diff options
437 files changed, 8355 insertions, 3592 deletions
diff --git a/Documentation/ABI/testing/evm b/Documentation/ABI/testing/evm new file mode 100644 index 000000000000..8374d4557e5d --- /dev/null +++ b/Documentation/ABI/testing/evm @@ -0,0 +1,23 @@ +What: security/evm +Date: March 2011 +Contact: Mimi Zohar <zohar@us.ibm.com> +Description: + EVM protects a file's security extended attributes(xattrs) + against integrity attacks. The initial method maintains an + HMAC-sha1 value across the extended attributes, storing the + value as the extended attribute 'security.evm'. + + EVM depends on the Kernel Key Retention System to provide it + with a trusted/encrypted key for the HMAC-sha1 operation. + The key is loaded onto the root's keyring using keyctl. Until + EVM receives notification that the key has been successfully + loaded onto the keyring (echo 1 > <securityfs>/evm), EVM + can not create or validate the 'security.evm' xattr, but + returns INTEGRITY_UNKNOWN. Loading the key and signaling EVM + should be done as early as possible. Normally this is done + in the initramfs, which has already been measured as part + of the trusted boot. For more information on creating and + loading existing trusted/encrypted keys, refer to: + Documentation/keys-trusted-encrypted.txt. (A sample dracut + patch, which loads the trusted/encrypted key and enables + EVM, is available from http://linux-ima.sourceforge.net/#EVM.) diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt new file mode 100644 index 000000000000..7ca52161e7ab --- /dev/null +++ b/Documentation/devicetree/bindings/arm/l2cc.txt @@ -0,0 +1,44 @@ +* ARM L2 Cache Controller + +ARM cores often have a separate level 2 cache controller. There are various +implementations of the L2 cache controller with compatible programming models. +The ARM L2 cache representation in the device tree should be done as follows: + +Required properties: + +- compatible : should be one of: + "arm,pl310-cache" + "arm,l220-cache" + "arm,l210-cache" +- cache-unified : Specifies the cache is a unified cache. +- cache-level : Should be set to 2 for a level 2 cache. +- reg : Physical base address and size of cache controller's memory mapped + registers. + +Optional properties: + +- arm,data-latency : Cycles of latency for Data RAM accesses. Specifies 3 cells of + read, write and setup latencies. Minimum valid values are 1. Controllers + without setup latency control should use a value of 0. +- arm,tag-latency : Cycles of latency for Tag RAM accesses. Specifies 3 cells of + read, write and setup latencies. Controllers without setup latency control + should use 0. Controllers without separate read and write Tag RAM latency + values should only use the first cell. +- arm,dirty-latency : Cycles of latency for Dirty RAMs. This is a single cell. +- arm,filter-ranges : <start length> Starting address and length of window to + filter. Addresses in the filter window are directed to the M1 port. Other + addresses will go to the M0 port. +- interrupts : 1 combined interrupt. + +Example: + +L2: cache-controller { + compatible = "arm,pl310-cache"; + reg = <0xfff12000 0x1000>; + arm,data-latency = <1 1 1>; + arm,tag-latency = <2 2 2>; + arm,filter-latency = <0x80000000 0x8000000>; + cache-unified; + cache-level = <2>; + interrupts = <45>; +}; diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 854ed5ca7e3f..d317f6cf0d35 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -49,6 +49,7 @@ parameter is applicable: EDD BIOS Enhanced Disk Drive Services (EDD) is enabled EFI EFI Partitioning (GPT) is enabled EIDE EIDE/ATAPI support is enabled. + EVM Extended Verification Module FB The frame buffer device is enabled. FTRACE Function tracing enabled. GCOV GCOV profiling is enabled. @@ -760,6 +761,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. This option is obsoleted by the "netdev=" option, which has equivalent usage. See its documentation for details. + evm= [EVM] + Format: { "fix" } + Permit 'security.evm' to be updated regardless of + current integrity status. + failslab= fail_page_alloc= fail_make_request=[KNL] @@ -2706,10 +2712,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. functions are at fixed addresses, they make nice targets for exploits that can control RIP. - emulate [default] Vsyscalls turn into traps and are - emulated reasonably safely. + emulate Vsyscalls turn into traps and are emulated + reasonably safely. - native Vsyscalls are native syscall instructions. + native [default] Vsyscalls are native syscall + instructions. This is a little bit faster than trapping and makes a few dynamic recompilers work better than they would in emulation mode. diff --git a/MAINTAINERS b/MAINTAINERS index 5483e0c93b4b..51a8160dc549 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2460,7 +2460,7 @@ S: Supported F: drivers/infiniband/hw/ehca/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Breno Leitao <leitao@linux.vnet.ibm.com> +M: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ehea/ @@ -2552,6 +2552,11 @@ S: Maintained F: Documentation/filesystems/ext4.txt F: fs/ext4/ +Extended Verification Module (EVM) +M: Mimi Zohar <zohar@us.ibm.com> +S: Supported +F: security/integrity/evm/ + F71805F HARDWARE MONITORING DRIVER M: Jean Delvare <khali@linux-fr.org> L: lm-sensors@lm-sensors.org @@ -3313,7 +3318,7 @@ M: David Woodhouse <dwmw2@infradead.org> L: iommu@lists.linux-foundation.org T: git git://git.infradead.org/iommu-2.6.git S: Supported -F: drivers/pci/intel-iommu.c +F: drivers/iommu/intel-iommu.c F: include/linux/intel-iommu.h INTEL IOP-ADMA DMA DRIVER @@ -6447,7 +6452,7 @@ L: tomoyo-users-en@lists.sourceforge.jp (subscribers-only, for users in English) L: tomoyo-dev@lists.sourceforge.jp (subscribers-only, for developers in Japanese) L: tomoyo-users@lists.sourceforge.jp (subscribers-only, for users in Japanese) W: http://tomoyo.sourceforge.jp/ -T: quilt http://svn.sourceforge.jp/svnroot/tomoyo/trunk/2.4.x/tomoyo-lsm/patches/ +T: quilt http://svn.sourceforge.jp/svnroot/tomoyo/trunk/2.5.x/tomoyo-lsm/patches/ S: Maintained F: security/tomoyo/ @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc9 +EXTRAVERSION = NAME = "Divemaster Edition" # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3146ed3f6eca..92e695412bd5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -3,7 +3,7 @@ config ARM default y select HAVE_AOUT select HAVE_DMA_API_DEBUG - select HAVE_IDE + select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_MEMBLOCK select RTC_LIB select SYS_SUPPORTS_APM_EMULATION @@ -195,7 +195,8 @@ config VECTORS_BASE The base address of exception vectors. config ARM_PATCH_PHYS_VIRT - bool "Patch physical to virtual translations at runtime" + bool "Patch physical to virtual translations at runtime" if EMBEDDED + default y depends on !XIP_KERNEL && MMU depends on !ARCH_REALVIEW || !SPARSEMEM help @@ -204,16 +205,16 @@ config ARM_PATCH_PHYS_VIRT kernel in system memory. This can only be used with non-XIP MMU kernels where the base - of physical memory is at a 16MB boundary, or theoretically 64K - for the MSM machine class. + of physical memory is at a 16MB boundary. + + Only disable this option if you know that you do not require + this feature (eg, building a kernel for a single machine) and + you need to shrink the kernel to the minimal size. -config ARM_PATCH_PHYS_VIRT_16BIT + +config GENERIC_BUG def_bool y - depends on ARM_PATCH_PHYS_VIRT && ARCH_MSM - help - This option extends the physical to virtual translation patching - to allow physical memory down to a theoretical minimum of 64K - boundaries. + depends on BUG source "init/Kconfig" @@ -301,7 +302,6 @@ config ARCH_AT91 select ARCH_REQUIRE_GPIOLIB select HAVE_CLK select CLKDEV_LOOKUP - select ARM_PATCH_PHYS_VIRT if MMU help This enables support for systems based on the Atmel AT91RM9200, AT91SAM9 and AT91CAP9 processors. @@ -385,6 +385,7 @@ config ARCH_FOOTBRIDGE select CPU_SA110 select FOOTBRIDGE select GENERIC_CLOCKEVENTS + select HAVE_IDE help Support for systems based on the DC21285 companion chip ("FootBridge"), such as the Simtec CATS and the Rebel NetWinder. @@ -631,6 +632,8 @@ config ARCH_PXA select SPARSE_IRQ select AUTO_ZRELADDR select MULTI_IRQ_HANDLER + select ARM_CPU_SUSPEND if PM + select HAVE_IDE help Support for Intel/Marvell's PXA2xx/PXA3xx processor line. @@ -671,6 +674,7 @@ config ARCH_RPC select NO_IOPORT select ARCH_SPARSEMEM_ENABLE select ARCH_USES_GETTIMEOFFSET + select HAVE_IDE help On the Acorn Risc-PC, Linux can support the internal IDE disk and CD-ROM interface, serial and parallel port, and the floppy drive. @@ -689,6 +693,7 @@ config ARCH_SA1100 select HAVE_SCHED_CLOCK select TICK_ONESHOT select ARCH_REQUIRE_GPIOLIB + select HAVE_IDE help Support for StrongARM 11x0 based boards. @@ -1375,6 +1380,7 @@ config SMP MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \ ARCH_EXYNOS4 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \ ARCH_MSM_SCORPIONMP || ARCH_SHMOBILE + depends on MMU select USE_GENERIC_SMP_HELPERS select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP help @@ -1407,6 +1413,31 @@ config SMP_ON_UP If you don't know what to do here, say Y. +config ARM_CPU_TOPOLOGY + bool "Support cpu topology definition" + depends on SMP && CPU_V7 + default y + help + Support ARM cpu topology definition. The MPIDR register defines + affinity between processors which is then used to describe the cpu + topology of an ARM System. + +config SCHED_MC + bool "Multi-core scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + +config SCHED_SMT + bool "SMT scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Improves the CPU scheduler's decision making when dealing with + MultiThreading at a cost of slightly increased overhead in some + places. If unsure say N here. + config HAVE_ARM_SCU bool help @@ -1482,6 +1513,7 @@ config THUMB2_KERNEL depends on CPU_V7 && !CPU_V6 && !CPU_V6K && EXPERIMENTAL select AEABI select ARM_ASM_UNIFIED + select ARM_UNWIND help By enabling this option, the kernel will be compiled in Thumb-2 mode. A compiler/assembler that understand the unified @@ -2101,6 +2133,9 @@ config ARCH_SUSPEND_POSSIBLE CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE def_bool y +config ARM_CPU_SUSPEND + def_bool PM_SLEEP + endmenu source "net/Kconfig" diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 81cbe40c159c..df3eb3ccd769 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -65,13 +65,71 @@ config DEBUG_USER # These options are only for real kernel hackers who want to get their hands dirty. config DEBUG_LL - bool "Kernel low-level debugging functions" + bool "Kernel low-level debugging functions (read help!)" depends on DEBUG_KERNEL help Say Y here to include definitions of printascii, printch, printhex in the kernel. This is helpful if you are debugging code that executes before the console is initialized. + Note that selecting this option will limit the kernel to a single + UART definition, as specified below. Attempting to boot the kernel + image on a different platform *will not work*, so this option should + not be enabled for kernels that are intended to be portable. + +choice + prompt "Kernel low-level debugging port" + depends on DEBUG_LL + + config DEBUG_LL_UART_NONE + bool "No low-level debugging UART" + help + Say Y here if your platform doesn't provide a UART option + below. This relies on your platform choosing the right UART + definition internally in order for low-level debugging to + work. + + config DEBUG_ICEDCC + bool "Kernel low-level debugging via EmbeddedICE DCC channel" + help + Say Y here if you want the debug print routines to direct + their output to the EmbeddedICE macrocell's DCC channel using + co-processor 14. This is known to work on the ARM9 style ICE + channel and on the XScale with the PEEDI. + + Note that the system will appear to hang during boot if there + is nothing connected to read from the DCC. + + config DEBUG_FOOTBRIDGE_COM1 + bool "Kernel low-level debugging messages via footbridge 8250 at PCI COM1" + depends on FOOTBRIDGE + help + Say Y here if