diff options
66 files changed, 705 insertions, 407 deletions
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile index fabc06466b9..9b1f6ca100d 100644 --- a/Documentation/DocBook/Makefile +++ b/Documentation/DocBook/Makefile @@ -136,7 +136,7 @@ quiet_cmd_db2ps = PS $@ %.ps : %.xml $(call cmd,db2ps) -quiet_cmd_db2pdf = PDF $@ +quiet_cmd_db2pdf = PDF $@ cmd_db2pdf = $(subst TYPE,pdf, $($(PDF_METHOD)template)) %.pdf : %.xml $(call cmd,db2pdf) @@ -148,7 +148,7 @@ build_main_index = rm -rf $(main_idx) && \ echo '<h2>Kernel Version: $(KERNELVERSION)</h2>' >> $(main_idx) && \ cat $(HTML) >> $(main_idx) -quiet_cmd_db2html = HTML $@ +quiet_cmd_db2html = HTML $@ cmd_db2html = xmlto xhtml $(XMLTOFLAGS) -o $(patsubst %.html,%,$@) $< && \ echo '<a HREF="$(patsubst %.html,%,$(notdir $@))/index.html"> \ $(patsubst %.html,%,$(notdir $@))</a><p>' > $@ diff --git a/Documentation/DocBook/deviceiobook.tmpl b/Documentation/DocBook/deviceiobook.tmpl index 60d6e0b81bd..3ed88126ab8 100644 --- a/Documentation/DocBook/deviceiobook.tmpl +++ b/Documentation/DocBook/deviceiobook.tmpl @@ -24,7 +24,7 @@ <surname>Cox</surname> <affiliation> <address> - <email>alan@redhat.com</email> + <email>alan@lxorguk.ukuu.org.uk</email> </address> </affiliation> </author> diff --git a/Documentation/DocBook/mcabook.tmpl b/Documentation/DocBook/mcabook.tmpl index 499eddc2d07..467ccac6ec5 100644 --- a/Documentation/DocBook/mcabook.tmpl +++ b/Documentation/DocBook/mcabook.tmpl @@ -12,7 +12,7 @@ <surname>Cox</surname> <affiliation> <address> - <email>alan@redhat.com</email> + <email>alan@lxorguk.ukuu.org.uk</email> </address> </affiliation> </author> diff --git a/Documentation/DocBook/wanbook.tmpl b/Documentation/DocBook/wanbook.tmpl index 9eebcc304de..8c93db122f0 100644 --- a/Documentation/DocBook/wanbook.tmpl +++ b/Documentation/DocBook/wanbook.tmpl @@ -12,7 +12,7 @@ <surname>Cox</surname> <affiliation> <address> - <email>alan@redhat.com</email> + <email>alan@lxorguk.ukuu.org.uk</email> </address> </affiliation> </author> diff --git a/Documentation/DocBook/z8530book.tmpl b/Documentation/DocBook/z8530book.tmpl index a42a8a4c768..6f3883be877 100644 --- a/Documentation/DocBook/z8530book.tmpl +++ b/Documentation/DocBook/z8530book.tmpl @@ -12,7 +12,7 @@ <surname>Cox</surname> <affiliation> <address> - <email>alan@redhat.com</email> + <email>alan@lxorguk.ukuu.org.uk</email> </address> </affiliation> </author> diff --git a/Documentation/ManagementStyle b/Documentation/ManagementStyle index 49a8efa5afe..a5f0ea58c78 100644 --- a/Documentation/ManagementStyle +++ b/Documentation/ManagementStyle @@ -17,7 +17,7 @@ companies. If you sign purchase orders or you have any clue about the budget of your group, you're almost certainly not a kernel manager. These suggestions may or may not apply to you. -First off, I'd suggest buying "Seven Habits of Highly Successful +First off, I'd suggest buying "Seven Habits of Highly Effective People", and NOT read it. Burn it, it's a great symbolic gesture. (*) This document does so not so much by answering the question, but by diff --git a/Documentation/accounting/.gitignore b/Documentation/accounting/.gitignore new file mode 100644 index 00000000000..86485203c4a --- /dev/null +++ b/Documentation/accounting/.gitignore @@ -0,0 +1 @@ +getdelays diff --git a/Documentation/auxdisplay/.gitignore b/Documentation/auxdisplay/.gitignore new file mode 100644 index 00000000000..7af222860a9 --- /dev/null +++ b/Documentation/auxdisplay/.gitignore @@ -0,0 +1 @@ +cfag12864b-example diff --git a/Documentation/connector/.gitignore b/Documentation/connector/.gitignore new file mode 100644 index 00000000000..d2b9c32accd --- /dev/null +++ b/Documentation/connector/.gitignore @@ -0,0 +1 @@ +ucon diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 8362860e21a..23d2f4460de 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -161,8 +161,12 @@ prototypes: int (*set_page_dirty)(struct page *page); int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); - int (*prepare_write)(struct file *, struct page *, unsigned, unsigned); - int (*commit_write)(struct file *, struct page *, unsigned, unsigned); + int (*write_begin)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata); + int (*write_end)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); int (*invalidatepage) (struct page *, unsigned long); int (*releasepage) (struct page *, int); @@ -180,8 +184,6 @@ sync_page: no maybe writepages: no set_page_dirty no no readpages: no -prepare_write: no yes yes -commit_write: no yes yes write_begin: no locks the page yes write_end: no yes, unlocks yes perform_write: no n/a yes @@ -191,7 +193,7 @@ releasepage: no yes direct_IO: no launder_page: no yes - ->prepare_write(), ->commit_write(), ->sync_page() and ->readpage() + ->write_begin(), ->write_end(), ->sync_page() and ->readpage() may be called from the request handler (/dev/loop). ->readpage() unlocks the page, either synchronously or via I/O diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index c4d348dabe9..5579bda58a6 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -492,7 +492,7 @@ written-back to storage typically in whole pages, however the address_space has finer control of write sizes. The read process essentially only requires 'readpage'. The write -process is more complicated and uses prepare_write/commit_write or +process is more complicated and uses write_begin/write_end or set_page_dirty to write data into the address_space, and writepage, sync_page, and writepages to writeback data to storage. @@ -521,8 +521,6 @@ struct address_space_operations { int (*set_page_dirty)(struct page *page); int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); - int (*prepare_write)(struct file *, struct page *, unsigned, unsigned); - int (*commit_write)(struct file *, struct page *, unsigned, unsigned); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); @@ -598,37 +596,7 @@ struct address_space_operations { readpages is only used for read-ahead, so read errors are ignored. If anything goes wrong, feel free to give up. - prepare_write: called by the generic write path in VM to set up a write - request for a page. This indicates to the address space that - the given range of bytes is about to be written. The - address_space should check that the write will be able to - complete, by allocating space if necessary and doing any other - internal housekeeping. If the write will update parts of - any basic-blocks on storage, then those blocks should be - pre-read (if they haven't been read already) so that the - updated blocks can be written out properly. - The page will be locked. - - Note: the page _must not_ be marked uptodate in this function - (or anywhere else) unless it actually is uptodate right now. As - soon as a page is marked uptodate, it is possible for a concurrent - read(2) to copy it to userspace. - - commit_write: If prepare_write succeeds, new data will be copied - into the page and then commit_write will be called. It will - typically update the size of the file (if appropriate) and - mark the inode as dirty, and do any other related housekeeping - operations. It should avoid returning an error if possible - - errors should have been handled by prepare_write. - - write_begin: This is intended as a replacement for prepare_write. The - key differences being that: - - it returns a locked page (in *pagep) rather than being - given a pre locked page; - - it must be able to cope with short