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>
Make do_execve() take a const filename pointer so that kernel_execve() compiles
correctly on ARM:
arch/arm/kernel/sys_arm.c:88: warning: passing argument 1 of 'do_execve' discards qualifiers from pointer target type
This also requires the argv and envp arguments to be consted twice, once for
the pointer array and once for the strings the array points to. This is
because do_execve() passes a pointer to the filename (now const) to
copy_strings_kernel(). A simpler alternative would be to cast the filename
pointer in do_execve() when it's passed to copy_strings_kernel().
do_execve() may not change any of the strings it is passed as part of the argv
or envp lists as they are some of them in .rodata, so marking these strings as
const should be fine.
Further kernel_execve() and sys_execve() need to be changed to match.
This has been test built on x86_64, frv, arm and mips.
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Ralf Baechle <ralf@linux-mips.org>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
arch/tile: don't validate CROSS_COMPILE needlessly
arch/tile: export only COMMAND_LINE_SIZE to userspace.
arch/tile: rename ARCH_KMALLOC_MINALIGN to ARCH_DMA_MINALIGN
arch/tile: Rename the hweight() implementations to __arch_hweight()
arch/tile: extend syscall ABI to set r1 on return as well.
arch/tile: Various cleanups.
arch/tile: support backtracing on TILE-Gx
arch/tile: Fix a couple of issues with the COMPAT code for TILE-Gx.
arch/tile: Use separate, better minsec values for clocksource and sched_clock.
arch/tile: correct a bug in freeing bootmem by VA for the optional second initrd.
arch: tile: mm: pgtable.c: Removed duplicated #include
arch: tile: kernel/proc.c Removed duplicated #include
Add fanotify syscalls to <asm-generic/unistd.h>.
arch/tile: support new kunmap_atomic() naming convention.
tile: remove unused ISA_DMA_THRESHOLD define
Conflicts in arch/tile/configs/tile_defconfig (pick the mainline version
with the reduced defconfig).
With this change, the arch/tile Makefile will only check for a valid
combination of CROSS_COMPILE vs "uname -m" for a few common targets
that are typically the ones we get wrong (vmlinux, all, and modules).
The change handles the case of an empty "make" goal like "make all".
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
This fixes a failure in "make headers_check" for tile.
I hadn't realized this file was exported to userspace by default.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Until now, the tile architecture ABI for syscall return has just been
that r0 holds the return value, and an error is only signalled like it is
for kernel code, with a negative small number.
However, this means that in multiple places in userspace we end up writing
the same three-cycle idiom that tests for a small negative number for
error. It seems cleaner to instead move that code into the kernel, and
set r1 to hold zero on success or errno on failure; previously, r1 was
just zeroed on return from the kernel (to avoid leaking kernel state).
This way a single conditional branch after the syscall is sufficient
to test for the failure case. The number of cycles taken is the same,
but the error-checking code is in just one place, so total code size is
smaller, and random userspace syscall code is easier to understand.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
This change rolls up random cleanups not representing any actual bugs.
- Remove a stale CONFIG_ value from the default tile_defconfig
- Remove unused tns_atomic_xxx() family of methods from <asm/atomic.h>
- Optimize get_order() using Tile's "clz" instruction
- Fix a bad hypervisor upcall name (not currently used in Linux anyway)
- Use __copy_in_user_inatomic() name for consistency, and export it
- Export some additional hypervisor driver I/O upcalls and some homecache calls
- Remove the obfuscating MEMCPY_TEST_WH64 support code
- Other stray comment cleanups, #if 0 removal, etc.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
This functionality was stubbed out until recently. Now we support our
normal backtracing API on TILE-Gx as well as on TILE64/TILEPro.
This change includes a tweak to the instruction encoding caused by
adding addxli for compat mode.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
First, the siginfo preamble wasn't quite right; we need to indicate
that we are padding up to 4 ints of preamble for 64-bit code, and
then for compat mode we need to pad differently, using only 3 ints.
Second, the C ABI requires a save area of two registers, not two
pointers, since in compat mode we have 64-bit registers all of which
we need to save, even though we only have 32-bit VAs.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
We were using the same 5-sec minsec for the clocksource and sched_clock
that we were using for the clock_event_device. For the clock_event_device
that's exactly right since it has a short maximum countdown time.
But for sched_clock we want to avoid wraparound when converting from
ticks to nsec over a much longer window, so we force a shift of 10.
And for clocksource it seems dodgy to use a 5-sec minsec as well, so we
copy some other platforms and force a shift of 22.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Architectures implement dma_is_consistent() in different ways (some
misinterpret the definition of API in DMA-API.txt). So it hasn't been so
useful for drivers. We have only one user of the API in tree. Unlikely
out-of-tree drivers use the API.
Even if we fix dma_is_consistent() in some architectures, it doesn't look
useful at all. It was invented long ago for some old systems that can't
allocate coherent memory at all. It's better to export only APIs that are
definitely necessary for drivers.