you want the debug print routines to direct + their output to the 8250 at PCI COM1. + + config DEBUG_DC21285_PORT + bool "Kernel low-level debugging messages via footbridge serial port" + depends on FOOTBRIDGE + help + Say Y here if you want the debug print routines to direct + their output to the serial port in the DC21285 (Footbridge). + + config DEBUG_CLPS711X_UART1 + bool "Kernel low-level debugging messages via UART1" + depends on ARCH_CLPS711X + help + Say Y here if you want the debug print routines to direct + their output to the first serial port on these devices. + + config DEBUG_CLPS711X_UART2 + bool "Kernel low-level debugging messages via UART2" + depends on ARCH_CLPS711X + help + Say Y here if you want the debug print routines to direct + their output to the second serial port on these devices. + +endchoice + config EARLY_PRINTK bool "Early printk" depends on DEBUG_LL @@ -80,43 +138,14 @@ config EARLY_PRINTK kernel low-level debugging functions. Add earlyprintk to your kernel parameters to enable this console. -config DEBUG_ICEDCC - bool "Kernel low-level debugging via EmbeddedICE DCC channel" - depends on DEBUG_LL - help - Say Y here if you want the debug print routines to direct their - output to the EmbeddedICE macrocell's DCC channel using - co-processor 14. This is known to work on the ARM9 style ICE - channel and on the XScale with the PEEDI. - - It does include a timeout to ensure that the system does not - totally freeze when there is nothing connected to read. - config OC_ETM bool "On-chip ETM and ETB" - select ARM_AMBA + depends on ARM_AMBA help Enables the on-chip embedded trace macrocell and embedded trace buffer driver that will allow you to collect traces of the kernel code. -config DEBUG_DC21285_PORT - bool "Kernel low-level debugging messages via footbridge serial port" - depends on DEBUG_LL && FOOTBRIDGE - help - Say Y here if you want the debug print routines to direct their - output to the serial port in the DC21285 (Footbridge). Saying N - will cause the debug messages to appear on the first 16550 - serial port. - -config DEBUG_CLPS711X_UART2 - bool "Kernel low-level debugging messages via UART2" - depends on DEBUG_LL && ARCH_CLPS711X - help - Say Y here if you want the debug print routines to direct their - output to the second serial port on these devices. Saying N will - cause the debug messages to appear on the first serial port. - config DEBUG_S3C_UART depends on PLAT_SAMSUNG int "S3C UART to use for low-level debug" diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 70c424eaf7b0..5665c2a3b652 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -128,6 +128,9 @@ textofs-$(CONFIG_PM_H1940) := 0x00108000 ifeq ($(CONFIG_ARCH_SA1100),y) textofs-$(CONFIG_SA1111) := 0x00208000 endif +textofs-$(CONFIG_ARCH_MSM7X30) := 0x00208000 +textofs-$(CONFIG_ARCH_MSM8X60) := 0x00208000 +textofs-$(CONFIG_ARCH_MSM8960) := 0x00208000 # Machine directory name. This list is sorted alphanumerically # by CONFIG_* macro name. diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index a1edfd5a129a..176062ac7f07 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -78,7 +78,16 @@ endif $(obj)/uImage: STARTADDR=$(LOADADDR) +check_for_multiple_loadaddr = \ +if [ $(words $(LOADADDR)) -gt 1 ]; then \ + echo 'multiple load addresses: $(LOADADDR)'; \ + echo 'This is incompatible with uImages'; \ + echo 'Specify LOADADDR on the commandline to build an uImage'; \ + false; \ +fi + $(obj)/uImage: $(obj)/zImage FORCE + @$(check_for_multiple_loadaddr) $(call if_changed,uimage) @echo ' Image $@ is ready' diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 0c74a6fab952..a6b30b35ca65 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -139,8 +139,16 @@ bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \ ( echo "following symbols must have non local/private scope:" >&2; \ echo "$$bad_syms" >&2; rm -f $@; false ) +check_for_multiple_zreladdr = \ +if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \ + echo 'multiple zreladdrs: $(ZRELADDR)'; \ + echo 'This needs CONFIG_AUTO_ZRELADDR to be set'; \ + false; \ +fi + $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \ $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE + @$(check_for_multiple_zreladdr) $(call if_changed,ld) @$(check_for_bad_syms) diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 3227ca952a12..666b278e56d7 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -180,7 +180,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, return -EINVAL; mask = 0xff << shift; - bit = 1 << (cpu + shift); + bit = 1 << (cpu_logical_map(cpu) + shift); spin_lock(&irq_controller_lock); val = readl_relaxed(reg) & ~mask; @@ -259,9 +259,15 @@ static void __init gic_dist_init(struct gic_chip_data *gic, unsigned int irq_start) { unsigned int gic_irqs, irq_limit, i; + u32 cpumask; void __iomem *base = gic->dist_base; - u32 cpumask = 1 << smp_processor_id(); + u32 cpu = 0; +#ifdef CONFIG_SMP + cpu = cpu_logical_map(smp_processor_id()); +#endif + + cpumask = 1 << cpu; cpumask |= cpumask << 8; cpumask |= cpumask << 16; @@ -382,7 +388,12 @@ void __cpuinit gic_enable_ppi(unsigned int irq) #ifdef CONFIG_SMP void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) { - unsigned long map = *cpus_addr(*mask); + int cpu; + unsigned long map = 0; + + /* Convert our logical CPU mask into a physical one. */ + for_each_cpu(cpu, mask) + map |= 1 << cpu_logical_map(cpu); /* * Ensure that stores to Normal memory are visible to the diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c index 97912fa48782..7129cfbdacd6 100644 --- a/arch/arm/common/pl330.c +++ b/arch/arm/common/pl330.c @@ -1546,7 +1546,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op) /* Start the next */ case PL330_OP_START: - if (!_start(thrd)) + if (!_thrd_active(thrd) && !_start(thrd)) ret = -EIO; break; diff --git a/arch/arm/common/vic.c b/arch/arm/common/vic.c index 7aa4262ada7a..01f18a421b17 100644 --- a/arch/arm/common/vic.c +++ b/arch/arm/common/vic.c @@ -259,7 +259,6 @@ static void __init vic_disable(void __iomem *base) writel(0, base + VIC_INT_SELECT); writel(0, base + VIC_INT_ENABLE); writel(~0, base + VIC_INT_ENABLE_CLEAR); - writel(0, base + VIC_IRQ_STATUS); writel(0, base + VIC_ITCR); writel(~0, base + VIC_INT_SOFT_CLEAR); } @@ -347,7 +346,8 @@ void __init vic_init(void __iomem *base, unsigned int irq_start, /* Identify which VIC cell this one is, by reading the ID */ for (i = 0; i < 4; i++) { - u32 addr = ((u32)base & PAGE_MASK) + 0xfe0 + (i * 4); + void __iomem *addr; + addr = (void __iomem *)((u32)base & PAGE_MASK) + 0xfe0 + (i * 4); cellid |= (readl(addr) & 0xff) << (8 * i); } vendor = (cellid >> 12) & 0xff; diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index 7196ade07e27..1103f62a1964 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -1,5 +1,6 @@ CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y +CONFIG_TINY_RCU=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -8,20 +9,29 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_ARCH_INTEGRATOR=y CONFIG_ARCH_INTEGRATOR_AP=y +CONFIG_ARCH_INTEGRATOR_CP=y CONFIG_CPU_ARM720T=y CONFIG_CPU_ARM920T=y +CONFIG_CPU_ARM922T=y +CONFIG_CPU_ARM926T=y +CONFIG_CPU_ARM1020=y +CONFIG_CPU_ARM1022=y +CONFIG_CPU_ARM1026=y CONFIG_PCI=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y +CONFIG_AEABI=y CONFIG_LEDS=y CONFIG_LEDS_CPU=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp mem=32M" +CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp" CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_FPE_NWFPE=y -CONFIG_PM=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -32,7 +42,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y # CONFIG_IPV6 is not set CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_AFS_PARTS=y CONFIG_MTD_CHAR=y @@ -40,6 +49,7 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 @@ -56,6 +66,8 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_PL030=y CONFIG_EXT2_FS=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y @@ -68,4 +80,3 @@ CONFIG_NFSD_V3=y CONFIG_PARTITION_ADVANCED=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_ERRORS=y diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 6550db3aa5c7..960abceb8e14 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -1,3 +1,20 @@ include include/asm-generic/Kbuild.asm header-y += hwcap.h + +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += cputime.h +generic-y += emergency-restart.h +generic-y += errno.h +generic-y += ioctl.h +generic-y += irq_regs.h +generic-y += kdebug.h +generic-y += local.h +generic-y += local64.h +generic-y += percpu.h +generic-y += poll.h +generic-y += resource.h +generic-y += sections.h +generic-y += siginfo.h +generic-y += sizes.h diff --git a/arch/arm/include/asm/auxvec.h b/arch/arm/include/asm/auxvec.h deleted file mode 100644 index c0536f6b29a7..000000000000 --- a/arch/arm/include/asm/auxvec.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef __ASMARM_AUXVEC_H -#define __ASMARM_AUXVEC_H - -#endif diff --git a/arch/arm/include/asm/bitsperlong.h b/arch/arm/include/asm/bitsperlong.h deleted file mode 100644 index 6dc0bb0c13b2..000000000000 --- a/arch/arm/include/asm/bitsperlong.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bitsperlong.h> diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 4d88425a4169..9abe7a07d5ac 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -3,21 +3,58 @@ #ifdef CONFIG_BUG -#ifdef CONFIG_DEBUG_BUGVERBOSE -extern void __bug(const char *file, int line) __attribute__((noreturn)); - -/* give file/line information */ -#define BUG() __bug(__FILE__, __LINE__) +/* + * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling. + * We need to be careful not to conflict with those used by other modules and + * the register_undef_hook() system. + */ +#ifdef CONFIG_THUMB2_KERNEL +#define BUG_INSTR_VALUE 0xde02 +#define BUG_INSTR_TYPE ".hword " #else +#define BUG_INSTR_VALUE 0xe7f001f2 +#define BUG_INSTR_TYPE ".word " +#endif -/* this just causes an oops */ -#define BUG() do { *(int *)0 = 0; } while (1) -#endif +#define BUG() _BUG(__FILE__, __LINE__, BUG_INSTR_VALUE) +#define _BUG(file, line, value) __BUG(file, line, value) + +#ifdef CONFIG_DEBUG_BUGVERBOSE + +/* + * The extra indirection is to ensure that the __FILE__ string comes through + * OK. Many version of gcc do not support the asm %c parameter which would be + * preferable to this unpleasantness. We use mergeable string sections to + * avoid multiple copies of the string appearing in the kernel image. + */ + +#define __BUG(__file, __line, __value) \ +do { \ + BUILD_BUG_ON(sizeof(struct bug_entry) != 12); \ + asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \ + ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ + "2:\t.asciz " #__file "\n" \ + ".popsection\n" \ + ".pushsection __bug_table,\"a\"\n" \ + "3:\t.word 1b, 2b\n" \ + "\t.hword " #__line ", 0\n" \ + ".popsection"); \ + unreachable(); \ +} while (0) + +#else /* not CONFIG_DEBUG_BUGVERBOSE */ + +#define __BUG(__file, __line, __value) \ +do { \ + asm volatile(BUG_INSTR_TYPE #__value); \ + unreachable(); \ +} while (0) +#endif /* CONFIG_DEBUG_BUGVERBOSE */ #define HAVE_ARCH_BUG -#endif +#endif /* CONFIG_BUG */ #include <asm-generic/bug.h> diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h index c023db09fcc1..7ea78144ae22 100644 --- a/arch/arm/include/asm/cachetype.h +++ b/arch/arm/include/asm/cachetype.h @@ -7,6 +7,7 @@ #define CACHEID_VIPT (CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING) #define CACHEID_ASID_TAGGED (1 << 3) #define CACHEID_VIPT_I_ALIASING (1 << 4) +#define CACHEID_PIPT (1 << 5) extern unsigned int cacheid; @@ -16,6 +17,7 @@ extern unsigned int cacheid; #define cache_is_vipt_aliasing() cacheid_is(CACHEID_VIPT_ALIASING) #define icache_is_vivt_asid_tagged() cacheid_is(CACHEID_ASID_TAGGED) #define icache_is_vipt_aliasing() cacheid_is(CACHEID_VIPT_I_ALIASING) +#define icache_is_pipt() cacheid_is(CACHEID_PIPT) /* * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture @@ -26,7 +28,8 @@ extern unsigned int cacheid; #if __LINUX_ARM_ARCH__ >= 