writes (where the - length passed to write_begin is greater than the number - of bytes copied into the page). - + write_begin: Called by the generic buffered write code to ask the filesystem to prepare to write len bytes at the given offset in the file. The address_space should check that the write will be able to complete, @@ -640,6 +608,9 @@ struct address_space_operations { The filesystem must return the locked pagecache page for the specified offset, in *pagep, for the caller to write into. + It must be able to cope with short writes (where the length passed to + write_begin is greater than the number of bytes copied into the page). + flags is a field for AOP_FLAG_xxx flags, described in include/linux/fs.h. diff --git a/Documentation/ia64/.gitignore b/Documentation/ia64/.gitignore new file mode 100644 index 00000000000..ab806edc873 --- /dev/null +++ b/Documentation/ia64/.gitignore @@ -0,0 +1 @@ +aliasing-test diff --git a/Documentation/isdn/CREDITS b/Documentation/isdn/CREDITS index 8cac6c2f23e..c1679e913fc 100644 --- a/Documentation/isdn/CREDITS +++ b/Documentation/isdn/CREDITS @@ -5,7 +5,7 @@ I want to thank all who contributed to this project and especially to: Thomas Bogendörfer (tsbogend@bigbug.franken.de) Tester, lots of bugfixes and hints. -Alan Cox (alan@redhat.com) +Alan Cox (alan@lxorguk.ukuu.org.uk) For help getting into standard-kernel. Henner Eisen (eis@baty.hanse.de) diff --git a/Documentation/networking/.gitignore b/Documentation/networking/.gitignore new file mode 100644 index 00000000000..286a5680f49 --- /dev/null +++ b/Documentation/networking/.gitignore @@ -0,0 +1 @@ +ifenslave diff --git a/Documentation/networking/dmfe.txt b/Documentation/networking/dmfe.txt index b1b7499dd9d..8006c227fda 100644 --- a/Documentation/networking/dmfe.txt +++ b/Documentation/networking/dmfe.txt @@ -60,6 +60,6 @@ Tobias Ringstrom <tori@unhappy.mine.nu> : Current Maintainer Contributors: Marcelo Tosatti <marcelo@conectiva.com.br> -Alan Cox <alan@redhat.com> +Alan Cox <alan@lxorguk.ukuu.org.uk> Jeff Garzik <jgarzik@pobox.com> Vojtech Pavlik <vojtech@suse.cz> diff --git a/Documentation/pcmcia/.gitignore b/Documentation/pcmcia/.gitignore new file mode 100644 index 00000000000..53d08133675 --- /dev/null +++ b/Documentation/pcmcia/.gitignore @@ -0,0 +1 @@ +crc32hash diff --git a/Documentation/scsi/aacraid.txt b/Documentation/scsi/aacraid.txt index 709ca991a45..ddace3afc83 100644 --- a/Documentation/scsi/aacraid.txt +++ b/Documentation/scsi/aacraid.txt @@ -128,7 +128,7 @@ Supported Cards/Chipsets People ------------------------- -Alan Cox <alan@redhat.com> +Alan Cox <alan@lxorguk.ukuu.org.uk> Christoph Hellwig <hch@infradead.org> (updates for new-style PCI probing and SCSI host registration, small cleanups/fixes) Matt Domsch <matt_domsch@dell.com> (revision ioctl, adapter messages) diff --git a/Documentation/spi/.gitignore b/Documentation/spi/.gitignore new file mode 100644 index 00000000000..4280576397e --- /dev/null +++ b/Documentation/spi/.gitignore @@ -0,0 +1,2 @@ +spidev_fdx +spidev_test diff --git a/Documentation/video4linux/.gitignore b/Documentation/video4linux/.gitignore new file mode 100644 index 00000000000..952703943e8 --- /dev/null +++ b/Documentation/video4linux/.gitignore @@ -0,0 +1 @@ +v4lgrab diff --git a/Documentation/video4linux/bttv/CONTRIBUTORS b/Documentation/video4linux/bttv/CONTRIBUTORS index 8aad6dd93d6..eb41b265086 100644 --- a/Documentation/video4linux/bttv/CONTRIBUTORS +++ b/Documentation/video4linux/bttv/CONTRIBUTORS @@ -3,7 +3,7 @@ Contributors to bttv: Michael Chu <mmchu@pobox.com> AverMedia fix and more flexible card recognition -Alan Cox <alan@redhat.com> +Alan Cox <alan@lxorguk.ukuu.org.uk> Video4Linux interface and 2.1.x kernel adaptation Chris Kleitsch diff --git a/Documentation/vm/.gitignore b/Documentation/vm/.gitignore new file mode 100644 index 00000000000..33e8a023df0 --- /dev/null +++ b/Documentation/vm/.gitignore @@ -0,0 +1 @@ +slabinfo diff --git a/Documentation/watchdog/src/.gitignore b/Documentation/watchdog/src/.gitignore new file mode 100644 index 00000000000..ac90997dba9 --- /dev/null +++ b/Documentation/watchdog/src/.gitignore @@ -0,0 +1,2 @@ +watchdog-simple +watchdog-test diff --git a/MAINTAINERS b/MAINTAINERS index 16202c8ac68..ce521d25ce3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2701,6 +2701,16 @@ M: matthew@wil.cx L: linux-scsi@vger.kernel.org S: Maintained +LTP (Linux Test Project) +P: Subrata Modak +M: subrata@linux.vnet.ibm.com +P: Mike Frysinger +M: vapier@gentoo.org +L: ltp-list@lists.sourceforge.net (subscribers-only) +W: http://ltp.sourceforge.net/ +T: git kernel.org/pub/scm/linux/kernel/git/galak/ltp.git +S: Maintained + M32R ARCHITECTURE P: Hirokazu Takata M: takata@linux-m32r.org diff --git a/arch/x86/boot/compressed/.gitignore b/arch/x86/boot/compressed/.gitignore index be0ed065249..63eff3b04d0 100644 --- a/arch/x86/boot/compressed/.gitignore +++ b/arch/x86/boot/compressed/.gitignore @@ -1 +1,3 @@ relocs +vmlinux.bin.all +vmlinux.relocs diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 3f09cd8bcc3..5c4ee70d5cf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -40,8 +40,7 @@ * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 * * Support for falling back on the write file operation when the address space - * operations prepare_write and/or commit_write are not available on the - * backing filesystem. + * operations write_begin is not available on the backing filesystem. * Anton Altaparmakov, 16 Feb 2005 * * Still To Fix: @@ -765,7 +764,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, */ if (!file->f_op->splice_read) goto out_putf; - if (aops->prepare_write || aops->write_begin) + if (aops->write_begin) lo_flags |= LO_FLAGS_USE_AOPS; if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write) lo_flags |= LO_FLAGS_READ_ONLY; diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index 835a33c8d5f..1d7b429f7ff 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -957,3 +957,4 @@ module_exit(cleanup_ipmi); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Corey Minyard <minyard@mvista.com>"); MODULE_DESCRIPTION("Linux device interface for the IPMI message handler."); +MODULE_ALIAS("platform:ipmi_si"); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 5a11e3cbcae..e0dbd388757 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -102,6 +102,13 @@ config EDAC_I3000 Support for error detection and correction on the Intel 3000 and 3010 server chipsets. +config EDAC_X38 + tristate "Intel X38" + depends on EDAC_MM_EDAC && PCI && X86 + help + Support for error detection and correction on the Intel + X38 server chipsets. + config EDAC_I82860 tristate "Intel 82860" depends on EDAC_MM_EDAC && PCI && X86_32 diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index e5e9104b552..62c2d9bad8d 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o obj-$(CONFIG_EDAC_I82875P) += i82875p_edac.o obj-$(CONFIG_EDAC_I82975X) += i82975x_edac.o obj-$(CONFIG_EDAC_I3000) += i3000_edac.o +obj-$(CONFIG_EDAC_X38) += x38_edac.o obj-$(CONFIG_EDAC_I82860) += i82860_edac.o obj-$(CONFIG_EDAC_R82600) += r82600_edac.o obj-$(CONFIG_EDAC_PASEMI) += pasemi_edac.o diff --git a/drivers/edac/cell_edac.c b/drivers/edac/cell_edac.c index 887072f5dc8..cd2e3b8087e 100644 --- a/drivers/edac/cell_edac.c +++ b/drivers/edac/cell_edac.c @@ -9,6 +9,7 @@ */ #undef DEBUG +#include <linux/edac.h> #include <linux/module.h> #include <linux/init.h> #include <linux/platform_device.h> @@ -164,6 +165,8 @@ static int __devinit cell_edac_probe(struct platform_device *pdev) if (regs == NULL) return -ENODEV; + edac_op_state = EDAC_OPSTATE_POLL; + /* Get channel population */ reg = in_be64(®s->mic_mnt_cfg); dev_dbg(&pdev->dev, "MIC_MNT_CFG = 0x%016lx\n", reg); diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c new file mode 100644 index 00000000000..2406c2ce284 --- /dev/null +++ b/drivers/edac/x38_edac.c @@ -0,0 +1,524 @@ +/* + * Intel X38 Memory Controller kernel module + * Copyright (C) 2008 Cluster Computing, Inc. + * + * This file may be distributed under the terms of the + * GNU General Public License. + * + * This file is based on i3200_edac.c + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/slab.h> +#include <linux/edac.h> +#include "edac_core.h" + +#define X38_REVISION "1.1" + +#define EDAC_MOD_STR "x38_edac" + +#define PCI_DEVICE_ID_INTEL_X38_HB 0x29e0 + +#define X38_RANKS 8 +#define X38_RANKS_PER_CHANNEL 4 +#define X38_CHANNELS 2 + +/* Intel X38 register addresses - device 0 function 0 - DRAM Controller */ + +#define X38_MCHBAR_LOW 0x48 /* MCH Memory Mapped Register BAR */ +#define X38_MCHBAR_HIGH 0x4b +#define X38_MCHBAR_MASK 0xfffffc000ULL /* bits 35:14 */ +#define X38_MMR_WINDOW_SIZE 16384 + +#define X38_TOM 0xa0 /* Top of Memory (16b) + * + * 15:10 reserved + * 9:0 total populated physical memory + */ +#define X38_TOM_MASK 0x3ff /* bits 9:0 */ +#define X38_TOM_SHIFT 26 /* 64MiB grain */ + +#define X38_ERRSTS 0xc8 /* Error Status Register (16b) + * + * 15 reserved + * 14 Isochronous TBWRR Run Behind FIFO Full + * (ITCV) + * 13 Isochronous TBWRR Run Behind FIFO Put + * (ITSTV) + * 12 reserved + * 11 MCH Thermal Sensor Event + * for SMI/SCI/SERR (GTSE) + * 10 reserved + * 9 LOCK to non-DRAM Memory Flag (LCKF) + * 8 reserved + * 7 DRAM Throttle Flag (DTF) + * 6:2 reserved + * 1 Multi-bit DRAM ECC Error Flag (DMERR) + * 0 Single-bit DRAM ECC Error Flag (DSERR) + */ +#define X38_ERRSTS_UE 0x0002 +#define X38_ERRSTS_CE 0x0001 +#define X38_ERRSTS_BITS (X38_ERRSTS_UE | X38_ERRSTS_CE) + + +/* Intel MMIO register space - device 0 function 0 - MMR space */ + +#define X38_C0DRB 0x200 /* Channel 0 DRAM Rank Boundary (16b x 4) + * + * 15:10 reserved + * 9:0 Channel 0 DRAM Rank Boundary Address + */ +#define X38_C1DRB 0x600 /* Channel 1 DRAM Rank Boundary (16b x 4) */ +#define X38_DRB_MASK 0x3ff /* bits 9:0 */ +#define X38_DRB_SHIFT 26 /* 64MiB grain */ + +#define X38_C0ECCERRLOG 0x280 /* Channel 0 ECC Error Log (64b) + * + * 63:48 Error Column Address (ERRCOL) + * 47:32 Error Row Address (ERRROW) + * 31:29 Error Bank Address (ERRBANK) + * 28:27 Error Rank Address (ERRRANK) + * 26:24 reserved + * 23:16 Error Syndrome (ERRSYND) + * 15: 2 reserved + * 1 Multiple Bit Error Status (MERRSTS) + * 0 Correctable Error Status (CERRSTS) + */ +#define X38_C1ECCERRLOG 0x680 /* Channel 1 ECC Error Log (64b) */ +#define X38_ECCERRLOG_CE 0x1 +#define X38_ECCERRLOG_UE 0x2 +#define X38_ECCERRLOG_RANK_BITS 0x18000000 +#define X38_ECCERRLOG_SYNDROME_BITS 0xff0000 + +#define X38_CAPID0 0xe0 /* see P.94 of spec for details */ + +static int x38_channel_num; + +static int how_many_channel(struct pci_dev *pdev) +{ + unsigned char capid0_8b; /* 8th byte of CAPID0 */ + + pci_read_config_byte(pdev, X38_CAPID0 + 8, &capid0_8b); + if (capid0_8b & 0x20) { /* check DCD: Dual Channel Disable */ + debugf0("In single channel mode.\n"); + x38_channel_num = 1; + } else { + debugf0("In dual channel mode.\n"); + x38_channel_num = 2; + } + + return x38_channel_num; +} + +static unsigned long eccerrlog_syndrome(u64 log) +{ + return (log & X38_ECCERRLOG_SYNDROME_BITS) >> 16; +} + +static int eccerrlog_row(int channel, u64 log) +{ + return ((log & X38_ECCERRLOG_RANK_BITS) >> 27) | + (channel * X38_RANKS_PER_CHANNEL); +} + +enum x38_chips { + X38 = 0, +}; + +struct x38_dev_info { + const char *ctl_name; +}; + +struct x38_error_info { + u16 errsts; + u16 errsts2; + u64 eccerrlog[X38_CHANNELS]; +}; + +static const struct x38_dev_info x38_devs[] = { + [X38] = { + .ctl_name = "x38"}, +}; + +static struct pci_dev *mci_pdev; +static int x38_registered = 1; + + +static void x38_clear_error_info(struct mem_ctl_info *mci) +{ + struct pci_dev *pdev; + + pdev = to_pci_dev(mci->dev); + + /* + * Clear any error bits. + * (Yes, we really clear bits by writing 1 to them.) + */ + pci_write_bits16(pdev, X38_ERRSTS, X38_ERRSTS_BITS, + X38_ERRSTS_BITS); +} + +static u64 x38_readq(const void __iomem *addr) +{ + return readl(addr) | (((u64)readl(addr + 4)) << 32); +} + +static void x38_get_and_clear_error_info(struct mem_ctl_info *mci, + struct x38_error_info *info) +{ + struct pci_dev *pdev; + void __iomem *window = mci->pvt_info; + + pdev = to_pci_dev(mci->dev); + + /* + * This is a mess because there is no atomic way to read all the + * registers at once and the registers can transition from CE being + * overwritten by UE. + */ + pci_read_config_word(pdev, X38_ERRSTS, &info->errsts); + if (!(info->errsts & X38_ERRSTS_BITS)) + return; + + info->eccerrlog[0] = x38_readq(window + X38_C0ECCERRLOG); + if (x38_channel_num == 2) + info->eccerrlog[1] = x38_readq(window + X38_C1ECCERRLOG); + + pci_read_config_word(pdev, X38_ERRSTS, &info->errsts2); + + /* + * If the error is the same for both reads then the first set + * of reads is valid. If there is a change then there is a CE + * with no info and the second set of reads is valid and + * should be UE info. + */ + if ((info->errsts ^ info->errsts2) & X38_ERRSTS_BITS) { + info->eccerrlog[0] = x38_readq(window + X38_C0ECCERRLOG); + if (x38_channel_num == 2) + info->eccerrlog[1] = + x38_readq(window + X38_C1ECCERRLOG); + } + + x38_clear_error_info(mci); +} + +static void x38_process_error_info(struct mem_ctl_info *mci, + struct x38_error_info *info) +{ + int channel; + u64 log; + + if (!(info->errsts & X38_ERRSTS_BITS)) + return; + + if ((info->errsts ^ info->errsts2) & X38_ERRSTS_BITS) { + edac_mc_handle_ce_no_info(mci, "UE overwrote CE"); + info->errsts = info->errsts2; + } + + for (channel = 0; channel < x38_channel_num; channel++) { + log = info->eccerrlog[channel]; + if (log & X38_ECCERRLOG_UE) { + edac_mc_handle_ue(mci, 0, 0, + eccerrlog_row(channel, log), "x38 UE"); + } else if (log & X38_ECCERRLOG_CE) { + edac_mc_handle_ce(mci, 0, 0, + eccerrlog_syndrome(log), + eccerrlog_row(channel, log), 0, "x38 CE"); + } + } +} + +static void x38_check(struct mem_ctl_info *mci) +{ + struct x38_error_info info; + + debugf1("MC%d: %s()\n", mci->mc_idx, __func__); + x38_get_and_clear_error_info(mci, &info); + x38_process_error_info(mci, &info); +} + + +void __iomem *x38_map_mchbar(struct pci_dev *pdev) +{ + union { + u64 mchbar; + struct { + u32 mchbar_low; + u32 mchbar_high; + }; + } u; + void __iomem *window; + + pci_read_config_dword(pdev, X38_MCHBAR_LOW, &u.mchbar_low); + pci_write_config_dword(pdev, X38_MCHBAR_LOW, u.mchbar_low | 0x1); + pci_read_config_dword(pdev, X38_MCHBAR_HIGH, &u.mchbar_high); + u.mchbar &= X38_MCHBAR_MASK; + + if (u.mchbar != (resource_size_t)u.mchbar) { + printk(KERN_ERR + "x38: mmio space beyond accessible range (0x%llx)\n", + (unsigned long long)u.mchbar); + return NULL; + } + + window = ioremap_nocache(u.mchbar, X38_MMR_WINDOW_SIZE); + if (!window) + printk(KERN_ERR "x38: cannot map mmio space at 0x%llx\n", + (unsigned long long)u.mchbar); + + return window; +} + + +static void x38_get_drbs(void __iomem *window, + u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL]) +{ + int i; + + for (i = 0; i < X38_RANKS_PER_CHANNEL; i++) { + drbs[0][i] = readw(window + X38_C0DRB + 2*i) & X38_DRB_MASK; + drbs[1][i] = readw(window + X38_C1DRB + 2*i) & X38_DRB_MASK; + } +} + +static bool x38_is_stacked(struct pci_dev *pdev, + u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL]) +{ + u16 tom; + + pci_read_config_word(pdev, X38_TOM, &tom); + tom &= X38_TOM_MASK; + + return drbs[X38_CHANNELS - 1][X38_RANKS_PER_CHANNEL - 1] == tom; +} + +static unsigned long drb_to_nr_pages( + u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL], + bool stacked, int channel, int rank) +{ + int n; + + n = drbs[channel][rank]; + if (rank > 0) + n -= drbs[channel][rank - 1]; + if (stacked && (channel == 1) && drbs[channel][rank] == + drbs[channel][X38_RANKS_PER_CHANNEL - 1]) { + n -= drbs[0][X38_RANKS_PER_CHANNEL - 1]; + } + + n <<= (X38_DRB_SHIFT - PAGE_SHIFT); + return n; +} + +static int x38_probe1(struct pci_dev *pdev, int dev_idx) +{ + int rc; + int i; + struct mem_ctl_info *mci = NULL; + unsigned long last_page; + u16 drbs[X38_CHANNELS][X38_RANKS_PER_CHANNEL]; + bool stacked; + void __iomem *window; + + debugf0("MC: %s()\n", __func__); + + window = x38_map_mchbar(pdev); + if (!window) + return -ENODEV; + + x38_get_drbs(window, drbs); + + how_many_channel(pdev); + + /* FIXME: unconventional pvt_info usage */ + mci = edac_mc_alloc(0, X38_RANKS, x38_channel_num, 0); + if (!mci) + return -ENOMEM; + + debugf3("MC: %s(): init mci\n", __func__); + + mci->dev = &pdev->dev; + mci->mtype_cap = MEM_FLAG_DDR2; + + mci->edac_ctl_cap = EDAC_FLAG_SECDED; + mci->edac_cap = EDAC_FLAG_SECDED; + + mci->mod_name = EDAC_MOD_STR; + mci->mod_ver = X38_REVISION; + mci->ctl_name = x38_devs[dev_idx].ctl_name; + mci->dev_name = pci_name(pdev); + mci->edac_check = x38_check; + mci->ctl_page_to_phys = NULL; + mci->pvt_info = window; + + stacked = x38_is_stacked(pdev, drbs); + + /* + * The dram rank boundary (DRB) reg values are boundary addresses + * for each DRAM rank with a granularity of 64MB. DRB regs are + * cumulative; the last one will contain the total memory + * contained in all ranks. + */ + last_page = -1UL; + for (i = 0; i < mci->nr_csrows; i++) { + unsigned long nr_pages; + struct csrow_info *csrow = &mci->csrows[i]; + + nr_pages = drb_to_nr_pages(drbs, stacked, + i / X38_RANKS_PER_CHANNEL, + i % X38_RANKS_PER_CHANNEL); + + if (nr_pages == 0) { + csrow->mtype = MEM_EMPTY; + continue; + } + + csrow->first_page = last_page + 1; + last_page += nr_pages; + csrow->last_page = last_page; + csrow->nr_pages = nr_pages; + + csrow->grain = nr_pages << PAGE_SHIFT; + csrow->mtype = MEM_DDR2; + csrow->dtype = DEV_UNKNOWN; + csrow->edac_mode = EDAC_UNKNOWN; + } + + x38_clear_error_info(mci); + + rc = -ENODEV; + if (edac_mc_add_mc(mci)) { + debugf3("MC: %s(): failed edac_mc_add_mc()\n", __func__); + goto fail; + } + + /* get this far and it's successful */ + debugf3("MC: %s(): success\n", __func__); + return 0; + +fail: + iounmap(window); + if (mci) + edac_mc_free(mci); + + return rc; +} + +static int __devinit x38_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + int rc; + + debugf0("MC: %s()\n", __func__); + + if (pci_enable_device(pdev) < 0) + return -EIO; + + rc = x38_probe1(pdev, ent->driver_data); + if (!mci_pdev) + mci_pdev = pci_dev_get(pdev); + + return rc; +} + +static void __devexit x38_remove_one(struct pci_dev *pdev) +{ + struct mem_ctl_info *mci; + + debugf0("%s()\n", __func__); + + mci = edac_mc_del_mc(&pdev->dev); + if (!mci) + return; + + iounmap(mci->pvt_info); + + edac_mc_free(mci); +} + +static const struct pci_device_id x38_pci_tbl[] __devinitdata = { + { + PCI_VEND_DEV(INTEL, X38_HB), PCI_ANY_ID, PCI_ANY_ID, 0, 0, + X38}, + { + 0, + } /* 0 terminated list. */ +}; + +MODULE_DEVICE_TABLE(pci, x38_pci_tbl); + +static struct pci_driver x38_driver = { + .name = EDAC_MOD_STR, + .probe = x38_init_one, + .remove = __devexit_p(x38_remove_one), + .id_table = x38_pci_tbl, +}; + +static int __init x38_init(void) +{ + int pci_rc; + + debugf3("MC: %s()\n", __func__); + + /* Ensure that the OPSTATE is set correctly for POLL or NMI */ + opstate_init(); + + pci_rc = pci_register_driver(&x38_driver); + if (pci_rc < 0) + goto fail0; + + if (!mci_pdev) { + x38_registered = 0; + mci_pdev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_X38_HB, NULL); + if (!mci_pdev) { + debugf0("x38 pci_get_device fail\n"); + pci_rc = -ENODEV; + goto fail1; + } + + pci_rc = x38_init_one(mci_pdev, x38_pci_tbl); + if (pci_rc < 0) { + debugf0("x38 init fail\n"); + pci_rc = -ENODEV; + goto fail1; + } + } + + return 0; + +fail1: + pci_unregister_driver(&x38_driver); + +fail0: + if (mci_pdev) + pci_dev_put(mci_pdev); + + return pci_rc; +} + +static void __exit x38_exit(void) +{ + debugf3("MC: %s()\n", __func__); + + pci_unregister_driver(&x38_driver); + if (!x38_registered) { + x38_remove_one(mci_pdev); + pci_dev_put(mci_pdev); + } +} + +module_init(x38_init); +module_exit(x38_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Cluster Computing, Inc. Hitoshi Mitake"); +MODULE_DESCRIPTION("MC support for Intel X38 memory hub controllers"); + +module_param(edac_op_state, int, 0444); +MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI"); diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index 11a617ab424..84bdc2ee69e 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -567,8 +567,8 @@ static void i2o_block_biosparam(unsigned long capacity, unsigned short *cyls, /** * i2o_block_open - Open the block device - * @inode: inode for block device being opened - * @file: file to open + * @bdev: block device being opened + * @mode: file open mode * * Power up the device, mount and lock the media. This function is called, * if the block device is opened for access. @@ -596,8 +596,8 @@ static int i2o_block_open(struct block_device *bdev, fmode_t mode) /** * i2o_block_release - Release the I2O block device - * @inode: inode for block device being released - * @file: file to close + * @disk: gendisk device being released + * @mode: file open mode * * Unlock and unmount the media, and power down the device. Gets called if * the block device is closed. @@ -643,8 +643,8 @@ static int i2o_block_getgeo(struct block_device *bdev, struct hd_geometry *geo) /** * i2o_block_ioctl - Issue device specific ioctl calls. - * @inode: inode for block device ioctl - * @file: file for ioctl + * @bdev: block device being opened + * @mode: file open mode * @cmd: ioctl command * @arg: arg * diff --git a/drivers/misc/hdpuftrs/hdpu_nexus.c b/drivers/misc/hdpuftrs/hdpu_nexus.c index 08e26beefe6..ce39fa54949 100644 --- a/drivers/misc/hdpuftrs/hdpu_nexus.c +++ b/drivers/misc/hdpuftrs/hdpu_nexus.c @@ -113,7 +113,6 @@ static int hdpu_nexus_probe(struct platform_device *pdev) if (!hdpu_chassis_id) printk(KERN_WARNING "sky_nexus: " "Unable to create proc dir entry: sky_chassis_id\n"); - } return 0; } diff --git a/drivers/misc/sgi-xp/Makefile b/drivers/misc/sgi-xp/Makefile index 35ce2857807..4fc40d8e1bc 100644 --- a/drivers/misc/sgi-xp/Makefile +++ b/drivers/misc/sgi-xp/Makefile @@ -5,14 +5,14 @@ obj-$(CONFIG_SGI_XP) += xp.o xp-y := xp_main.o xp-$(CONFIG_IA64_SGI_SN2) += xp_sn2.o xp_nofault.o -xp-$(CONFIG_IA64_GENERIC) += xp_sn2.o xp_nofault.o xp_uv.o +xp-$(CONFIG_IA64_GENERIC) += xp_sn2.o xp_nofault.o xp-$(CONFIG_IA64_SGI_UV) += xp_uv.o xp-$(CONFIG_X86_64) += xp_uv.o obj-$(CONFIG_SGI_XP) += xpc.o xpc-y := xpc_main.o xpc_channel.o xpc_partition.o xpc-$(CONFIG_IA64_SGI_SN2) += xpc_sn2.o -xpc-$(CONFIG_IA64_GENERIC) += xpc_sn2.o xpc_uv.o +xpc-$(CONFIG_IA64_GENERIC) += xpc_sn2.o xpc-$(CONFIG_IA64_SGI_UV) += xpc_uv.o xpc-$(CONFIG_X86_64) += xpc_uv.o diff --git a/drivers/misc/sgi-xp/xp.h b/drivers/misc/sgi-xp/xp.h index 859a5281c61..ed1722e5004 100644 --- a/drivers/misc/sgi-xp/xp.h +++ b/drivers/misc/sgi-xp/xp.h @@ -19,7 +19,11 @@ #include <asm/system.h> #include <asm/sn/arch.h> /* defines is_shub1() and is_shub2() */ #define is_shub() ia64_platform_is("sn2") +#ifdef CONFIG_IA64_SGI_UV #define is_uv() ia64_platform_is("uv") +#else +#define is_uv() 0 +#endif #endif #ifdef CONFIG_X86_64 #include <asm/genapic.h> diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index 46325fc8481..e8d5cfbd32c 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -1104,7 +1104,7 @@ xpc_do_exit(enum xp_retval reason) if (is_shub()) xpc_exit_sn2(); - else + else if (is_uv()) xpc_exit_uv(); } @@ -1363,7 +1363,7 @@ out_2: out_1: if (is_shub()) xpc_exit_sn2(); - else + else if (is_uv()) xpc_exit_uv(); return ret; } diff --git a/drivers/misc/sony-laptop.c b/drivers/misc/sony-laptop.c index 5a97d3a9d74..f483c4221f7 100644 --- a/drivers/misc/sony-laptop.c +++ b/drivers/misc/sony-laptop.c @@ -2315,8 +2315,10 @@ end: */ static int sony_pic_disable(struct acpi_device *device) { - if (ACPI_FAILURE(acpi_evaluate_object(device->handle, - "_DIS", NULL, NULL))) + acpi_status ret = acpi_evaluate_object(device->handle, "_DIS", NULL, + NULL); + + if (ACPI_FAILURE(ret) && ret != AE_NOT_FOUND) return -ENXIO; dprintk("Device disabled\n"); diff --git a/drivers/rtc/rtc-ds3234.c b/drivers/rtc/rtc-ds3234.c index 37d131d03f3..45e5b106af7 100644 --- a/drivers/rtc/rtc-ds3234.c +++ b/drivers/rtc/rtc-ds3234.c @@ -189,7 +189,7 @@ static const struct rtc_class_ops ds3234_rtc_ops = { .set_time = ds3234_set_time, }; -static int ds3234_probe(struct spi_device *spi) +static int __devinit ds3234_probe(struct spi_device *spi) { struct rtc_device *rtc; unsigned char tmp; @@ -249,7 +249,7 @@ static int ds3234_probe(struct spi_device *spi) return 0; } -static int __exit ds3234_remove(struct spi_device *spi) +static int __devexit ds3234_remove(struct spi_device *spi) { struct ds3234 *chip = platform_get_drvdata(spi); struct rtc_device *rtc = chip->rtc; diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 910bc704939..f59277bbeda 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -455,6 +455,8 @@ static int __devinit s3c_rtc_probe(struct platform_device *pdev) s3c_rtc_setfreq(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, 1); + /* register RTC and exit */ rtc = rtc_device_register("s3c", &pdev->dev, &s3c_rtcops, @@ -507,7 +509,7 @@ static int s3c_rtc_resume(struct platform_device *pdev) #define s3c_rtc_resume NULL #endif -static struct platform_driver s3c2410_rtcdrv = { +static struct platform_driver s3c2410_rtc_driver = { .probe = s3c_rtc_probe, .remove = __devexit_p(s3c_rtc_remove), .suspend = s3c_rtc_suspend, @@ -523,12 +525,12 @@ static char __initdata banner[] = "S3C24XX RTC, (c) 2004,2006 Simtec Electronics static int __init s3c_rtc_init(void) { printk(banner); - return platform_driver_register(&s3c2410_rtcdrv); + return platform_driver_register(&s3c2410_rtc_driver); } static void __exit s3c_rtc_exit(void) { - platform_driver_unregister(&s3c2410_rtcdrv); + platform_driver_unregister(&s3c2410_rtc_driver); } module_init(s3c_rtc_init); diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 64b3d30027b..b92947d62ad 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -2118,7 +2118,7 @@ static void fbcon_bmove_rec(struct vc_data *vc, struct display *p, int sy, int s height, width); } -static __inline__ void updatescrollmode(struct display *p, +static void updatescrollmode(struct display *p, struct fb_info *info, struct vc_data *vc) { diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index cd5f20da738..6048b55f287 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -1262,8 +1262,8 @@ fb_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FBIOPUT_CON2FBMAP: arg = (unsigned long) compat_ptr(arg); case FBIOBLANK: - ret = fb_ioctl(file, cmd, arg); - break; + mutex_unlock(&info->lock); + return fb_ioctl(file, cmd, arg); case FBIOGET_FSCREENINFO: ret = fb_get_fscreeninfo(inode, file, cmd, arg); diff --git a/drivers/video/via/global.h b/drivers/video/via/global.h index 8e5263c5b81..7543d5f7e30 100644 --- a/drivers/video/via/global.h +++ b/drivers/video/via/global.h @@ -38,7 +38,6 @@ #include "iface.h" #include "viafbdev.h" #include "chip.h" -#include "debug.h" #include "accel.h" #include "share.h" #include "dvi.h" @@ -48,12 +47,10 @@ #include "lcd.h" #include "ioctl.h" -#include "viamode.h" #include "via_utility.h" #include "vt1636.h" #include "tblDPASetting.h" #include "tbl1636.h" -#include "viafbdev.h" /* External struct*/ diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 06db79d05c1..6046239465a 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1251,6 +1251,7 @@ struct kmem_cache *ecryptfs_header_cache_2; /** * ecryptfs_write_headers_virt * @page_virt: The virtual address to write the headers to + * @max: The size of memory allocated at page_virt * @size: Set to the number of bytes written by this function * @crypt_stat: The cryptographic context * @ecryptfs_dentry: The eCryptfs dentry @@ -1278,7 +1279,8 @@ struct kmem_cache *ecryptfs_header_cache_2; * * Returns zero on success */ -static int ecryptfs_write_headers_virt(char *page_virt, size_t *size, +static int ecryptfs_write_headers_virt(char *page_virt, size_t max, + size_t *size, struct ecryptfs_crypt_stat *crypt_stat, struct dentry *ecryptfs_dentry) { @@ -1296,7 +1298,7 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t *size, offset += written; rc = ecryptfs_generate_key_packet_set((page_virt + offset), crypt_stat, ecryptfs_dentry, &written, - PAGE_CACHE_SIZE - offset); + max - offset); if (rc) ecryptfs_printk(KERN_WARNING, "Error generating key packet " "set; rc = [%d]\n", rc); @@ -1368,14 +1370,14 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) goto out; } /* Released in this function */ - virt = kzalloc(crypt_stat->num_header_bytes_at_front, GFP_KERNEL); + virt = (char *)get_zeroed_page(GFP_KERNEL); if (!virt) { printk(KERN_ERR "%s: Out of memory\n", __func__); rc = -ENOMEM; goto out; } - rc = ecryptfs_write_headers_virt(virt, &size, crypt_stat, - ecryptfs_dentry); + rc = ecryptfs_write_headers_virt(virt, PAGE_CACHE_SIZE, &size, + crypt_stat, ecryptfs_dentry); if (unlikely(rc)) { printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n", __func__, rc); @@ -1393,8 +1395,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) goto out_free; } out_free: - memset(virt, 0, crypt_stat->num_header_bytes_at_front); - kfree(virt); + free_page((unsigned long)virt); out: return rc; } diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 19eafbe3c37..2b2eec1283b 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -175,7 +175,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, if (rw == WRITE) { /* - * FIXME: blockdev_direct_IO() doesn't use ->prepare_write(), + * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), * so we need to update the ->mmu_private to block boundary. * * But we must fill the remaining area or hole by nul for diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index d15cd6e7251..60d4c32c880 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -860,7 +860,6 @@ out: * int journal_get_undo_access() - Notify intent to modify metadata with non-rewindable consequences * @handle: transaction * @bh: buffer to undo - * @credits: store the number of taken credits here (if not NULL) * * Sometimes there is a need to distinguish between metadata which has * been committed to disk and that which has not. The ext3fs code uses diff --git a/fs/libfs.c b/fs/libfs.c index 74688598bcf..e960a832190 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -814,7 +814,7 @@ EXPORT_SYMBOL(simple_getattr); EXPORT_SYMBOL(simple_link); EXPORT_SYMBOL(simple_lookup); EXPORT_SYMBOL(simple_pin_fs); -EXPORT_SYMBOL(simple_prepare_write); +EXPORT_UNUSED_SYMBOL(simple_prepare_write); EXPORT_SYMBOL(simple_readpage); EXPORT_SYMBOL(simple_release_fs); EXPORT_SYMBOL(simple_rename); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8d3225a7807..7efe937a415 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -679,8 +679,7 @@ leave: /* Some parts of this taken from generic_cont_expand, which turned out * to be too fragile to do exactly what we need without us having to - * worry about recursive locking in ->prepare_write() and - * ->commit_write(). */ + * worry about recursive locking in ->write_begin() and ->write_end(). */ static int ocfs2_write_zero_page(struct inode *inode, u64 size) { diff --git a/fs/splice.c b/fs/splice.c index a1e701c2715..1abab5cee4b 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -731,8 +731,8 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, }; /* - * The actor worker might be calling ->prepare_write and - * ->commit_write. Most of the time, these expect i_mutex to + * The actor worker might be calling ->write_begin and + * ->write_end. Most of the time, these expect i_mutex to * be held. Since this may result in an ABBA deadlock with * pipe->inode, we have to order lock acquiry here. */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8b00f6643e9..1164963c3a8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -25,7 +25,6 @@ struct cgroup; extern int cgroup_init_early(void); extern int cgroup_init(void); -extern void cgroup_init_smp(void); extern void cgroup_lock(void); extern bool cgroup_lock_live_group(struct cgroup *cgrp); extern void cgroup_unlock(void); @@ -348,8 +347,6 @@ struct cgroup_subsys { struct cgroupfs_root *root; struct list_head sibling; - - void *private; }; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys; @@ -410,7 +407,6 @@ void cgroup_mm_owner_callbacks(struct task_struct *old, static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } -static inline void cgroup_init_smp(void) {} static inline void cgroup_fork(struct task_struct *p) {} static inline void cgroup_fork_callbacks(struct task_struct *p) {} static inline void cgroup_post_fork(struct task_struct *p) {} diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 8f225339eee..5a361f85cfe 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -44,11 +44,6 @@ static inline bool should_send_signal(struct task_struct *p) return !(p->flags & PF_FREEZER_NOSIG); } -/* - * Wake up a frozen process - */ -extern int __thaw_process(struct task_struct *p); - /* Takes and releases task alloc lock using task_lock() */ extern int thaw_process(struct task_struct *p); diff --git a/include/linux/fs.h b/include/linux/fs.h index 5b248d61430..0dcdd9458f4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -489,13 +489,6 @@ struct address_space_operations { int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); - /* - * ext3 requires that a successful prepare_write() call be followed - * by a commit_write() call - they must be balanced - */ - int (*prepare_write)(struct file *, struct page *, unsigned, unsigned); - int (*commit_write)(struct file *, struct page *, unsigned, unsigned); - int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 396a350b87a..fba141d3ca0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -116,6 +116,8 @@ extern int _cond_resched(void); # define might_resched() do { } while (0) #endif +#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP + void __might_sleep(char *file, int line); /** * might_sleep - annotation for functions that can sleep * @@ -126,8 +128,6 @@ extern int _cond_resched(void); * be bitten later when the calling function happens to sleep when it is not * supposed to. */ -#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - void __might_sleep(char *file, int line); # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) #else diff --git a/include/linux/resource.h b/include/linux/resource.h index aaa423a6f3d..40fc7e62608 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -59,10 +59,10 @@ struct rlimit { #define _STK_LIM (8*1024*1024) /* - * GPG wants 32kB of mlocked memory, to make sure pass phrases + * GPG2 wants 64kB of mlocked memory, to make sure pass phrases * and other sensitive information are never written to disk. */ -#define MLOCK_LIMIT (8 * PAGE_SIZE) +#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024) /* * Due to binary compatibility, the actual resource numbers diff --git a/include/linux/security.h b/include/linux/security.h index f5c4a51eb42..c13f1cec9ab 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1585,6 +1585,7 @@ int security_syslog(int type); int security_settime(struct timespec *ts, struct timezone *tz); int security_vm_enough_memory(long pages); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); +int security_vm_enough_memory_kern(long pages); int security_bprm_alloc(struct linux_binprm *bprm); void security_bprm_free(struct linux_binprm *bprm); void security_bprm_apply_creds(struct linux_binprm *bprm, int unsafe); @@ -1820,6 +1821,11 @@ static inline int security_vm_enough_memory(long pages) return cap_vm_enough_memory(current->mm, pages); } +static inline int security_vm_enough_memory_kern(long pages) +{ + return cap_vm_enough_memory(current->mm, pages); +} + static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { return cap_vm_enough_memory(mm, pages); diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index b8db32cea1d..bf8de281b4e 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -18,6 +18,9 @@ * duplex (MicroWire) controllers. Provide chipslect() and txrx_bufs(), * and custom setup()/cleanup() methods. */ + +#include <linux/workqueue.h> + struct spi_bitbang { struct workqueue_struct *workqueue; struct work_struct work; diff --git a/init/Kconfig b/init/Kconfig index 44e9208f9c7..86b00c53fad 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -401,16 +401,20 @@ config CGROUP_MEM_RES_CTLR depends on CGROUPS && RESOURCE_COUNTERS select MM_OWNER help - Provides a memory resource controller that manages both page cache and - RSS memory. + Provides a memory resource controller that manages both anonymous + memory and page cache. (See Documentation/controllers/memory.txt) Note that setting this option increases fixed memory overhead - associated with each page of memory in the system by 4/8 bytes - and also increases cache misses because struct page on many 64bit - systems will not fit into a single cache line anymore. + associated with each page of memory in the system. By this, + 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory + usage tracking struct at boot. Total amount of this is printed out + at boot. Only enable when you're ok with these trade offs and really - sure you need the memory resource controller. + sure you need the memory resource controller. Even when you enable + this, you can set "cgroup_disable=memory" at your boot option to + disable memory resource controller and you can avoid