Let's remove this API.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
dma_get_cache_alignment returns the minimum DMA alignment. Architectures
defines it as ARCH_DMA_MINALIGN (formally ARCH_KMALLOC_MINALIGN). So we
can unify dma_get_cache_alignment implementations.
Note that some architectures implement dma_get_cache_alignment wrongly.
dma_get_cache_alignment() should return the minimum DMA alignment. So
fully-coherent architectures should return 1. This patch also fixes this
issue.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
No need to define ISA_DMA_THRESHOLD
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
[cmetcalf@tilera.com: converted to a single-line #include file]
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
None of these changes fix any actual bugs, but are just various cleanups
that fell out along the way. In particular, some unused #defines and
includes are removed, PREFETCH_STRIDE is added (the default is right for
our shipping chips, but wrong for our next generation), our tile-specific
prefetching code is removed so the (identical) generic prefetching code
can be used instead, a comment is fixed to be proper GPL and not just a
"paste GPL here" token, a "//" comment is converted to "/* */", etc.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Architectures that handle DMA-non-coherent memory need to set
ARCH_KMALLOC_MINALIGN to make sure that kmalloc'ed buffer is DMA-safe:
the buffer doesn't share a cache with the others.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Let's use the standard L1_CACHE_ALIGN macro instead.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
This commit is primarily changes caused by reviewing "sparse"
and "checkpatch" output on our sources, so is somewhat noisy, since
things like "printk() -> pr_err()" (or whatever) throughout the
codebase tend to get tedious to read. Rather than trying to tease
apart precisely which things changed due to which type of code
review, this commit includes various cleanups in the code:
- sparse: Add declarations in headers for globals.
- sparse: Fix __user annotations.
- sparse: Using gfp_t consistently instead of int.
- sparse: removing functions not actually used.
- checkpatch: Clean up printk() warnings by using pr_info(), etc.;
also avoid partial-line printks except in bootup code.
- checkpatch: Use exposed structs rather than typedefs.
- checkpatch: Change some C99 comments to C89 comments.
In addition, a couple of minor other changes are rolled in
to this commit:
- Add support for a "raise" instruction to cause SIGFPE, etc., to be raised.
- Remove some compat code that is unnecessary when we fully eliminate
some of the deprecated syscalls from the generic syscall ABI.
- Update the tile_defconfig to reflect current config contents.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
This code is used in other places in our system than in Linux, so
to share it we now implement it as an inline function in our low-level
<arch> headers, and instantiate it in one file in Linux's arch/tile/lib.
The file is now cacheflush.c and is C code rather than the strangely-named
and assembler-implemented __invalidate_icache.S.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
This wasn't properly tested until the perf-event subsystem started
to get brought up under the tile architecture.
The bug caused bogus atomic64_cmpxchg() values to be returned,
among other things.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
The C file (tile-desc_{32,64}.c) was about 300KB before this change,
and is now shrunk down to 100K. The original file included support
for BFD in the binutils toolchain, which is not necessary in the
kernel; the kernel version only needs to include enough support to
enable the single-stepper and backtracer.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
This network (the "UDN") connects all the cpus on the chip in a
wormhole-routed dynamic network. Subrectangles of the chip can
be allocated by a "create" ioctl on /dev/hardwall, and then to access the
UDN in that rectangle, tasks must perform an "activate" ioctl on that
same file object after affinitizing themselves to a single cpu in
the region. Sending a wormhole-routed message that tries to leave
that subrectangle causes all activated tasks to receive a SIGILL
(just as they would if they tried to access the UDN without first
activating themselves to a hardwall rectangle).
The original submission of this code to LKML had the driver
instantiated under /proc/tile/hardwall. Now we just use a character
device for this, conventionally /dev/hardwall. Some futures planning
for the TILE-Gx chip suggests that we may want to have other types of
devices that share the general model of "bind a task to a cpu, then
'activate' a file descriptor on a pseudo-device that gives access to
some hardware resource". As such, we are using a device rather
than, for example, a syscall, to set up and activate this code.
As part of this change, the compat_ptr() declaration was fixed and used
to pass the compat_ioctl argument to the normal ioctl. So far we limit
compat code to 2GB, so the difference between zero-extend and sign-extend
(the latter being correct, eventually) had been overlooked.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
This model is based on the on-chip interrupt model used by the
TILE-Gx next-generation hardware, and interacts much more cleanly
with the Linux generic IRQ layer.
The change includes modifications to the Tilera hypervisor, which
are reflected in the hypervisor headers in arch/tile/include/arch/.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
It turns out there is some variance on the calling conventions for
these syscalls, and <asm-generic/syscalls.h> is already the mechanism
used to handle this. Switch arch/tile over to using that mechanism and
tweak the calling conventions for a couple of tile syscalls to match
<asm-generic/syscalls.h>.
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
This change is the core kernel support for TILEPro and TILE64 chips.
No driver support (except the console driver) is included yet.
This includes the relevant Linux headers in asm/; the low-level
low-level "Tile architecture" headers in arch/, which are
shared with the hypervisor, etc., and are build-system agnostic;
and the relevant hypervisor headers in hv/.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Reviewed-by: Paul Mundt <lethal@linux-sh.org>