7 #define __CACHEID_ARCH_MIN (CACHEID_VIPT_NONALIASING |\ CACHEID_ASID_TAGGED |\ - CACHEID_VIPT_I_ALIASING) + CACHEID_VIPT_I_ALIASING |\ + CACHEID_PIPT) #elif __LINUX_ARM_ARCH__ >= 6 #define __CACHEID_ARCH_MIN (~CACHEID_VIVT) #else diff --git a/arch/arm/include/asm/cputime.h b/arch/arm/include/asm/cputime.h deleted file mode 100644 index 3a8002a5fec7..000000000000 --- a/arch/arm/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ARM_CPUTIME_H -#define __ARM_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __ARM_CPUTIME_H */ diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index cd4458f64171..cb47d28cbe1f 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -8,6 +8,7 @@ #define CPUID_CACHETYPE 1 #define CPUID_TCM 2 #define CPUID_TLBTYPE 3 +#define CPUID_MPIDR 5 #define CPUID_EXT_PFR0 "c1, 0" #define CPUID_EXT_PFR1 "c1, 1" @@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void) return read_cpuid(CPUID_TCM); } +static inline unsigned int __attribute_const__ read_cpuid_mpidr(void) +{ + return read_cpuid(CPUID_MPIDR); +} + /* * Intel's XScale3 core supports some v6 features (supersections, L2) * but advertises itself as v5 as it does not support the v6 ISA. For diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index 9f390ce335cb..6615f03f56a5 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -10,6 +10,9 @@ struct dev_archdata { #ifdef CONFIG_DMABOUNCE struct dmabounce_device_info *dmabounce; #endif +#ifdef CONFIG_IOMMU_API + void *iommu; /* private IOMMU data */ +#endif }; struct pdev_archdata { diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 7a21d0bf7134..28b7ee8d7398 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -32,7 +32,7 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) static inline void *dma_to_virt(struct device *dev, dma_addr_t addr) { - return (void *)__bus_to_virt(addr); + return (void *)__bus_to_virt((unsigned long)addr); } static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h index 29f2610efc70..eaea14676d57 100644 --- a/arch/arm/include/asm/ecard.h +++ b/arch/arm/include/asm/ecard.h @@ -161,7 +161,6 @@ struct expansion_card { /* Private internal data */ const char *card_desc; /* Card description */ - CONST unsigned int podaddr; /* Base Linux address for card */ CONST loader_t loader; /* loader program */ u64 dma_mask; }; diff --git a/arch/arm/include/asm/emergency-restart.h b/arch/arm/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c48e42e..000000000000 --- a/arch/arm/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/arm/include/asm/errno.h b/arch/arm/include/asm/errno.h deleted file mode 100644 index 6e60f0612bb6..000000000000 --- a/arch/arm/include/asm/errno.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ARM_ERRNO_H -#define _ARM_ERRNO_H - -#include <asm-generic/errno.h> - -#endif diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h new file mode 100644 index 000000000000..5abaf5bbd985 --- /dev/null +++ b/arch/arm/include/asm/exception.h @@ -0,0 +1,19 @@ +/* + * Annotations for marking C functions as exception handlers. + * + * These should only be used for C functions that are called from the low + * level exception entry code and not any intervening C code. + */ +#ifndef __ASM_ARM_EXCEPTION_H +#define __ASM_ARM_EXCEPTION_H + +#include <linux/ftrace.h> + +#define __exception __attribute__((section(".exception.text"))) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#define __exception_irq_entry __irq_entry +#else +#define __exception_irq_entry __exception +#endif + +#endif /* __ASM_ARM_EXCEPTION_H */ diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 99a6ed7e1bfd..434edccdf7f3 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -52,6 +52,8 @@ #define L2X0_LOCKDOWN_WAY_D_BASE 0x900 #define L2X0_LOCKDOWN_WAY_I_BASE 0x904 #define L2X0_LOCKDOWN_STRIDE 0x08 +#define L2X0_ADDR_FILTER_START 0xC00 +#define L2X0_ADDR_FILTER_END 0xC04 #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 @@ -65,8 +67,23 @@ #define L2X0_CACHE_ID_PART_MASK (0xf << 6) #define L2X0_CACHE_ID_PART_L210 (1 << 6) #define L2X0_CACHE_ID_PART_L310 (3 << 6) +#define L2X0_CACHE_ID_RTL_MASK 0x3f +#define L2X0_CACHE_ID_RTL_R0P0 0x0 +#define L2X0_CACHE_ID_RTL_R1P0 0x2 +#define L2X0_CACHE_ID_RTL_R2P0 0x4 +#define L2X0_CACHE_ID_RTL_R3P0 0x5 +#define L2X0_CACHE_ID_RTL_R3P1 0x6 +#define L2X0_CACHE_ID_RTL_R3P2 0x8 #define L2X0_AUX_CTRL_MASK 0xc0000fff +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT 0 +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK 0x7 +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT 3 +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (0x7 << 3) +#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT 6 +#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (0x7 << 6) +#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT 9 +#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (0x7 << 9) #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT 16 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT 17 #define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x7 << 17) @@ -77,8 +94,33 @@ #define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT 29 #define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT 30 +#define L2X0_LATENCY_CTRL_SETUP_SHIFT 0 +#define L2X0_LATENCY_CTRL_RD_SHIFT 4 +#define L2X0_LATENCY_CTRL_WR_SHIFT 8 + +#define L2X0_ADDR_FILTER_EN 1 + #ifndef __ASSEMBLY__ extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask); +extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask); + +struct l2x0_regs { + unsigned long phy_base; + unsigned long aux_ctrl; + /* + * Whether the following registers need to be saved/restored + * depends on platform + */ + unsigned long tag_latency; + unsigned long data_latency; + unsigned long filter_start; + unsigned long filter_end; + unsigned long prefetch_ctrl; + unsigned long pwr_ctrl; +}; + +extern struct l2x0_regs l2x0_saved_regs; + #endif #endif diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index d66605dea55a..769f65d918ac 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -80,6 +80,7 @@ extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int, extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int); extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int); +extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached); extern void __iounmap(volatile void __iomem *addr); /* @@ -110,6 +111,27 @@ static inline void __iomem *__typesafe_io(unsigned long addr) #include <mach/io.h> /* + * This is the limit of PC card/PCI/ISA IO space, which is by default + * 64K if we have PC card, PCI or ISA support. Otherwise, default to + * zero to prevent ISA/PCI drivers claiming IO space (and potentially + * oopsing.) + * + * Only set this larger if you really need inb() et.al. to operate over + * a larger address space. Note that SOC_COMMON ioremaps each sockets + * IO space area, and so inb() et.al. must be defined to operate as per + * readb() et.al. on such platforms. + */ +#ifndef IO_SPACE_LIMIT +#if defined(CONFIG_PCMCIA_SOC_COMMON) || defined(CONFIG_PCMCIA_SOC_COMMON_MODULE) +#define IO_SPACE_LIMIT ((resource_size_t)0xffffffff) +#elif defined(CONFIG_PCI) || defined(CONFIG_ISA) || defined(CONFIG_PCCARD) +#define IO_SPACE_LIMIT ((resource_size_t)0xffff) +#else +#define IO_SPACE_LIMIT ((resource_size_t)0) +#endif +#endif + +/* * IO port access primitives * ------------------------- * @@ -189,11 +211,11 @@ extern void _memset_io(volatile void __iomem *, int, size_t); * IO port primitives for more information. */ #ifdef __mem_pci -#define readb_relaxed(c) ({ u8 __v = __raw_readb(__mem_pci(c)); __v; }) -#define readw_relaxed(c) ({ u16 __v = le16_to_cpu((__force __le16) \ - __raw_readw(__mem_pci(c))); __v; }) -#define readl_relaxed(c) ({ u32 __v = le32_to_cpu((__force __le32) \ - __raw_readl(__mem_pci(c))); __v; }) +#define readb_relaxed(c) ({ u8 __r = __raw_readb(__mem_pci(c)); __r; }) +#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \ + __raw_readw(__mem_pci(c))); __r; }) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \ + __raw_readl(__mem_pci(c))); __r; }) #define writeb_relaxed(v,c) ((void)__raw_writeb(v,__mem_pci(c))) #define writew_relaxed(v,c) ((void)__raw_writew((__force u16) \ @@ -260,10 +282,16 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define ioread16(p) ({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; }) #define ioread32(p) ({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; }) +#define ioread16be(p) ({ unsigned int __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ unsigned int __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + #define iowrite8(v,p) ({ __iowmb(); (void)__raw_writeb(v, p); }) #define iowrite16(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_le16(v), p); }) #define iowrite32(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_le32(v), p); }) +#define iowrite16be(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_be32(v), p); }) + #define ioread8_rep(p,d,c) __raw_readsb(p,d,c) #define ioread16_rep(p,d,c) __raw_readsw(p,d,c) #define ioread32_rep(p,d,c) __raw_readsl(p,d,c) diff --git a/arch/arm/include/asm/ioctl.h b/arch/arm/include/asm/ioctl.h deleted file mode 100644 index b279fe06dfe5..000000000000 --- a/arch/arm/include/asm/ioctl.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ioctl.h> diff --git a/arch/arm/include/asm/irq_regs.h b/arch/arm/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b70270..000000000000 --- a/arch/arm/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/irq_regs.h> diff --git a/arch/arm/include/asm/kdebug.h b/arch/arm/include/asm/kdebug.h deleted file mode 100644 index 6ece1b037665..000000000000 --- a/arch/arm/include/asm/kdebug.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/kdebug.h> diff --git a/arch/arm/include/asm/local.h b/arch/arm/include/asm/local.h deleted file mode 100644 index c11c530f74d0..000000000000 --- a/arch/arm/include/asm/local.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local.h> diff --git a/arch/arm/include/asm/local64.h b/arch/arm/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/arm/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h index 080d74f8128d..6fd955d34c65 100644 --- a/arch/arm/include/asm/localtimer.h +++ b/arch/arm/include/asm/localtimer.h @@ -10,6 +10,8 @@ #ifndef __ASM_ARM_LOCALTIMER_H #define __ASM_ARM_LOCALTIMER_H +#include <linux/errno.h> + struct clock_event_device; /* @@ -22,6 +24,10 @@ void percpu_timer_setup(void); */ asmlinkage void do_local_timer(struct pt_regs *); +/* + * Called from C code + */ +void handle_local_timer(struct pt_regs *); #ifdef CONFIG_LOCAL_TIMERS diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 217aa1911dd7..c5699987fa98 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -34,8 +34,7 @@ struct machine_desc { unsigned int reserve_lp1 :1; /* never has lp1 */ unsigned int reserve_lp2 :1; /* never has lp2 */ unsigned int soft_reboot :1; /* soft reboot */ - void (*fixup)(struct machine_desc *, - struct tag *, char **, + void (*fixup)(struct tag *, char **, struct meminfo *); void (*reserve)(void);/* reserve mem blocks */ void (*map_io)(void);/* IO mapping function */ diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index b8de516e600e..441fc4fe8263 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -160,7 +160,6 @@ * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 -#define __PV_BITS_23_16 0x00810000 extern unsigned long __pv_phys_offset; #define PHYS_OFFSET __pv_phys_offset @@ -178,9 +177,6 @@ static inline unsigned long __virt_to_phys(unsigned long x) { unsigned long t; __pv_stub(x, t, "add", __PV_BITS_31_24); -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - __pv_stub(t, t, "add", __PV_BITS_23_16); -#endif return t; } @@ -188,9 +184,6 @@ static inline unsigned long __phys_to_virt(unsigned long x) { unsigned long t; __pv_stub(x, t, "sub", __PV_BITS_31_24); -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - __pv_stub(t, t, "sub", __PV_BITS_23_16); -#endif return t; } #else diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index 