- 22 Nov, 2005 26 commits
-
-
Eric Paris authored
If there are multiple updaters to /proc/sys/vm/nr_hugepages simultaneously it is possible for the nr_huge_pages variable to become incorrect. There is no locking in the set_max_huge_pages function around alloc_fresh_huge_page which is able to update nr_huge_pages. Two callers to alloc_fresh_huge_page could race against each other as could a call to alloc_fresh_huge_page and a call to update_and_free_page. This patch just expands the area covered by the hugetlb_lock to cover the call into alloc_fresh_huge_page. I'm not sure how we could say that a sysctl section is performance critical where more specific locking would be needed. My reproducer was to run a couple copies of the following script simultaneously while [ true ]; do echo 1000 > /proc/sys/vm/nr_hugepages echo 500 > /proc/sys/vm/nr_hugepages echo 750 > /proc/sys/vm/nr_hugepages echo 100 > /proc/sys/vm/nr_hugepages echo 0 > /proc/sys/vm/nr_hugepages done and then watch /proc/meminfo and eventually you will see things like HugePages_Total: 100 HugePages_Free: 109 After applying the patch all seemed well. Signed-off-by:
Eric Paris <eparis@redhat.com> Acked-by:
William Irwin <wli@holomorphy.com> Signed-off-by:
Andrew Morton <akpm@osdl.org> Signed-off-by:
Linus Torvalds <torvalds@osdl.org>
-
Antonino A. Daplas authored
Reported by: Wayne E. Harlan "[1.] One line summary of the problem: When the kernel option "vga=1" is used, additional tty's (alt+control+Fx with x=2,3,4,5, etc) do not provide the full 50 lines of output. The first one does have 50 lines, however. [2.] Full description of the problem/report: These addtitional tty's show only 39 lines plus the top pixel of the 40-th line. The remaining lines are black and not shown. Kernel version 2.6.13.4 does not show this problem." This bug is caused by using a stale font height value on vgacon_init. Booting with vga=1 gives an 80x50 screen with an 8x8 font. Somewhere during the initialization, the font was changed to 8x9 and the first vc was correctly resized to 80x44. However, the rest of the vc's were not allocated yet, and when they were subsequently initialized, they still used a font height of 8 (instead of 9) causing the mentioned bug. Fix by saving the new font height to vga_video_font_height. Signed-off-by:
Antonino Daplas <adaplas@pol.net> Signed-off-by:
-
Antonino A. Daplas authored
The shift value (amount to shift the bitmap so first pixel starts at origin(0,0)) is incorrect. This causes corrupted characters or a kernel crash if fontwidth is not divisible by 8 at 270 degrees, or fontheight not divisible by 8 at 180 degrees. Report and part of the fix contributed by Knut Petersen. Signed-off-by:
-
David Gibson authored
Currently, if a hugetlbfs is mounted without limits (the default), statfs() will return -1 for max/free/used blocks. This does not appear to be in line with normal convention: simple_statfs() and shmem_statfs() both return 0 in similar cases. Worse, it confuses the translation logic in put_compat_statfs(), causing it to return -EOVERFLOW on such a mount. This patch alters hugetlbfs_statfs() to return 0 for max/free/used blocks on a mount without limits. Note that we need the test in the patch below, rather than just using 0 in the sbinfo structure, because the -1 marked in the free blocks field is used internally to tell the Signed-off-by:
David Gibson <david@gibson.dropbear.id.au> Signed-off-by:
-
David Gibson authored
In fs/compat.c, whenever put_compat_statfs() returns an error, the containing syscall returns -EFAULT. This is presumably by analogy with the non-compat case, where any non-zero code from copy_to_user() should be translated into an EFAULT. However, put_compat_statfs() is also return -EOVERFLOW. The same applies for put_compat_statfs64(). This bug can be observed with a statfs() on a hugetlbfs directory. hugetlbfs, when mounted without limits reports available, free and total blocks as -1 (itself a bug, another patch coming). statfs() will mysteriously return EFAULT although it's parameters are perfectly valid addresses. This patch causes the compat versions of statfs() and statfs64() to correctly propogate the return values from put_compat_statfs() and put_compat_statfs64(). Signed-off-by:
-
Hugh Dickins authored
Earlier I unifdefed PageCompound, so that snd_pcm_mmap_control_nopage and others can give out a 0-order component of a higher-order page, which won't be mistakenly freed when zap_pte_range unmaps it. But many Bad page states reported a PG_reserved was freed after all: I had missed that we need to say __GFP_COMP to get compound page behaviour. Some of these higher-order pages are allocated by snd_malloc_pages, some by snd_malloc_dev_pages; or if SBUS, by sbus_alloc_consistent - but that has no gfp arg, so add __GFP_COMP into its sparc32/64 implementations. I'm still rather puzzled that DRM seems not to need a similar change. Signed-off-by:
Hugh Dickins <hugh@veritas.com> Signed-off-by:
-
Hugh Dickins authored
For copy_one_pte's print_bad_pte to show the task correctly (instead of "???"), dup_mmap must pass down parent vma rather than child vma. Signed-off-by:
-
Hugh Dickins authored
It used to be the case that PG_reserved pages were silently never freed, but in 2.6.15-rc1 they may be freed with a "Bad page state" message. We should work through such cases as they appear, fixing the code; but for now it's safer to issue the message without freeing the page, leaving PG_reserved set. Signed-off-by:
-
Hugh Dickins authored
It's strange enough to be looking out for anonymous pages in VM_UNPAGED areas, let's not insert the ZERO_PAGE there - though whether it would matter will depend on what we decide about ZERO_PAGE refcounting. But whereas do_anonymous_page may (exceptionally) be called on a VM_UNPAGED area, do_no_page should never be: just BUG_ON. Signed-off-by:
-
Hugh Dickins authored
copy_one_pte needs to copy the anonymous COWed pages in a VM_UNPAGED area, zap_pte_range needs to free them, do_wp_page needs to COW them: just like ordinary pages, not like the unpaged. But recognizing them is a little subtle: because PageReserved is no longer a condition for remap_pfn_range, we can now mmap all of /dev/mem (whether the distro permits, and whether it's advisable on this or that architecture, is another matter). So if we can see a PageAnon, it may not be ours to mess with (or may be ours from elsewhere in the address space). I suspect there's an entertaining insoluble self-referential problem here, but the page_is_anon function does a good practical job, and MAP_PRIVATE PROT_WRITE VM_UNPAGED will always be an odd choice. In updating the comment on page_address_in_vma, noticed a potential NULL dereference, in a path we don't actually take, but fixed it. Signed-off-by:
-
Hugh Dickins authored
Remove the BUG_ON(vma->vm_flags & VM_UNPAGED) from do_wp_page, and let it do Copy-On-Write without touching the VM_UNPAGED's page counts - but this is incomplete, because the anonymous page it inserts will itself need to be handled, here and in other functions - next patch. We still don't copy the page if the pfn is invalid, because the copy_user_highpage interface does not allow it. But that's not been a problem in the past: can be added in later if the need arises. Signed-off-by:
-
Hugh Dickins authored
There's one peculiar use of VM_RESERVED which the previous patch left behind: because VM_NONLINEAR's try_to_unmap_cluster uses vm_private_data as a swapout cursor, but should never meet VM_RESERVED vmas, it was a way of extending VM_NONLINEAR to VM_RESERVED vmas using vm_private_data for some other purpose. But that's an empty set - they don't have the populate function required. So just throw away those VM_RESERVED tests. But one more interesting in rmap.c has to go too: try_to_unmap_one will want to swap out an anonymous page from VM_RESERVED or VM_UNPAGED area. Signed-off-by:
-
Hugh Dickins authored