overheads. + (and lose benefits of memory resource contoller) This config option also selects MM_OWNER config option, which could in turn add some fork/exit overhead. diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 4c87ee1fe5d..4d42f450b59 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -1,4 +1,4 @@ - +#include <linux/delay.h> #include <linux/raid/md.h> #include <linux/delay.h> diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index e9505695449..7fa476f01d0 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -162,9 +162,13 @@ static int freezer_can_attach(struct cgroup_subsys *ss, struct task_struct *task) { struct freezer *freezer; - int retval; - /* Anything frozen can't move or be moved to/from */ + /* + * Anything frozen can't move or be moved to/from. + * + * Since orig_freezer->state == FROZEN means that @task has been + * frozen, so it's sufficient to check the latter condition. + */ if (is_task_frozen_enough(task)) return -EBUSY; @@ -173,13 +177,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss, if (freezer->state == CGROUP_FROZEN) return -EBUSY; - retval = 0; - task_lock(task); - freezer = task_freezer(task); - if (freezer->state == CGROUP_FROZEN) - retval = -EBUSY; - task_unlock(task); - return retval; + return 0; } static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) @@ -190,8 +188,9 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) freezer = task_freezer(task); task_unlock(task); - BUG_ON(freezer->state == CGROUP_FROZEN); spin_lock_irq(&freezer->lock); + BUG_ON(freezer->state == CGROUP_FROZEN); + /* Locking avoids race with FREEZING -> THAWED transitions. */ if (freezer->state == CGROUP_FREEZING) freeze_task(task, true); @@ -276,25 +275,18 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) return num_cant_freeze_now ? -EBUSY : 0; } -static int unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) +static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) { struct cgroup_iter it; struct task_struct *task; cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { - int do_wake; - - task_lock(task); - do_wake = __thaw_process(task); - task_unlock(task); - if (do_wake) - wake_up_process(task); + thaw_process(task); } cgroup_iter_end(cgroup, &it); - freezer->state = CGROUP_THAWED; - return 0; + freezer->state = CGROUP_THAWED; } static int freezer_change_state(struct cgroup *cgroup, @@ -304,27 +296,22 @@ static int freezer_change_state(struct cgroup *cgroup, int retval = 0; freezer = cgroup_freezer(cgroup); + spin_lock_irq(&freezer->lock); + update_freezer_state(cgroup, freezer); if (goal_state == freezer->state) goto out; - switch (freezer->state) { + + switch (goal_state) { case CGROUP_THAWED: - retval = try_to_freeze_cgroup(cgroup, freezer); + unfreeze_cgroup(cgroup, freezer); break; - case CGROUP_FREEZING: - if (goal_state == CGROUP_FROZEN) { - /* Userspace is retrying after - * "/bin/echo FROZEN > freezer.state" returned -EBUSY */ - retval = try_to_freeze_cgroup(cgroup, freezer); - break; - } - /* state == FREEZING and goal_state == THAWED, so unfreeze */ case CGROUP_FROZEN: - retval = unfreeze_cgroup(cgroup, freezer); + retval = try_to_freeze_cgroup(cgroup, freezer); break; default: - break; + BUG(); } out: spin_unlock_irq(&freezer->lock); diff --git a/kernel/freezer.c b/kernel/freezer.c index ba6248b323e..2f4936cf708 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -121,16 +121,7 @@ void cancel_freezing(struct task_struct *p) } } -/* - * Wake up a frozen process - * - * task_lock() is needed to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. - */ -int __thaw_process(struct task_struct *p) +static int __thaw_process(struct task_struct *p) { if (frozen(p)) { p->flags &= ~PF_FROZEN; @@ -140,6 +131,15 @@ int __thaw_process(struct task_struct *p) return 0; } +/* + * Wake up a frozen process + * + * task_lock() is needed to prevent the race with refrigerator() which may + * occur if the freezing of tasks fails. Namely, without the lock, if the + * freezing of tasks failed, thaw_tasks() might have run before a task in + * refrigerator() could call frozen_process(), in which case the task would be + * frozen and no one would thaw it. + */ int thaw_process(struct task_struct *p) { task_lock(p); diff --git a/kernel/profile.c b/kernel/profile.c index a9e422df6bf..9830a037d8d 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -102,7 +102,7 @@ int profile_setup(char *str) __setup("profile=", profile_setup); -int profile_init(void) +int __ref profile_init(void) { int buffer_bytes; if (!prof_on) diff --git a/kernel/signal.c b/kernel/signal.c index 105217da5c8..4530fc65445 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1144,7 +1144,8 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) struct task_struct * p; for_each_process(p) { - if (p->pid > 1 && !same_thread_group(p, current)) { + if (task_pid_vnr(p) > 1 && + !same_thread_group(p, current)) { int err = group_send_sig_info(sig, info, p); ++count; if (err != -EPERM) diff --git a/mm/filemap.c b/mm/filemap.c index ab8553658af..f3e5f8944d1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2029,48 +2029,8 @@ int pagecache_write_begin(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - if (aops->write_begin) { - return aops->write_begin(file, mapping, pos, len, flags, + return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); - } else { - int ret; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); - struct inode *inode = mapping->host; - struct page *page; -again: - page = __grab_cache_page(mapping, index); - *pagep = page; - if (!page) - return -ENOMEM; - - if (flags & AOP_FLAG_UNINTERRUPTIBLE && !PageUptodate(page)) { - /* - * There is no way to resolve a short write situation - * for a !Uptodate page (except by double copying in - * the caller done by generic_perform_write_2copy). - * - * Instead, we have to bring it uptodate here. - */ - ret = aops->readpage(file, page); - page_cache_release(page); - if (ret) { - if (ret == AOP_TRUNCATED_PAGE) - goto again; - return ret; - } - goto again; - } - - ret = aops->prepare_write(file, page, offset, offset+len); - if (ret) { - unlock_page(page); - page_cache_release(page); - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); - } - return ret; - } } EXPORT_SYMBOL(pagecache_write_begin); @@ -2079,32 +2039,9 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; - int ret; - - if (aops->write_end) { - mark_page_accessed(page); - ret = aops->write_end(file, mapping, pos, len, copied, - page, fsdata); - } else { - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); - struct inode *inode = mapping->host; - - flush_dcache_page(page); - ret = aops->commit_write(file, page, offset, offset+len); - unlock_page(page); - mark_page_accessed(page); - page_cache_release(page); - - if (ret < 0) { - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); - } else if (ret > 0) - ret = min_t(size_t, copied, ret); - else - ret = copied; - } - return ret; + mark_page_accessed(page); + return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2226,174 +2163,6 @@ repeat: } EXPORT_SYMBOL(__grab_cache_page); -static ssize_t generic_perform_write_2copy(struct file *file, - struct iov_iter *i, loff_t pos) -{ - struct address_space *mapping = file->f_mapping; - const struct address_space_operations *a_ops = mapping->a_ops; - struct inode *inode = mapping->host; - long status = 0; - ssize_t written = 0; - - do { - struct page *src_page; - struct page *page; - pgoff_t