543b44916d2c..6c6809f982f1 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -31,11 +31,7 @@ struct mod_arch_specific { /* Add __virt_to_phys patching state as well */ #ifdef CONFIG_ARM_PATCH_PHYS_VIRT -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT -#define MODULE_ARCH_VERMAGIC_P2V "p2v16 " -#else #define MODULE_ARCH_VERMAGIC_P2V "p2v8 " -#endif #else #define MODULE_ARCH_VERMAGIC_P2V "" #endif diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h index d8387437ec5a..53426c66352a 100644 --- a/arch/arm/include/asm/outercache.h +++ b/arch/arm/include/asm/outercache.h @@ -34,6 +34,7 @@ struct outer_cache_fns { void (*sync)(void); #endif void (*set_debug)(unsigned long); + void (*resume)(void); }; #ifdef CONFIG_OUTER_CACHE @@ -74,6 +75,12 @@ static inline void outer_disable(void) outer_cache.disable(); } +static inline void outer_resume(void) +{ + if (outer_cache.resume) + outer_cache.resume(); +} + #else static inline void outer_inv_range(phys_addr_t start, phys_addr_t end) diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index ac75d0848889..ca94653f1ecb 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -151,47 +151,7 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from, #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, const void *from); -typedef unsigned long pteval_t; - -#undef STRICT_MM_TYPECHECKS - -#ifdef STRICT_MM_TYPECHECKS -/* - * These are used to make use of C type-checking.. - */ -typedef struct { pteval_t pte; } pte_t; -typedef struct { unsigned long pmd; } pmd_t; -typedef struct { unsigned long pgd[2]; } pgd_t; -typedef struct { unsigned long pgprot; } pgprot_t; - -#define pte_val(x) ((x).pte) -#define pmd_val(x) ((x).pmd) -#define pgd_val(x) ((x).pgd[0]) -#define pgprot_val(x) ((x).pgprot) - -#define __pte(x) ((pte_t) { (x) } ) -#define __pmd(x) ((pmd_t) { (x) } ) -#define __pgprot(x) ((pgprot_t) { (x) } ) - -#else -/* - * .. while these make it easier on the compiler - */ -typedef pteval_t pte_t; -typedef unsigned long pmd_t; -typedef unsigned long pgd_t[2]; -typedef unsigned long pgprot_t; - -#define pte_val(x) (x) -#define pmd_val(x) (x) -#define pgd_val(x) ((x)[0]) -#define pgprot_val(x) (x) - -#define __pte(x) (x) -#define __pmd(x) (x) -#define __pgprot(x) (x) - -#endif /* STRICT_MM_TYPECHECKS */ +#include <asm/pgtable-2level-types.h> #endif /* CONFIG_MMU */ diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h deleted file mode 100644 index b4e32d8ec072..000000000000 --- a/arch/arm/include/asm/percpu.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ARM_PERCPU -#define __ARM_PERCPU - -#include <asm-generic/percpu.h> - -#endif diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 22de005f159c..3e08fd3fbb6b 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -105,9 +105,9 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) } static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, - unsigned long prot) + pmdval_t prot) { - unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot; + pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot; pmdp[0] = __pmd(pmdval); pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t)); flush_pmd_entry(pmdp); diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h new file mode 100644 index 000000000000..5cfba15cb401 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -0,0 +1,93 @@ +/* + * arch/arm/include/asm/pgtable-2level-hwdef.h + * + * Copyright (C) 1995-2002 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _ASM_PGTABLE_2LEVEL_HWDEF_H +#define _ASM_PGTABLE_2LEVEL_HWDEF_H + +/* + * Hardware page table definitions. + * + * + Level 1 descriptor (PMD) + * - common + */ +#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) +#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) +#define PMD_TYPE_TABLE (_AT(pmdval_t, 1) << 0) +#define PMD_TYPE_SECT (_AT(pmdval_t, 2) << 0) +#define PMD_BIT4 (_AT(pmdval_t, 1) << 4) +#define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5) +#define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */ +/* + * - section + */ +#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2) +#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3) +#define PMD_SECT_XN (_AT(pmdval_t, 1) << 4) /* v6 */ +#define PMD_SECT_AP_WRITE (_AT(pmdval_t, 1) << 10) +#define PMD_SECT_AP_READ (_AT(pmdval_t, 1) << 11) +#define PMD_SECT_TEX(x) (_AT(pmdval_t, (x)) << 12) /* v5 */ +#define PMD_SECT_APX (_AT(pmdval_t, 1) << 15) /* v6 */ +#define PMD_SECT_S (_AT(pmdval_t, 1) << 16) /* v6 */ +#define PMD_SECT_nG (_AT(pmdval_t, 1) << 17) /* v6 */ +#define PMD_SECT_SUPER (_AT(pmdval_t, 1) << 18) /* v6 */ +#define PMD_SECT_AF (_AT(pmdval_t, 0)) + +#define PMD_SECT_UNCACHED (_AT(pmdval_t, 0)) +#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) +#define PMD_SECT_WT (PMD_SECT_CACHEABLE) +#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) +#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) + +/* + * - coarse table (not used) + */ + +/* + * + Level 2 descriptor (PTE) + * - common + */ +#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0) +#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0) +#define PTE_TYPE_LARGE (_AT(pteval_t, 1) << 0) +#define PTE_TYPE_SMALL (_AT(pteval_t, 2) << 0) +#define PTE_TYPE_EXT (_AT(pteval_t, 3) << 0) /* v5 */ +#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) +#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) + +/* + * - extended small page/tiny page + */ +#define PTE_EXT_XN (_AT(pteval_t, 1) << 0) /* v6 */ +#define PTE_EXT_AP_MASK (_AT(pteval_t, 3) << 4) +#define PTE_EXT_AP0 (_AT(pteval_t, 1) << 4) +#define PTE_EXT_AP1 (_AT(pteval_t, 2) << 4) +#define PTE_EXT_AP_UNO_SRO (_AT(pteval_t, 0) << 4) +#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) +#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) +#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) +#define PTE_EXT_TEX(x) (_AT(pteval_t, (x)) << 6) /* v5 */ +#define PTE_EXT_APX (_AT(pteval_t, 1) << 9) /* v6 */ +#define PTE_EXT_COHERENT (_AT(pteval_t, 1) << 9) /* XScale3 */ +#define PTE_EXT_SHARED (_AT(pteval_t, 1) << 10) /* v6 */ +#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* v6 */ + +/* + * - small page + */ +#define PTE_SMALL_AP_MASK (_AT(pteval_t, 0xff) << 4) +#define PTE_SMALL_AP_UNO_SRO (_AT(pteval_t, 0x00) << 4) +#define PTE_SMALL_AP_UNO_SRW (_AT(pteval_t, 0x55) << 4) +#define PTE_SMALL_AP_URO_SRW (_AT(pteval_t, 0xaa) << 4) +#define PTE_SMALL_AP_URW_SRW (_AT(pteval_t, 0xff) << 4) + +#define PHYS_MASK (~0UL) + +#endif diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h new file mode 100644 index 000000000000..66cb5b0e89c5 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level-types.h @@ -0,0 +1,67 @@ +/* + * arch/arm/include/asm/pgtable-2level-types.h + * + * Copyright (C) 1995-2003 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H +#define _ASM_PGTABLE_2LEVEL_TYPES_H + +#include <asm/types.h> + +typedef u32 pteval_t; +typedef u32 pmdval_t; + +#undef STRICT_MM_TYPECHECKS + +#ifdef STRICT_MM_TYPECHECKS +/* + * These are used to make use of C type-checking.. + */ +typedef struct { pteval_t pte; } pte_t; +typedef struct { pmdval_t pmd; } pmd_t; +typedef struct { pmdval_t pgd[2]; } pgd_t; +typedef struct { pteval_t pgprot; } pgprot_t; + +#define pte_val(x) ((x).pte) +#define pmd_val(x) ((x).pmd) +#define pgd_val(x) ((x).pgd[0]) +#define pgprot_val(x) ((x).pgprot) + +#define __pte(x) ((pte_t) { (x) } ) +#define __pmd(x) ((pmd_t) { (x) } ) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#else +/* + * .. while these make it easier on the compiler + */ +typedef pteval_t pte_t; +typedef pmdval_t pmd_t; +typedef pmdval_t pgd_t[2]; +typedef pteval_t pgprot_t; + +#define pte_val(x) (x) +#define pmd_val(x) (x) +#define pgd_val(x) ((x)[0]) +#define pgprot_val(x) (x) + +#define __pte(x) (x) +#define __pmd(x) (x) +#define __pgprot(x) (x) + +#endif /* STRICT_MM_TYPECHECKS */ + +#endif /* _ASM_PGTABLE_2LEVEL_TYPES_H */ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h new file mode 100644 index 000000000000..470457e1cfc5 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level.h @@ -0,0 +1,143 @@ +/* + * arch/arm/include/asm/pgtable-2level.h + * + * Copyright (C) 1995-2002 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _ASM_PGTABLE_2LEVEL_H +#define _ASM_PGTABLE_2LEVEL_H + +/* + * Hardware-wise, we have a two level page table structure, where the first + * level has 4096 entries, and the second level has 256 entries. Each entry + * is one 32-bit word. Most of the bits in the second level entry are used + * by hardware, and there aren't any "accessed" and "dirty" bits. + * + * Linux on the other hand has a three level page table structure, which can + * be wrapped to fit a two level page table structure easily - using the PGD + * and PTE only. However, Linux also expects one "PTE" table per page, and + * at least a "dirty" bit. + * + * Therefore, we tweak the implementation slightly - we tell Linux that we + * have 2048 entries in the first level, each of which is 8 bytes (iow, two + * hardware pointers to the second level.) The second level contains two + * hardware PTE tables arranged contiguously, preceded by Linux versions + * which contain the state information Linux needs. We, therefore, end up + * with 512 entries in the "PTE" level. + * + * This leads to the page tables having the following layout: + * + * pgd pte + * | | + * +--------+ + * | | +------------+ +0 + * +- - - - + | Linux pt 0 | + * | | +------------+ +1024 + * +--------+ +0 | Linux pt 1 | + * | |-----> +------------+ +2048 + * +- - - - + +4 | h/w pt 0 | + * | |-----> +------------+ +3072 + * +--------+ +8 | h/w pt 1 | + * | | +------------+ +4096 + * + * See L_PTE_xxx below for definitions of bits in the "Linux pt", and + * PTE_xxx for definitions of bits appearing in the "h/w pt". + * + * PMD_xxx definitions refer to bits in the first level page table. + * + * The "dirty" bit is emulated by only granting hardware write permission + * iff the page is marked "writable" and "dirty" in the Linux PTE. This + * means that a write to a clean page will cause a permission fault, and + * the Linux MM layer will mark the page dirty via handle_pte_fault(). + * For the hardware to notice the permission change, the TLB entry must + * be flushed, and ptep_set_access_flags() does that for us. + * + * The "accessed" or "young" bit is emulated by a similar method; we only + * allow accesses to the page if the "young" bit is set. Accesses to the + * page will cause a fault, and handle_pte_fault() will set the young bit + * for us as long as the page is marked present in the corresponding Linux + * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is + * up to date. + * + * However, when the "young" bit is cleared, we deny access to the page + * by clearing the hardware PTE. Currently Linux does not flush the TLB + * for us in this case, which means the TLB will retain the transation + * until either the TLB entry is evicted under pressure, or a context + * switch which changes the user space mapping occurs. + */ +#define PTRS_PER_PTE 512 +#define PTRS_PER_PMD 1 +#define PTRS_PER_PGD 2048 + +#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) +#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) +#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) + +/* + * PMD_SHIFT determines the size of the area a second-level page table can map + * PGDIR_SHIFT determines what a third-level page table entry can map + */ +#define PMD_SHIFT 21 +#define PGDIR_SHIFT 21 + +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* + * section address mask and size definitions. + */ +#define SECTION_SHIFT 20 +#define SECTION_SIZE (1UL << SECTION_SHIFT) +#define SECTION_MASK (~(SECTION_SIZE-1)) + +/* + * ARMv6 supersection address mask and size definitions. + */ +#define SUPERSECTION_SHIFT 24 +#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT) +#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1)) + +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) + +/* + * "Linux" PTE definitions. + * + * We keep two sets of PTEs - the hardware