Although we tend to associate VM_RESERVED with remap_pfn_range, quite a few drivers set VM_RESERVED on areas which are then populated by nopage. The PageReserved removal in 2.6.15-rc1 changed VM_RESERVED not to free pages in zap_pte_range, without changing those drivers not to set it: so their pages just leak away. Let's not change miscellaneous drivers now: introduce VM_UNPAGED at the core, to flag the special areas where the ptes may have no struct page, or if they have then it's not to be touched. Replace most instances of VM_RESERVED in core mm by VM_UNPAGED. Force it on in remap_pfn_range, and the sparc and sparc64 io_remap_pfn_range. Revert addition of VM_RESERVED to powerpc vdso, it's not needed there. Is it needed anywhere? It still governs the mm->reserved_vm statistic, and special vmas not to be merged, and areas not to be core dumped; but could probably be eliminated later (the drivers are probably specifying it because in 2.4 it kept swapout off the vma, but in 2.6 we work from the LRU, which these pages don't get on). Use the VM_SHM slot for VM_UNPAGED, and define VM_SHM to 0: it serves no purpose whatsoever, and should be removed from drivers when we clean up. Signed-off-by:
-
Hugh Dickins authored
It looks like snd_xxx is not the only nopage to be using PageReserved as a way of holding a high-order page together: which no longer works, but is masked by our failure to free from VM_RESERVED areas. We cannot fix that bug without first substituting another way to hold the high-order page together, while farming out the 0-order pages from within it. That's just what PageCompound is designed for, but it's been kept under CONFIG_HUGETLB_PAGE. Remove the #ifdefs: which saves some space (out- of-line put_page), doesn't slow down what most needs to be fast (already using hugetlb), and unifies the way we handle high-order pages. Signed-off-by:
-
Hugh Dickins authored
Something noticed when studying use of VM_RESERVED in different drivers: snd_usX2Y_hwdep_pcm_vm_nopage omitted to get_page: fixed. And how did this work before? Aargh! That nopage is returning a page from within a buffer allocated by snd_malloc_pages, which allocates a high-order page, then does SetPageReserved on each 0-order page within. That would have worked in 2.6.14, because when the area was unmapped, PageReserved inhibited put_page. 2.6.15-rc1 removed that inhibition (while leaving ineffective PageReserveds around for now), but it hasn't caused trouble because.. we've not been freeing from VM_RESERVED at all. Signed-off-by:
-
Hugh Dickins authored
The PageReserved removal in 2.6.15-rc1 issued a "deprecated" message when you tried to mmap or mprotect MAP_PRIVATE PROT_WRITE a VM_RESERVED, and failed with -EACCES: because do_wp_page lacks the refinement to COW pages in those areas, nor do we expect to find anonymous pages in them; and it seemed just bloat to add code for handling such a peculiar case. But immediately it caused vbetool and ddcprobe (using lrmi) to fail. So revert the "deprecated" messages, letting mmap and mprotect succeed. But leave do_wp_page's BUG_ON(vma->vm_flags & VM_RESERVED) in place until we've added the code to do it right: so this particular patch is only good if the app doesn't really need to write to that private area. Signed-off-by:
-
Hugh Dickins authored
The PageReserved removal in 2.6.15-rc1 prohibited get_user_pages on the areas flagged VM_RESERVED in place of PageReserved. That is correct in theory - we ought not to interfere with struct pages in such a reserved area; but in practice it broke BTTV for one. So revert to prohibiting only on VM_IO: if someone gets into trouble with get_user_pages on VM_RESERVED, it'll just be a "don't do that". You can argue that videobuf_mmap_mapper shouldn't set VM_RESERVED in the first place, but now's not the time for breaking drivers without notice. Signed-off-by:
-
Jeff Dike authored
On some systems, libc PAGE_SIZE calls getpagesize, which can't happen from a stub. So, I use UM_KERN_PAGE_SIZE, which is less variable in its definition, instead. Signed-off-by:
Jeff Dike <jdike@addtoit.com> Signed-off-by:
-
Jeff Dike authored
This patch makes stub_segv use the stub_syscall macros. This was needed anyway, but the bug that prompted this was the discovery that gcc was storing stuff in RCX, which is trashed across a system call. This is exactly the sort of problem that the new macros fix. There is a stub_syscall0 for getpid. stub_segv was changed to be a libc file, and that caused some include changes. Signed-off-by:
-
Jeff Dike authored
This gives a name to the anonymous union introduced in skas-hold-own-ldt, allowing to build on a wider range of gccs. It also removes ldt.h, which somehow became real, and replaces it with a symlink, and creates ldt-x86_64.h as a copy of ldt-i386.h for now. Signed-off-by:
-
Jeff Dike authored
We have a bug in the i386 stub_syscall6 which pushes ebp before the system call and pops it afterwards. Because we use syscall6 to remap the stack, the old contents of the stack (and the former value of ebp) are no longer available. Some versions of gcc make from a real local, accessed through ebp, despite my efforts to make it obvious that references to from are really constants. This patch attempts to make it even more obvious by eliminating from and using a macro to access the stub's data explicitly with constants. My original thinking on this was to replace syscall6 with a remap_stack interface which saved ebp someplace and restored it afterwards. The problem is that there are no registers to put it in, except for esp. That could work, since we can store a constant in esp after the mmap because we just replaced the stack. However, this approach seems a tad cleaner. Signed-off-by:
-
Richard Knutsson authored
drivers/net/dgrs.c: In function `dgrs_init_module': drivers/net/dgrs.c:1598: `dgrs_pci_driver' undeclared (first use in this function) Signed-off-by:
Richard Knutsson <ricknu-0@student.ltu.se> Signed-off-by:
-
-
Linus Torvalds authored
-
Linus Torvalds authored
-
-
- 21 Nov, 2005 14 commits
-
-
Russ Anderson authored
The nasid_index was not being incremented if the pointer was null, causing an infinite loop. Signed-off-by: Russ Anderson (rja@sgi.com) Signed-off-by:Tony Luck <tony.luck@intel.com>
-
Jack Steiner authored
Add support for old versions of the SN PROMs. Eventually this support will be deleted but it is useful right now to continue supporting older PROMs. Signed-off-by:
Jack Steiner <steiner@sgi.com> Signed-off-by:
-
hawkes@sgi.com authored
The kernel's use of the for_each_*cpu(i) macros has allowed for sparse CPU numbering. When I hacked the kernel to test sparse cpu_present_map[] and cpu_possible_map[] cpumasks, I discovered one remaining spot, in sn_hwperf_ioctl() during sn initialization, that needs to be fixed. Signed-off-by:
John Hawkes <hawkes@sgi.com> Signed-off-by:
Dean Roe <roe@sgi.com> Signed-off-by:
-
Prarit Bhargava authored
Patch to prevent sn2_ptc_init code from attempting to load on non-sn2 systems when sn2_smp.c is built-in to generic kernel. Signed-off-by:
Prarit Bhargava <prarit@sgi.com> Signed-off-by:
-
Jens Axboe authored
Kill the arq->state poison statement in as_add_request(), it can trigger for perfectly valid code that just reuses a request after io completion instead of freeing it and allocating a new one. We probably should introduce a blk_init_request() to start from scratch, but for now just kill it as we will be removing the as specific poisoning soon. Signed-off-by:
Jens Axboe <axboe@suse.de> Signed-off-by:
-
Linus Torvalds authored
-
Linus Torvalds authored
-
Russell King authored
Signed-off-by:Russell King <rmk+kernel@arm.linux.org.uk>
-
Russell King authored
core.c:263: warning: initialization makes integer from pointer without a cast Signed-off-by: -
Russell King authored
assabet.c:291: warning: 'scr' may be used uninitialized in this function Signed-off-by: -
Russell King authored
Signed-off-by: -
Russell King authored
Since the defintion of NODES_SHIFT may be overridden in asm/arch/memory.h it's important to include asm/memory.h into asm/numnodes.h to ensure that the correct value is always defined. Signed-off-by: -
Kenneth Tan authored
Patch from Kenneth Tan To add queue manager region size which is missing from ixp4xx-regs.h Signed-off-by:
Kenneth Tan <chong.yin.tan@intel.com> Signed-off-by:
-
Dirk Opfer authored
Patch from Dirk Opfer Fix an error in tosa.c after the platform device conversion. Signed-off-by:
Dirk Opfer <Dirk@Opfer-Online.de> Signed-off-by:
-
