs out of its stack-trace entries
with certain configs:
BUG: MAX_STACK_TRACE_ENTRIES too low
This happens because there are 1024 hash buckets, each with a
separate lock. Lockdep puts each lock into a separate lock class and
tracks them independently.
But in reality we never take more than one of the buckets, so they
really belong into a single lock-class. Annotate the has bucket lock
init accordingly.
[ Impact: reduce the lockdep footprint of dma-debug ]
Reported-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch fixes a bug in the overlap function which returned true if
one region ends exactly before the second region begins. This is no
overlap but the function returned true in that case.
Cc: stable@kernel.org
Reported-by: Andrew Randrianasulu <randrik@mail.ru>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The current code is not very careful when it builds reference
dma_debug_entries which get passed to hash_bucket_find(). But since this
function changed to a best-fit algorithm these entries have to be more
acurate. This patch adds this higher level of accuracy.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
If we don't check for sg_call_ents the hash_bucket_find function might
still return the wrong dma_debug_entry for sg mappings.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch makes the driver_filter function more readable by
reorganizing the code. The removal of a code code block to an upper
indentation level makes hard-to-read line-wraps unnecessary.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
There is no need to disable/enable irqs on each loop iteration. Just
disable irqs for the whole time the loop runs.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The pr_* macros are shorter than the old printk(KERN_ ...) variant.
Change the dma-debug code to use the new macros and save a few
unnecessary line breaks. If lines don't break the source code can also
be grepped more easily.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch changes the recent updates to dma-debug to conform with
coding style guidelines of Linux and the -tip tree.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Last patch series introduced some new comment which does not fit the
Kernel comment style guidelines. Fix it with this patch.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Some device drivers map the same physical address multiple times to a
dma address. Without an IOMMU this results in the same dma address being
put into the dma-debug hash multiple times. With a first-fit match in
hash_bucket_find() this function may return the wrong dma_debug_entry.
This can result in false positive warnings. This patch fixes it by
changing the first-fit behavior of hash_bucket_find() into a best-fit
algorithm.
Reported-by: Torsten Kaiser <just.for.lkml@googlemail.com>
Reported-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: lethal@linux-sh.org
Cc: just.for.lkml@googlemail.com
Cc: hancockrwd@gmail.com
Cc: jens.axboe@oracle.com
Cc: bharrosh@panasas.com
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@kernel.org>
LKML-Reference: <20090605104132.GE24836@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds the dma-api/driver_filter file to debugfs. The root user
can write a driver name into this file to see only dma-api errors for
that particular driver in the kernel log. Writing an empty string to
that file disables the driver filter.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch adds the state variables for the driver filter and a function
to check if the filter is enabled and matches to the current device. The
check is built into the err_printk function.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
DMA-mapping.txt says that debug_dma_sync_sg family must be called with
the _same_ one you passed into the dma_map_sg call, it should _NOT_ be
the 'count' value _returned_ from the dma_map_sg call.
debug_dma_sync_sg_for_cpu and debug_dma_sync_sg_for_device can't
handle this properly; they need to use the sg_mapped_ents in struct
dma_debug_entry as debug_dma_unmap_sg() does.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
debug_dma_map_sg() and debug_dma_unmap_sg() use length in struct
scatterlist while debug_dma_sync_sg_for_cpu() and
debug_dma_sync_sg_for_device() use dma_length. This causes bugs
warnings on some IOMMU implementations since these values are not
same; the length doesn't represent the dma length.
We always need to use sg_dma_len() accessor to get the dma length of a
scatterlist entry.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Architectures might not have dma_address in struct scatterlist (PARISC
doesn't). Directly accessing to dma_address in struct scatterlist is
wrong; we need to use sg_dma_address() accesssor instead.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The feature needs some more work because the notfier which is used to
check for pending allocations is called before the device drivers
->remove() function. Therefore this feature reports false positives.
A real fix for this issue is to introduce a new notifier event which sent
_after_ the driver has deinitialized itself. That will done for the next
kernel version.
[ Impact: reduce the scope of CONFIG_DMA_API_DEBUG=y checks ]
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: iommu@lists.linux-foundation.org
LKML-Reference: <1240576557-22442-1-git-send-email-joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We use a static value for the number of dma_debug_entries. It can be
overwritten by a kernel command line option.
Some IOMMUs (e.g. GART) can't set an appropriate value by a kernel
command line option because they can't know such value until they
finish initializing up their hardware.
This patch adds dma_debug_resize_entries() enables IOMMUs to adjust
the number of dma_debug_entries anytime.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: fujita.tomonori@lab.ntt.co.jp
Cc: akpm@linux-foundation.org
LKML-Reference: <20090415182234R.fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix printk format warnings in dma-debug:
lib/dma-debug.c:645: warning: format '%016llx' expects type 'long long unsigned int', but argument 6 has type 'dma_addr_t'
lib/dma-debug.c:662: warning: format '%016llx' expects type 'long long unsigned int', but argument 6 has type 'dma_addr_t'
lib/dma-debug.c:676: warning: format '%016llx' expects type 'long long unsigned int', but argument 6 has type 'dma_addr_t'
lib/dma-debug.c:686: warning: format '%016llx' expects type 'long long unsigned int', but argument 6 has type 'dma_addr_t'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Impact: extend on-kernel-stack DMA debug checks to all !highmem pages
We only checked dma_map_single() - extend it to dma_map_page()
and dma_map_sg() as well.
Also, fix dma_map_single() corner case bug: make sure we dont
stack-check highmem (not mapped) pages.
Reported-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: iommu@lists.linux-foundation.org
LKML-Reference: <1237818908-26516-1-git-send-email-joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: allow architectures to monitor busses for dma mem leakage
This patch adds checking code to detect if a device has pending DMA
operations when it is about to be unbound from its device driver.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Impact: get notified if a device dma maps illegal areas
This patch adds a check to print a warning message when a device driver
tries to map a memory area from the kernel text segment or rodata.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Impact: saves stacktrace of a dma mapping and prints it if there is an error
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This adds a function to dump the DMA mappings that the debugging code is
aware of -- either for a single device, or for _all_ devices.
This can be useful for debugging -- sticking a call to it in the DMA
page fault handler, for example, to see if the faulting address _should_
be mapped or not, and hence work out whether it's IOMMU bugs we're
seeing, or driver bugs.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