and the linux version. + * This allows greater flexibility in the way we map the Linux bits + * onto the hardware tables, and allows us to have YOUNG and DIRTY + * bits. + * + * The PTE table pointer refers to the hardware entries; the "Linux" + * entries are stored 1024 bytes below. + */ +#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) +#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) +#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ +#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) +#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) +#define L_PTE_USER (_AT(pteval_t, 1) << 8) +#define L_PTE_XN (_AT(pteval_t, 1) << 9) +#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */ + +/* + * These are the memory types, defined to be compatible with + * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB + */ +#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ +#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ +#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ +#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ +#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ +#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ +#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ +#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) + +#endif /* _ASM_PGTABLE_2LEVEL_H */ diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h index fd1521d5cb9d..183111164ce9 100644 --- a/arch/arm/include/asm/pgtable-hwdef.h +++ b/arch/arm/include/asm/pgtable-hwdef.h @@ -10,81 +10,6 @@ #ifndef _ASMARM_PGTABLE_HWDEF_H #define _ASMARM_PGTABLE_HWDEF_H -/* - * Hardware page table definitions. - * - * + Level 1 descriptor (PMD) - * - common - */ -#define PMD_TYPE_MASK (3 << 0) -#define PMD_TYPE_FAULT (0 << 0) -#define PMD_TYPE_TABLE (1 << 0) -#define PMD_TYPE_SECT (2 << 0) -#define PMD_BIT4 (1 << 4) -#define PMD_DOMAIN(x) ((x) << 5) -#define PMD_PROTECTION (1 << 9) /* v5 */ -/* - * - section - */ -#define PMD_SECT_BUFFERABLE (1 << 2) -#define PMD_SECT_CACHEABLE (1 << 3) -#define PMD_SECT_XN (1 << 4) /* v6 */ -#define PMD_SECT_AP_WRITE (1 << 10) -#define PMD_SECT_AP_READ (1 << 11) -#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */ -#define PMD_SECT_APX (1 << 15) /* v6 */ -#define PMD_SECT_S (1 << 16) /* v6 */ -#define PMD_SECT_nG (1 << 17) /* v6 */ -#define PMD_SECT_SUPER (1 << 18) /* v6 */ - -#define PMD_SECT_UNCACHED (0) -#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) -#define PMD_SECT_WT (PMD_SECT_CACHEABLE) -#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) -#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) -#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) -#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) - -/* - * - coarse table (not used) - */ - -/* - * + Level 2 descriptor (PTE) - * - common - */ -#define PTE_TYPE_MASK (3 << 0) -#define PTE_TYPE_FAULT (0 << 0) -#define PTE_TYPE_LARGE (1 << 0) -#define PTE_TYPE_SMALL (2 << 0) -#define PTE_TYPE_EXT (3 << 0) /* v5 */ -#define PTE_BUFFERABLE (1 << 2) -#define PTE_CACHEABLE (1 << 3) - -/* - * - extended small page/tiny page - */ -#define PTE_EXT_XN (1 << 0) /* v6 */ -#define PTE_EXT_AP_MASK (3 << 4) -#define PTE_EXT_AP0 (1 << 4) -#define PTE_EXT_AP1 (2 << 4) -#define PTE_EXT_AP_UNO_SRO (0 << 4) -#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) -#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) -#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) -#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */ -#define PTE_EXT_APX (1 << 9) /* v6 */ -#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */ -#define PTE_EXT_SHARED (1 << 10) /* v6 */ -#define PTE_EXT_NG (1 << 11) /* v6 */ - -/* - * - small page - */ -#define PTE_SMALL_AP_MASK (0xff << 4) -#define PTE_SMALL_AP_UNO_SRO (0x00 << 4) -#define PTE_SMALL_AP_UNO_SRW (0x55 << 4) -#define PTE_SMALL_AP_URO_SRW (0xaa << 4) -#define PTE_SMALL_AP_URW_SRW (0xff << 4) +#include <asm/pgtable-2level-hwdef.h> #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 5750704e0271..8ade1840c6f2 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -24,6 +24,8 @@ #include <mach/vmalloc.h> #include <asm/pgtable-hwdef.h> +#include <asm/pgtable-2level.h> + /* * Just any arbitrary offset to the start of the vmalloc VM area: the * current 8MB value just means that there will be a 8MB "hole" after the @@ -41,79 +43,6 @@ #define VMALLOC_START (((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) #endif -/* - * Hardware-wise, we have a two level page table structure, where the first - * level has 4096 entries, and the second level has 256 entries. Each entry - * is one 32-bit word. Most of the bits in the second level entry are used - * by hardware, and there aren't any "accessed" and "dirty" bits. - * - * Linux on the other hand has a three level page table structure, which can - * be wrapped to fit a two level page table structure easily - using the PGD - * and PTE only. However, Linux also expects one "PTE" table per page, and - * at least a "dirty" bit. - * - * Therefore, we tweak the implementation slightly - we tell Linux that we - * have 2048 entries in the first level, each of which is 8 bytes (iow, two - * hardware pointers to the second level.) The second level contains two - * hardware PTE tables arranged contiguously, preceded by Linux versions - * which contain the state information Linux needs. We, therefore, end up - * with 512 entries in the "PTE" level. - * - * This leads to the page tables having the following layout: - * - * pgd pte - * | | - * +--------+ - * | | +------------+ +0 - * +- - - - + | Linux pt 0 | - * | | +------------+ +1024 - * +--------+ +0 | Linux pt 1 | - * | |-----> +------------+ +2048 - * +- - - - + +4 | h/w pt 0 | - * | |-----> +------------+ +3072 - * +--------+ +8 | h/w pt 1 | - * | | +------------+ +4096 - * - * See L_PTE_xxx below for definitions of bits in the "Linux pt", and - * PTE_xxx for definitions of bits appearing in the "h/w pt". - * - * PMD_xxx definitions refer to bits in the first level page table. - * - * The "dirty" bit is emulated by only granting hardware write permission - * iff the page is marked "writable" and "dirty" in the Linux PTE. This - * means that a write to a clean page will cause a permission fault, and - * the Linux MM layer will mark the page dirty via handle_pte_fault(). - * For the hardware to notice the permission change, the TLB entry must - * be flushed, and ptep_set_access_flags() does that for us. - * - * The "accessed" or "young" bit is emulated by a similar method; we only - * allow accesses to the page if the "young" bit is set. Accesses to the - * page will cause a fault, and handle_pte_fault() will set the young bit - * for us as long as the page is marked present in the corresponding Linux - * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is - * up to date. - * - * However, when the "young" bit is cleared, we deny access to the page - * by clearing the hardware PTE. Currently Linux does not flush the TLB - * for us in this case, which means the TLB will retain the transation - * until either the TLB entry is evicted under pressure, or a context - * switch which changes the user space mapping occurs. - */ -#define PTRS_PER_PTE 512 -#define PTRS_PER_PMD 1 -#define PTRS_PER_PGD 2048 - -#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) -#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) -#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) - -/* - * PMD_SHIFT determines the size of the area a second-level page table can map - * PGDIR_SHIFT determines what a third-level page table entry can map - */ -#define PMD_SHIFT 21 -#define PGDIR_SHIFT 21 - #define LIBRARY_TEXT_START 0x0c000000 #ifndef __ASSEMBLY__ @@ -124,12 +53,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); #define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte) #define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd) #define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd) -#endif /* !__ASSEMBLY__ */ - -#define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE-1)) -#define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) /* * This is the lowest virtual address we can permit any user space @@ -138,60 +61,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); */ #define FIRST_USER_ADDRESS PAGE_SIZE -#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) - -/* - * section address mask and size definitions. - */ -#define SECTION_SHIFT 20 -#define SECTION_SIZE (1UL << SECTION_SHIFT) -#define SECTION_MASK (~(SECTION_SIZE-1)) - -/* - * ARMv6 supersection address mask and size definitions. - */ -#define SUPERSECTION_SHIFT 24 -#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT) -#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1)) - -/* - * "Linux" PTE definitions. - * - * We keep two sets of PTEs - the hardware and the linux version. - * This allows greater flexibility in the way we map the Linux bits - * onto the hardware tables, and allows us to have YOUNG and DIRTY - * bits. - * - * The PTE table pointer refers to the hardware entries; the "Linux" - * entries are stored 1024 bytes below. - */ -#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) -#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) -#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ -#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) -#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) -#define L_PTE_USER (_AT(pteval_t, 1) << 8) -#define L_PTE_XN (_AT(pteval_t, 1) << 9) -#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */ - -/* - * These are the memory types, defined to be compatible with - * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB - */ -#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ -#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ -#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ -#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ -#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ -#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ -#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ -#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) - -#ifndef __ASSEMBLY__ - /* * The pgprot_* and protection_map entries will be fixed up in runtime * to include the cachable and bufferable bits based on memory policy, @@ -327,10 +196,10 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; static inline pte_t *pmd_page_vaddr(pmd_t pmd) { - return __va(pmd_val(pmd) & PAGE_MASK); + return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK); } -#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd))) +#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) /* we don't need complex calculations here as the pmd is folded into the pgd */ #define pmd_addr_end(addr,end) (end) @@ -351,7 +220,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr)) #define pte_unmap(pte) __pte_unmap(pte) -#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) +#define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot)) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) diff --git a/arch/arm/include/asm/poll.h b/arch/arm/include/asm/poll.h deleted file mode 100644 index c98509d3149e..000000000000 --- a/arch/arm/include/asm/poll.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/poll.h> diff --git a/arch/arm/include/asm/resource.h b/arch/arm/include/asm/resource.h deleted file mode 100644 index 734b581b5b6a..000000000000 --- a/arch/arm/include/asm/resource.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ARM_RESOURCE_H -#define _ARM_RESOURCE_H - -#include <asm-generic/resource.h> - -#endif diff --git a/arch/arm/include/asm/sections.h b/arch/arm/include/asm/sections.h deleted file mode 100644 index 2b8c5160388f..000000000000 --- a/arch/arm/include/asm/sections.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/sections.h> diff --git a/arch/arm/include/asm/siginfo.h b/arch/arm/include/asm/siginfo.h deleted file mode 100644 index 5e21852e6039..000000000000 --- a/arch/arm/include/asm/siginfo.