index; /* Pagecache index for current page */ - unsigned long offset; /* Offset into pagecache page */ - unsigned long bytes; /* Bytes to write to page */ - size_t copied; /* Bytes copied from user */ - - offset = (pos & (PAGE_CACHE_SIZE - 1)); - index = pos >> PAGE_CACHE_SHIFT; - bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, - iov_iter_count(i)); - - /* - * a non-NULL src_page indicates that we're doing the - * copy via get_user_pages and kmap. - */ - src_page = NULL; - - /* - * Bring in the user page that we will copy from _first_. - * Otherwise there's a nasty deadlock on copying from the - * same page as we're writing to, without it being marked - * up-to-date. - * - * Not only is this an optimisation, but it is also required - * to check that the address is actually valid, when atomic - * usercopies are used, below. - */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { - status = -EFAULT; - break; - } - - page = __grab_cache_page(mapping, index); - if (!page) { - status = -ENOMEM; - break; - } - - /* - * non-uptodate pages cannot cope with short copies, and we - * cannot take a pagefault with the destination page locked. - * So pin the source page to copy it. - */ - if (!PageUptodate(page) && !segment_eq(get_fs(), KERNEL_DS)) { - unlock_page(page); - - src_page = alloc_page(GFP_KERNEL); - if (!src_page) { - page_cache_release(page); - status = -ENOMEM; - break; - } - - /* - * Cannot get_user_pages with a page locked for the - * same reason as we can't take a page fault with a - * page locked (as explained below). - */ - copied = iov_iter_copy_from_user(src_page, i, - offset, bytes); - if (unlikely(copied == 0)) { - status = -EFAULT; - page_cache_release(page); - page_cache_release(src_page); - break; - } - bytes = copied; - - lock_page(page); - /* - * Can't handle the page going uptodate here, because - * that means we would use non-atomic usercopies, which - * zero out the tail of the page, which can cause - * zeroes to become transiently visible. We could just - * use a non-zeroing copy, but the APIs aren't too - * consistent. - */ - if (unlikely(!page->mapping || PageUptodate(page))) { - unlock_page(page); - page_cache_release(page); - page_cache_release(src_page); - continue; - } - } - - status = a_ops->prepare_write(file, page, offset, offset+bytes); - if (unlikely(status)) - goto fs_write_aop_error; - - if (!src_page) { - /* - * Must not enter the pagefault handler here, because - * we hold the page lock, so we might recursively - * deadlock on the same lock, or get an ABBA deadlock - * against a different lock, or against the mmap_sem - * (which nests outside the page lock). So increment - * preempt count, and use _atomic usercopies. - * - * The page is uptodate so we are OK to encounter a - * short copy: if unmodified parts of the page are - * marked dirty and written out to disk, it doesn't - * really matter. - */ - pagefault_disable(); - copied = iov_iter_copy_from_user_atomic(page, i, - offset, bytes); - pagefault_enable(); - } else { - void *src, *dst; - src = kmap_atomic(src_page, KM_USER0); - dst = kmap_atomic(page, KM_USER1); - memcpy(dst + offset, src + offset, bytes); - kunmap_atomic(dst, KM_USER1); - kunmap_atomic(src, KM_USER0); - copied = bytes; - } - flush_dcache_page(page); - - status = a_ops->commit_write(file, page, offset, offset+bytes); - if (unlikely(status < 0)) - goto fs_write_aop_error; - if (unlikely(status > 0)) /* filesystem did partial write */ - copied = min_t(size_t, copied, status); - - unlock_page(page); - mark_page_accessed(page); - page_cache_release(page); - if (src_page) - page_cache_release(src_page); - - iov_iter_advance(i, copied); - pos += copied; - written += copied; - - balance_dirty_pages_ratelimited(mapping); - cond_resched(); - continue; - -fs_write_aop_error: - unlock_page(page); - page_cache_release(page); - if (src_page) - page_cache_release(src_page); - - /* - * prepare_write() may have instantiated a few blocks - * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. - */ - if (pos + bytes > inode->i_size) - vmtruncate(inode, inode->i_size); - break; - } while (iov_iter_count(i)); - - return written ? written : status; -} - static ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { @@ -2494,10 +2263,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, struct iov_iter i; iov_iter_init(&i, iov, nr_segs, count, written); - if (a_ops->write_begin) - status = generic_perform_write(file, &i, pos); - else - status = generic_perform_write_2copy(file, &i, pos); + status = generic_perform_write(file, &i, pos); if (likely(status >= 0)) { written += status; diff --git a/mm/mmap.c b/mm/mmap.c index 74f4d158022..de14ac21e5b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -175,7 +175,8 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) /* Don't let a single process grow too big: leave 3% of the size of this process for other processes */ - allowed -= mm->total_vm / 32; + if (mm) + allowed -= mm->total_vm / 32; /* * cast `allowed' as a signed long because vm_committed_space diff --git a/mm/nommu.c b/mm/nommu.c index 2696b24f2bb..7695dc85078 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1454,7 +1454,8 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) /* Don't let a single process grow too big: leave 3% of the size of this process for other processes */ - allowed -= current->mm->total_vm / 32; + if (mm) + allowed -= mm->total_vm / 32; /* * cast `allowed' as a signed long because vm_committed_space diff --git a/mm/shmem.c b/mm/shmem.c index d38d7e61fcd..0ed075215e5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -161,8 +161,8 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { - return (flags & VM_ACCOUNT)? - security_vm_enough_memory(VM_ACCT(size)): 0; + return (flags & VM_ACCOUNT) ? + security_vm_enough_memory_kern(VM_ACCT(size)) : 0; } static inline void shmem_unacct_size(unsigned long flags, loff_t size) @@ -179,8 +179,8 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) */ static inline int shmem_acct_block(unsigned long flags) { - return (flags & VM_ACCOUNT)? - 0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE)); + return (flags & VM_ACCOUNT) ? + 0 : security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 036536945dd..f1cc03bbf6a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -897,7 +897,8 @@ EXPORT_SYMBOL(vm_unmap_ram); * @count: number of pages * @node: prefer to allocate data structures on this node * @prot: memory protection to use. PAGE_KERNEL for regular RAM - * @returns: a pointer to the address that has been mapped, or NULL on failure + * + * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) { diff --git a/security/security.c b/security/security.c index 255b08559b2..c0acfa7177e 100644 --- a/security/security.c +++ b/security/security.c @@ -198,14 +198,23 @@ int security_settime(struct timespec *ts, struct timezone *tz) int security_vm_enough_memory(long pages) { + WARN_ON(current->mm == NULL); return security_ops->vm_enough_memory(current->mm, pages); } int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { + WARN_ON(mm == NULL); return security_ops->vm_enough_memory(mm, pages); } +int security_vm_enough_memory_kern(long pages) +{ + /* If current->mm is a kernel thread then we will pass NULL, + for this specific case that is fine */ + return security_ops->vm_enough_memory(current->mm, pages); +} + int security_bprm_alloc(struct linux_binprm *bprm) { return security_ops->bprm_alloc_security(bprm); |