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASMARM_SIGINFO_H -#define _ASMARM_SIGINFO_H - -#include <asm-generic/siginfo.h> - -#endif diff --git a/arch/arm/include/asm/sizes.h b/arch/arm/include/asm/sizes.h deleted file mode 100644 index 154b89b81d3e..000000000000 --- a/arch/arm/include/asm/sizes.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -/* Size definitions - * Copyright (C) ARM Limited 1998. All rights reserved. - */ -#include <asm-generic/sizes.h> - -#define SZ_48M (SZ_32M + SZ_16M) diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index e42d96a45d3e..0a17b62538c2 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -33,6 +33,11 @@ extern void show_ipi_list(struct seq_file *, int); asmlinkage void do_IPI(int ipinr, struct pt_regs *regs); /* + * Called from C code, this handles an IPI. + */ +void handle_IPI(int ipinr, struct pt_regs *regs); + +/* * Setup the set of possible CPUs (via set_cpu_possible) */ extern void smp_init_cpus(void); @@ -66,6 +71,12 @@ extern void platform_secondary_init(unsigned int cpu); extern void platform_smp_prepare_cpus(unsigned int); /* + * Logical CPU mapping. + */ +extern int __cpu_logical_map[NR_CPUS]; +#define cpu_logical_map(cpu) __cpu_logical_map[cpu] + +/* * Initial data for bringing up a secondary CPU. */ struct secondary_data { diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 832888d0c20c..984014b92647 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -57,18 +57,12 @@ #ifndef __ASSEMBLY__ +#include <linux/compiler.h> #include <linux/linkage.h> #include <linux/irqflags.h> #include <asm/outercache.h> -#define __exception __attribute__((section(".exception.text"))) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#define __exception_irq_entry __irq_entry -#else -#define __exception_irq_entry __exception -#endif - struct thread_info; struct task_struct; @@ -97,14 +91,13 @@ void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, #define xchg(ptr,x) \ ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) -extern asmlinkage void __backtrace(void); extern asmlinkage void c_backtrace(unsigned long fp, int pmode); struct mm_struct; extern void show_pte(struct mm_struct *mm, unsigned long addr); extern void __show_regs(struct pt_regs *); -extern int cpu_architecture(void); +extern int __pure cpu_architecture(void); extern void cpu_init(void); void arm_machine_restart(char mode, const char *cmd); diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 8077145698ff..02b2f8203982 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -471,7 +471,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) * these operations. This is typically used when we are removing * PMD entries. */ -static inline void flush_pmd_entry(pmd_t *pmd) +static inline void flush_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; @@ -487,7 +487,7 @@ static inline void flush_pmd_entry(pmd_t *pmd) dsb(); } -static inline void clean_pmd_entry(pmd_t *pmd) +static inline void clean_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index accbd7cad9b5..a7e457ed27c3 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -1,6 +1,39 @@ #ifndef _ASM_ARM_TOPOLOGY_H #define _ASM_ARM_TOPOLOGY_H +#ifdef CONFIG_ARM_CPU_TOPOLOGY + +#include <linux/cpumask.h> + +struct cputopo_arm { + int thread_id; + int core_id; + int socket_id; + cpumask_t thread_sibling; + cpumask_t core_sibling; +}; + +extern struct cputopo_arm cpu_topology[NR_CPUS]; + +#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) +#define topology_core_id(cpu) (cpu_topology[cpu].core_id) +#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) +#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) + +#define mc_capable() (cpu_topology[0].socket_id != -1) +#define smt_capable() (cpu_topology[0].thread_id != -1) + +void init_cpu_topology(void); +void store_cpu_topology(unsigned int cpuid); +const struct cpumask *cpu_coregroup_mask(unsigned int cpu); + +#else + +static inline void init_cpu_topology(void) { } +static inline void store_cpu_topology(unsigned int cpuid) { } + +#endif + #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index f7887dc53c1f..68036eece340 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES) += armksyms.o module.o obj-$(CONFIG_ARTHUR) += arthur.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o -obj-$(CONFIG_PM_SLEEP) += sleep.o +obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o obj-$(CONFIG_HAVE_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_SMP) += smp.o smp_tlb.o obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o @@ -66,6 +66,7 @@ obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_CPU_HAS_PMU) += pmu.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt +obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o ifneq ($(CONFIG_ARCH_EBSA110),y) obj-y += io.o diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index aeef960ff795..8e3c6f11b0a1 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -49,9 +49,6 @@ extern void __aeabi_ulcmp(void); extern void fpundefinstr(void); - -EXPORT_SYMBOL(__backtrace); - /* platform dependent support */ EXPORT_SYMBOL(__udelay); EXPORT_SYMBOL(__const_udelay); diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 16baba2e4369..1429d8989fb9 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -20,6 +20,7 @@ #include <asm/thread_info.h> #include <asm/memory.h> #include <asm/procinfo.h> +#include <asm/hardware/cache-l2x0.h> #include <linux/kbuild.h> /* @@ -92,6 +93,17 @@ int main(void) DEFINE(S_OLD_R0, offsetof(struct pt_regs, ARM_ORIG_r0)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); +#ifdef CONFIG_CACHE_L2X0 + DEFINE(L2X0_R_PHY_BASE, offsetof(struct l2x0_regs, phy_base)); + DEFINE(L2X0_R_AUX_CTRL, offsetof(struct l2x0_regs, aux_ctrl)); + DEFINE(L2X0_R_TAG_LATENCY, offsetof(struct l2x0_regs, tag_latency)); + DEFINE(L2X0_R_DATA_LATENCY, offsetof(struct l2x0_regs, data_latency)); + DEFINE(L2X0_R_FILTER_START, offsetof(struct l2x0_regs, filter_start)); + DEFINE(L2X0_R_FILTER_END, offsetof(struct l2x0_regs, filter_end)); + DEFINE(L2X0_R_PREFETCH_CTRL, offsetof(struct l2x0_regs, prefetch_ctrl)); + DEFINE(L2X0_R_PWR_CTRL, offsetof(struct l2x0_regs, pwr_ctrl)); + BLANK(); +#endif #ifdef CONFIG_CPU_HAS_ASID DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id)); BLANK(); diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index d6df359408f0..c0d9203fc75e 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -412,6 +412,9 @@ void pcibios_fixup_bus(struct pci_bus *bus) printk(KERN_INFO "PCI: bus%d: Fast back to back transfers %sabled\n", bus->number, (features & PCI_COMMAND_FAST_BACK) ? "en" : "dis"); } +#ifdef CONFIG_HOTPLUG +EXPORT_SYMBOL(pcibios_fixup_bus); +#endif /* * Convert from Linux-centric to bus-centric addresses for bridge devices. @@ -431,6 +434,7 @@ pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, region->start = res->start - offset; region->end = res->end - offset; } +EXPORT_SYMBOL(pcibios_resource_to_bus); void __devinit pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, @@ -447,12 +451,7 @@ pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, res->start = region->start + offset; res->end = region->end + offset; } - -#ifdef CONFIG_HOTPLUG -EXPORT_SYMBOL(pcibios_fixup_bus); -EXPORT_SYMBOL(pcibios_resource_to_bus); EXPORT_SYMBOL(pcibios_bus_to_resource); -#endif /* * Swizzle the device pin each time we cross a bridge. diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S index bcd66e00bdbe..0f852d082fcf 100644 --- a/arch/arm/kernel/debug.S +++ b/arch/arm/kernel/debug.S @@ -151,6 +151,8 @@ printhex: adr r2, hexbuf b printascii ENDPROC(printhex2) +hexbuf: .space 16 + .ltorg ENTRY(printascii) @@ -175,5 +177,3 @@ ENTRY(printch) mov r0, #0 b 1b ENDPROC(printch) - -hexbuf: .space 16 diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c index d16500110ee9..4dd0edab6a65 100644 --- a/arch/arm/kernel/ecard.c +++ b/arch/arm/kernel/ecard.c @@ -237,7 +237,7 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (IO_SIZE / PGDIR_SIZE)); - src_pgd = pgd_offset(mm, EASI_BASE); + src_pgd = pgd_offset(mm, (unsigned long)EASI_BASE); dst_pgd = pgd_offset(mm, EASI_START); memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); @@ -674,44 +674,37 @@ static int __init ecard_probeirqhw(void) #define ecard_probeirqhw() (0) #endif -#ifndef IO_EC_MEMC8_BASE -#define IO_EC_MEMC8_BASE 0 -#endif - -static unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed) +static void __iomem *__ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed) { - unsigned long address = 0; + void __iomem *address = NULL; int slot = ec->slot_no; if (ec->slot_no == 8) - return IO_EC_MEMC8_BASE; + return ECARD_MEMC8_BASE; ectcr &= ~(1 << slot); switch (type) { case ECARD_MEMC: if (slot < 4) - address = IO_EC_MEMC_BASE + (slot << 12); + address = ECARD_MEMC_BASE + (slot << 14); break; case ECARD_IOC: if (slot < 4) - address = IO_EC_IOC_BASE + (slot << 12); -#ifdef IO_EC_IOC4_BASE + address = ECARD_IOC_BASE + (slot << 14); else - address = IO_EC_IOC4_BASE + ((slot - 4) << 12); -#endif + address = ECARD_IOC4_BASE + ((slot - 4) << 14); if (address) - address += speed << 17; + address += speed << 19; break; -#ifdef IO_EC_EASI_BASE case ECARD_EASI: - address = IO_EC_EASI_BASE + (slot << 22); + address = ECARD_EASI_BASE + (slot << 24); if (speed == ECARD_FAST) ectcr |= 1 << slot; break; -#endif + default: break; } @@ -990,6 +983,7 @@ ecard_probe(int slot, card_type_t type) ecard_t **ecp; ecard_t *ec; struct ex_ecid cid; + void __iomem *addr; int i, rc; ec = ecard_alloc_card(type, slot); @@ -999,7 +993,7 @@ ecard_probe(int slot, card_type_t type) } rc = -ENODEV; - if ((ec->podaddr = __ecard_address(ec, type, ECARD_SYNC)) == 0) + if ((addr = __ecard_address(ec, type, ECARD_SYNC)) == NULL) goto nodev; cid.r_zero = 1; @@ -1019,7 +1013,7 @@ ecard_probe(int slot, card_type_t type) ec->cid.fiqmask = cid.r_fiqmask; ec->cid.fiqoff = ecard_gets24(cid.r_fiqoff); ec->fiqaddr = - ec->irqaddr = (void __iomem *)ioaddr(ec->podaddr); + ec->irqaddr = addr; if (ec->cid.is) { ec->irqmask = ec->cid.irqmask; @@ -1048,10 +1042,8 @@ ecard_probe(int slot, card_type_t type) set_irq_flags(ec->irq, IRQF_VALID); } -#ifdef IO_EC_MEMC8_BASE if (slot == 8) ec->irq = 11; -#endif #ifdef CONFIG_ARCH_RPC /* On RiscPC, only first two slots have DMA capability */ if (slot < 2) @@ -1097,9 +1089,7 @@ static int __init ecard_init(void) ecard_probe(slot, ECARD_IOC); } -#ifdef IO_EC_MEMC8_BASE ecard_probe(8, ECARD_IOC); -#endif irqhw = ecard_probeirqhw(); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index a87cbf889ff4..9ad50c4208ae 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -24,6 +24,7 @@ #include <asm/unwind.h> #include <asm/unistd.h> #include <asm/tls.h> +#include <asm/system.h> #include "entry-header.S" #include <asm/entry-macro-multi.S> @@ -262,8 +263,7 @@ __und_svc: ldr r0, [r4, #-4] #else ldrh r0, [r4, #-2] @ Thumb instruction at LR - 2 - and r9, r0, #0xf800 - cmp r9, #0xe800 @ 32-bit instruction if xx >= 0 + cmp r0, #0xe800 @ 32-bit instruction if xx >= 0 ldrhhs r9, [r4] @ bottom 16 bits orrhs r0, r9, r0, lsl #16 #endif @@ -440,18 +440,46 @@ __und_usr: #endif beq call_fpe @ Thumb instruction -#if __LINUX_ARM_ARCH__ >= 7 +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 +/* + * Thumb-2 instruction handling. Note that because pre-v6 and >= v6 platforms + * can never be supported in a single kernel, this code is not applicable at + * all when __LINUX_ARM_ARCH__ < 6. This allows simplifying assumptions to be + * made about .arch directives. + */ +#if __LINUX_ARM_ARCH__ < 7 +/* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */ +#define NEED_CPU_ARCHITECTURE + ldr r5, .LCcpu_architecture + ldr r5, [r5] + cmp r5, #CPU_ARCH_ARMv7 + blo __und_usr_unknown +/* + * The following code won't get run unless the running CPU really is v7, so + * coding round the lack of ldrht on older arches is pointless. Temporarily + * override the assembler target arch with the minimum required instead: + */ + .arch armv6t2 +#endif 2: ARM( ldrht r5, [r4], #2 ) THUMB( ldrht r5, [r4] ) THUMB( add r4, r4, #2 ) - and r0, r5, #0xf800 @ mask bits 111x x... .... .... - cmp r0, #0xe800 @ 32bit instruction if xx != 0 + cmp r5, #0xe800 @ 32bit instruction if xx != 0 blo __und_usr_unknown 3: ldrht r0, [r4] add r2, r2, #2 @ r2 is PC + 2, make it PC + 4 orr r0, r0, r5, lsl #16 + +#if __LINUX_ARM_ARCH__ < 7 +/* If the target arch was overridden, change it back: */ +#ifdef CONFIG_CPU_32v6K + .arch armv6k #else + .arch armv6 +#endif +#endif /* __LINUX_ARM_ARCH__ < 7 */ +#else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */ b __und_usr_unknown #endif UNWIND(.fnend ) @@ -578,6 +606,12 @@ call_fpe: movw_pc lr @ CP#14 (Debug) movw_pc lr @ CP#15 (Control) +#ifdef NEED_CPU_ARCHITECTURE + .align 2 +.LCcpu_architecture: + .word __cpu_architecture +#endif + #ifdef CONFIG_NEON .align 6 diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 742b6108a001..239703dbdf4f 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -21,6 +21,7 @@ #include <asm/memory.h> #include <asm/thread_info.h> #include <asm/system.h> +#include <asm/pgtable.h> #ifdef CONFIG_DEBUG_LL #include <mach/debug-macro.S> @@ -38,11 +39,14 @@ #error KERNEL_RAM_VADDR must start at 0xXXXX8000 #endif +#define PG_DIR_SIZE 0x4000 +#define PMD_ORDER 2 + .globl swapper_pg_dir - .equ swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000 + .equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE .macro pgtbl, rd, phys - add \rd, \phys, #TEXT_OFFSET - 0x4000 + add \rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE .endm #ifdef CONFIG_XIP_KERNEL @@ -148,11 +152,11 @@ __create_page_tables: pgtbl r4, r8 @ page table address /* - * Clear the 16K level 1 swapper page table + * Clear the swapper page table */ mov r0, r4 mov r3, #0 - add r6, r0, #0x4000 + add r6, r0, #PG_DIR_SIZE 1: str r3, [r0], #4 str r3, [r0], #4 str r3, [r0], #4 @@ -171,30 +175,30 @@ __create_page_tables: sub r0, r0, r3 @ virt->phys offset add r5, r5, r0 @ phys __enable_mmu add r6, r6, r0 @ phys __enable_mmu_end - mov r5, r5, lsr #20 - mov r6, r6, lsr #20 + mov r5, r5, lsr #SECTION_SHIFT + mov r6, r6, lsr #SECTION_SHIFT -1: orr r3, r7, r5, lsl #20 @ flags + kernel base - str r3, [r4, r5, lsl #2] @ identity mapping - teq r5, r6 - addne r5, r5, #1 @ next section - bne 1b +1: orr r3, r7, r5, lsl #SECTION_SHIFT @ flags + kernel base + str r3, [r4, r5, lsl #PMD_ORDER] @ identity mapping + cmp r5, r6 + addlo r5, r5, #1 @ next section + blo 1b /* * Now setup the pagetables for our kernel direct * mapped region. */ mov r3, pc - mov r3, r3, lsr #20 - orr r3, r7, r3, lsl #20 - add r0, r4, #(KERNEL_START & 0xff000000) >> 18 - str r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]! + mov r3, r3, lsr #SECTION_SHIFT + orr r3, r7, r3, lsl #SECTION_SHIFT + add r0, r4, #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) + str r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]! ldr r6, =(KERNEL_END - 1) - add r0, r0, #4 - add r6, r4, r6, lsr #18 + add r0, r0, #1 << PMD_ORDER + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) 1: cmp r0, r6 - add r3, r3, #1 << 20 - strls r3, [r0], #4 + add r3, r3, #1 << SECTION_SHIFT + strls r3, [r0], #1 << PMD_ORDER bls 1b #ifdef CONFIG_XIP_KERNEL @@ -203,11 +207,11 @@ __create_page_tables: */ add r3, r8, #TEXT_OFFSET orr r3, r3, r7 - add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> 18 - str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]! + add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) + str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]! ldr r6, =(_end - 1) add r0, r0, #4 - add r6, r4, r6, lsr #18 + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) 1: cmp r0, r6 add r3, r3, #1 << 20 strls r3, [r0], #4 @@ -218,12 +222,12 @@ __create_page_tables: * Then map boot params address in r2 or * the first 1MB of ram if boot params address is not specified. */ - mov r0, r2, lsr #20 - movs r0, r0, lsl #20 + mov r0, r2, lsr #SECTION_SHIFT + movs r0, r0, lsl #SECTION_SHIFT moveq r0, r8 sub r3, r0, r8 add r3, r3, #PAGE_OFFSET - add r3, r4, r3, lsr #18 + add r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER) orr r6, r7, r0 str r6, [r3] @@ -236,21 +240,21 @@ __create_page_tables: */ addruart r7, r3 - mov r3, r3, lsr #20 - mov r3, r3, lsl #2 + mov r3, r3, lsr #SECTION_SHIFT + mov r3, r3, lsl #PMD_ORDER add r0, r4, r3 rsb r3, r3, #0x4000 @ PTRS_PER_PGD*sizeof(long) cmp r3, #0x0800 @ limit to 512MB movhi r3, #0x0800 add r6, r0, r3 - mov r3, r7, lsr #20 + mov r3, r7, lsr #SECTION_SHIFT ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags - orr r3, r7, r3, lsl #20 + orr r3, r7, r3, lsl #SECTION_SHIFT 1: str r3, [r0], #4 - add r3, r3, #1 << 20 - teq r0, r6 - bne 1b + add r3, r3, #1 << SECTION_SHIFT + cmp r0, r6 + blo 1b #else /* CONFIG_DEBUG_ICEDCC */ /* we don't need any serial debugging mappings for ICEDCC */ @@ -262,7 +266,7 @@ __create_page_tables: * If we're using the NetWinder or CATS, we also need to map * in the 16550-type serial port for the debug messages */ - add r0, r4, #0xff000000 >> 18 + add r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER) orr r3, r7, #0x7c000000 str r3, [r0] #endif @@ -272,10 +276,10 @@ __create_page_tables: * Similar reasons here - for debug. This is * only for Acorn RiscPC architectures. */ - add r0, r4, #0x02000000 >> 18 + add r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER) orr r3, r7, #0x02000000 str r3, [r0] - add r0, r4, #0xd8000000 >> 18 + add r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER) str r3, [r0] #endif #endif @@ -488,13 +492,8 @@ __fixup_pv_table: add r5, r5, r3 @ adjust table end address add r7, r7, r3 @ adjust __pv_phys_offset address str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset -#ifndef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT mov r6, r3, lsr #24 @ constant for add/sub instructions teq r3, r6, lsl #24 @ must be 16MiB aligned -#else - mov r6, r3, lsr #16 @ constant for add/sub instructions - teq r3, r6, lsl #16 @ must be 64kiB aligned -#endif THUMB( it ne @ cross section branch ) bne __error str r6, [r7, #4] @ save to __pv_offset @@ -510,20 +509,8 @@ ENDPROC(__fixup_pv_table) .text __fixup_a_pv_table: #ifdef CONFIG_THUMB2_KERNEL -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - lsls r0, r6, #24 - lsr r6, #8 - beq 1f - clz r7, r0 - lsr r0, #24 - lsl r0, r7 - bic r0, 0x0080 - lsrs r7, #1 - orrcs r0, #0x0080 - orr r0, r0, r7, lsl #12 -#endif -1: lsls r6, #24 - beq 4f + lsls r6, #24 + beq 2f clz r7, r6 lsr r6, #24 lsl r6, r7 @@ -532,43 +519,25 @@ __fixup_a_pv_table: orrcs r6, #0x0080 orr r6, r6, r7, lsl #12 orr r6, #0x4000 - b 4f -2: @ at this point the C flag is always clear - add r7, r3 -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - ldrh ip, [r7] - tst ip, 0x0400 @ the i bit tells us LS or MS byte - beq 3f - cmp r0, #0 @ set C flag, and ... - biceq ip, 0x0400 @ immediate zero value has a special encoding - streqh ip, [r7] @ that requires the i bit cleared -#endif -3: ldrh ip, [r7, #2] + b 2f +1: add r7, r3 + ldrh ip, [r7, #2] and ip, 0x8f00 - orrcc ip, r6 @ mask in offset bits 31-24 - orrcs ip, r0 @ mask in offset bits 23-16 + orr ip, r6 @ mask in offset bits 31-24 strh ip, [r7, #2] -4: cmp r4, r5 +2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot - bcc 2b + bcc 1b bx lr #else -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - and r0, r6, #255 @ offset bits 23-16 - mov r6, r6, lsr #8 @ offset bits 31-24 -#else - mov r0, #0 @ just in case... -#endif - b 3f -2: ldr ip, [r7, r3] + b 2f +1: ldr ip, [r7, r3] bic ip, ip, #0x000000ff - tst ip, #0x400 @ rotate shift tells us LS or MS byte - orrne ip, ip, r6 @ mask in offset bits 31-24 - orreq ip, ip, r0 @ mask in offset bits 23-16 + orr ip, ip, r6 @ mask in offset bits 31-24 str ip, [r7, r3] -3: cmp r4, r5 +2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot - bcc 2b + bcc 1b mov pc, lr #endif ENDPROC(__fixup_a_pv_table) diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index de3dcab8610b..53919b230e8b 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -35,8 +35,8 @@ #include <linux/list.h> #include <linux/kallsyms.h> #include <linux/proc_fs.h> -#include <linux/ftrace.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/mach/arch.h> #include <asm/mach/irq.h> diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index e59bbd496c39..c1b4463dcc83 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -32,6 +32,24 @@ static atomic_t waiting_for_crash_ipi; int machine_kexec_prepare(struct kimage *image) { + unsigned long page_list; + void *reboot_code_buffer; + page_list = image->head & PAGE_MASK; + + reboot_code_buffer = page_address(image->control_code_page); + + /* Prepare parameters for reboot_code_buffer*/ + kexec_start_address = image->start; + kexec_indirection_page = page_list; + kexec_mach_type = machine_arch_type; + kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET; + + /* copy our kernel relocation code to the control code page */ + memcpy(reboot_code_buffer, + relocate_new_kernel, relocate_new_kernel_size); + + flush_icache_range((unsigned long) reboot_code_buffer, + (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); return 0; } @@ -82,31 +100,14 @@ void (*kexec_reinit)(void); void machine_kexec(struct kimage *image) { - unsigned long page_list; unsigned long reboot_code_buffer_phys; void *reboot_code_buffer; - - page_list = image->head & PAGE_MASK; - /* we need both effective and real address here */ reboot_code_buffer_phys = page_to_pfn(image->control_code_page) << PAGE_SHIFT; reboot_code_buffer = page_address(image->control_code_page); - /* Prepare parameters for reboot_code_buffer*/ - kexec_start_address = image->start; - kexec_indirection_page = page_list; - kexec_mach_type = machine_arch_type; - kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET; - - /* copy our kernel relocation code to the control code page */ - memcpy(reboot_code_buffer, - relocate_new_kernel, relocate_new_kernel_size); - - - flush_icache_range((unsigned long) reboot_code_buffer, - (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); printk(KERN_INFO "Bye!\n"); if (kexec_reinit) diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index cc2020c2c709..1e9be5d25e56 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -33,7 +33,7 @@ * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off. */ #undef MODULES_VADDR -#define MODULES_VADDR (((unsigned long)_etext + ~PGDIR_MASK) & PGDIR_MASK) +#define MODULES_VADDR (((unsigned long)_etext + ~PMD_MASK) & PMD_MASK) #endif #ifdef CONFIG_MMU diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 4c851834f68e..6be3e2e4d838 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -321,8 +321,8 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE, - [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_COHERENT_LINE_HIT, - [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_COHERENT_LINE_MISS, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_DCACHE_REFILL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 1a347f481e5e..fd0814076ff6 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -319,7 +319,7 @@ void show_regs(struct pt_regs * regs) printk("\n"); printk("Pid: %d, comm: %20s\n", task_pid_nr(current), current->comm); __show_regs(regs); - __backtrace(); + dump_stack(); } ATOMIC_NOTIFIER_HEAD(thread_notify_head); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index e514c76043b4..3fe93f75b55a 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -29,6 +29,8 @@ #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/memblock.h> +#include <linux/bug.h> +#include <linux/compiler.h> #include <asm/unified.h> #include <asm/cpu.h> @@ -42,6 +44,7 @@ #include <asm/cacheflush.h> #include <asm/cachetype.h> #include <asm/tlbflush.h> +#include <asm/system.h> #include <asm/prom.h> #include <asm/mach/arch.h> @@ -115,6 +118,13 @@ struct outer_cache_fns outer_cache __read_mostly; EXPORT_SYMBOL(outer_cache); #endif +/* + * Cached cpu_architecture() result for use by assembler code. + * C code should use the cpu_architecture() function instead of accessing this + * variable directly. + */ +int __cpu_architecture __read_mostly = CPU_ARCH_UNKNOWN; + struct stack { u32 irq[3]; u32 abt[3]; @@ -210,7 +220,7 @@ static const char *proc_arch[] = { "?(17)", }; -int cpu_architecture(void) +static int __get_cpu_architecture(void) { int cpu_arch; @@ -243,11 +253,22 @@ int cpu_architecture(void) return cpu_arch; } +int __pure cpu_architecture(void) +{ + BUG_ON(__cpu_architecture == CPU_ARCH_UNKNOWN); + + return __cpu_architecture; +} + static int cpu_has_aliasing_icache(unsigned int arch) { int aliasing_icache; unsigned int id_reg, num_sets, line_size; + /* PIPT caches never alias. */ + if (icache_is_pipt()) + return 0; + /* arch specifies the register format */ switch (arch) { case CPU_ARCH_ARMv7: @@ -282,8 +303,14 @@ static void __init cacheid_init(void) /* ARMv7 register format */ arch = CPU_ARCH_ARMv7; cacheid = CACHEID_VIPT_NONALIASING; - if ((cachetype & (3 << 14)) == 1 << 14) + switch (cachetype & (3 << 14)) { + case (1 << 14): cacheid |= CACHEID_ASID_TAGGED; + break; + case (3 << 14): + cacheid |= CACHEID_PIPT; + break; + } } else { arch = CPU_ARCH_ARMv6; if (cachetype & (1 << 23)) @@ -300,10 +327,11 @@ static void __init cacheid_init(void) printk("CPU: %s data cache, %s instruction cache\n", cache_is_vivt() ? "VIVT" : cache_is_vipt_aliasing() ? "VIPT aliasing" : - cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown", + cache_is_vipt_nonaliasing() ? "PIPT / VIPT nonaliasing" : "unknown", cache_is_vivt() ? "VIVT" : icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" : icache_is_vipt_aliasing() ? "VIPT aliasing" : + icache_is_pipt() ? "PIPT" : cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown"); } @@ -414,6 +442,7 @@ static void __init setup_processor(void) } cpu_name = list->cpu_name; + __cpu_architecture = __get_cpu_architecture(); #ifdef MULTI_CPU processor = *list->proc; @@ -861,7 +890,7 @@ static struct machine_desc * __init setup_machine_tags(unsigned int nr) } if (mdesc->fixup) - mdesc->fixup(mdesc, tags, &from, &meminfo); + mdesc->fixup(tags, &from, &meminfo); if (tags->hdr.tag == ATAG_CORE) { if (meminfo.nr_banks != 0) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index d88ff0230e82..854ce33715f4 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -16,7 +16,6 @@ #include <linux/cache.h> #include <linux/profile.h> #include <linux/errno.h> -#include <linux/ftrace.h> #include <linux/mm.h> #include <linux/err.h> #include <linux/cpu.h> @@ -31,6 +30,8 @@ #include <asm/cacheflush.h> #include <asm/cpu.h> #include <asm/cputype.h> +#include <asm/exception.h> +#include <asm/topology.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -39,6 +40,7 @@ #include <asm/tlbflush.h> #include <asm/ptrace.h> #include <asm/localtimer.h> +#include <asm/smp_plat.h> /* * as from 2.5, kernels no longer have an init_tasks structure @@ -259,6 +261,20 @@ void __ref cpu_die(void) } #endif /* CONFIG_HOTPLUG_CPU */ +int __cpu_logical_map[NR_CPUS]; + +void __init smp_setup_processor_id(void) +{ + int i; + u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0; + + cpu_logical_map(0) = cpu; + for (i = 1; i < NR_CPUS; ++i) + cpu_logical_map(i) = i == cpu ? 0 : i; + + printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu); +} + /* * Called by both boot and secondaries to move global data into * per-processor storage. @@ -268,6 +284,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid) struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid); cpu_info->loops_per_jiffy = loops_per_jiffy; + + store_cpu_topology(cpuid); } /* @@ -301,17 +319,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void) */ platform_secondary_init(cpu); - /* - * Enable local interrupts. - */ notify_cpu_starting(cpu); - local_irq_enable(); - local_fiq_enable(); - - /* - * Setup the percpu timer for this CPU. - */ - percpu_timer_setup(); calibrate_delay(); @@ -323,10 +331,23 @@ asmlinkage void __cpuinit secondary_start_kernel(void) * before we continue. */ set_cpu_online(cpu, true); + + /* + * Setup the percpu timer for this CPU. + */ + percpu_timer_setup(); + while (!cpu_active(cpu)) cpu_relax(); /* + * cpu_active bit is set, so it's safe to enalbe interrupts + * now. + */ + local_irq_enable(); + local_fiq_enable(); + + /* * OK, it's off to the idle thread for us */ cpu_idle(); @@ -358,6 +379,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned int ncores = num_possible_cpus(); + init_cpu_topology(); + smp_store_cpu_info(smp_processor_id()); /* @@ -460,6 +483,11 @@ static void ipi_timer(void) #ifdef CONFIG_LOCAL_TIMERS asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs) { + handle_local_timer(regs); +} + +void handle_local_timer(struct pt_regs *regs) +{ struct pt_regs *old_regs = set_irq_regs(regs); int cpu = smp_processor_id(); @@ -567,6 +595,11 @@ static void ipi_cpu_stop(unsigned int cpu) */ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) { + handle_IPI(ipinr, regs); +} + +void handle_IPI(int ipinr, struct pt_regs *regs) +{ unsigned int cpu = smp_processor_id(); struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 7fcddb75c877..8f5dd7963356 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -34,7 +34,7 @@ unsigned int __init scu_get_core_count(void __iomem *scu_base) /* * Enable the SCU */ -void __init scu_enable(void __iomem *scu_base) +void scu_enable(void __iomem *scu_base) { u32 scu_ctrl; diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index cb634c3e28e9..5a54b95d6bd2 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -39,13 +39,11 @@ */ static struct sys_timer *system_timer; -#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) +#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) || \ + defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) /* this needs a better home */ DEFINE_SPINLOCK(rtc_lock); - -#ifdef CONFIG_RTC_DRV_CMOS_MODULE EXPORT_SYMBOL(rtc_lock); -#endif #endif /* pc-style 'CMOS' RTC support */ /* change this if you have some constant time drift */ diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c new file mode 100644 index 000000000000..1040c00405d0 --- /dev/null +++ b/arch/arm/kernel/topology.c @@ -0,0 +1,148 @@ +/* + * arch/arm/kernel/topology.c + * + * Copyright (C) 2011 Linaro Limited. + * Written by: Vincent Guittot + * + * based on arch/sh/kernel/topology.c + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/sched.h> + +#include <asm/cputype.h> +#include <asm/topology.h> + +#define MPIDR_SMP_BITMASK (0x3 << 30) +#define MPIDR_SMP_VALUE (0x2 << 30) + +#define MPIDR_MT_BITMASK (0x1 << 24) + +/* + * These masks reflect the current use of the affinity levels. + * The affinity level can be up to 16 bits according to ARM ARM + */ + +#define MPIDR_LEVEL0_MASK 0x3 +#define MPIDR_LEVEL0_SHIFT 0 + +#define MPIDR_LEVEL1_MASK 0xF +#define MPIDR_LEVEL1_SHIFT 8 + +#define MPIDR_LEVEL2_MASK 0xFF +#define MPIDR_LEVEL2_SHIFT 16 + +struct cputopo_arm cpu_topology[NR_CPUS]; + +const struct cpumask *cpu_coregroup_mask(unsigned int cpu) +{ + return &cpu_topology[cpu].core_sibling; +} + +/* + * store_cpu_topology is called at boot when only one cpu is running + * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, + * which prevents simultaneous write access to cpu_topology array + */ +void store_cpu_topology(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + unsigned int mpidr; + unsigned int cpu; + + /* If the cpu topology has been already set, just return */ + if (cpuid_topo->core_id != -1) + return; + + mpidr = read_cpuid_mpidr(); + + /* create cpu topology mapping */ + if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) { + /* + * This is a multiprocessor system + * multiprocessor format & multiprocessor mode field are set + */ + + if (mpidr & MPIDR_MT_BITMASK) { + /* core performance interdependency */ + cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT) + & MPIDR_LEVEL0_MASK; + cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT) + & MPIDR_LEVEL1_MASK; + cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT) + & MPIDR_LEVEL2_MASK; + } else { + /* largely independent cores */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT) + & MPIDR_LEVEL0_MASK; + cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT) + & MPIDR_LEVEL1_MASK; + } + } else { + /* + * This is an uniprocessor system + * we are in multiprocessor format but uniprocessor system + * or in the old uniprocessor format + */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = 0; + cpuid_topo->socket_id = -1; + } + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id == cpu_topo->socket_id) { + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id == cpu_topo->core_id) { + cpumask_set_cpu(cpuid, + &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->thread_sibling); + } + } + } + smp_wmb(); + + printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", + cpuid, cpu_topology[cpuid].thread_id, + cpu_topology[cpuid].core_id, + cpu_topology[cpuid].socket_id, mpidr); +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void init_cpu_topology(void) +{ + unsigned int cpu; + + /* init core mask */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); + + cpu_topo->thread_id = -1; + cpu_topo->core_id = -1; + cpu_topo->socket_id = -1; + cpumask_clear(&cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + } + smp_wmb(); +} diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index bc9f9da782cb..7f5b99eb2c50 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -21,12 +21,14 @@ #include <linux/kdebug.h> #include <linux/module.h> #include <linux/kexec.h> +#include <linux/bug.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/atomic.h> #include <asm/cacheflush.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/unistd.h> #include <asm/traps.h> @@ -270,6 +272,8 @@ void die(const char *str, struct pt_regs *regs, int err) spin_lock_irq(&die_lock); console_verbose(); bust_spinlocks(1); + if (!user_mode(regs)) + report_bug(regs->ARM_pc, regs); ret = __die(str, err, thread, regs); if (regs && kexec_should_crash(thread->task)) @@ -301,6 +305,24 @@ void arm_notify_die(const char *str, struct pt_regs *regs, } } +#ifdef CONFIG_GENERIC_BUG + +int is_valid_bugaddr(unsigned long pc) +{ +#ifdef CONFIG_THUMB2_KERNEL + unsigned short bkpt; +#else + unsigned long bkpt; +#endif + + if (probe_kernel_address((unsigned *)pc, bkpt)) + return 0; + + return bkpt == BUG_INSTR_VALUE; +} + +#endif + static LIST_HEAD(undef_hook); static DEFINE_SPINLOCK(undef_lock); @@ -706,16 +728,6 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs) arm_notify_die("unknown data abort code", regs, &info, instr, 0); } -void __attribute__((noreturn)) __bug(const char *file, int line) -{ - printk(KERN_CRIT"kernel BUG at %s:%d!\n", file, line); - *(int *)0 = 0; - - /* Avoid "noreturn function does return" */ - for (;;); -} -EXPORT_SYMBOL(__bug); - void __readwrite_bug(const char *fn) { printk("%s called, but not implemented\n", fn); diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 4e66f62b8d41..20b3041e0860 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -21,7 +21,8 @@ #define ARM_CPU_KEEP(x) #endif -#if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK) +#if (defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)) || \ + defined(CONFIG_GENERIC_BUG) #define ARM_EXIT_KEEP(x) x #define ARM_EXIT_DISCARD(x) #else diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S index a673297b0cf1..cd07b5814c23 100644 --- a/arch/arm/lib/backtrace.S +++ b/arch/arm/lib/backtrace.S @@ -22,15 +22,10 @@ #define mask r7 #define offset r8 -ENTRY(__backtrace) - mov r1, #0x10 - mov r0, fp - ENTRY(c_backtrace) #if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK) mov pc, lr -ENDPROC(__backtrace) ENDPROC(c_backtrace) #else stmfd sp!, {r4 - r8, lr} @ Save an extra register so we have a location... @@ -107,7 +102,6 @@ for_each_frame: tst frame, mask @ Check for address exceptions mov r1, frame bl printk no_frame: ldmfd sp!, {r4 - r8, pc} -ENDPROC(__backtrace) ENDPROC(c_backtrace) .pushsection __ex_table,"a" diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S index faa7748142da..e55c4842c290 100644 --- a/arch/arm/lib/div64.S +++ b/arch/arm/lib/div64.S @@ -13,6 +13,7 @@ */ #include <linux/linkage.h> +#include <asm/unwind.h> #ifdef __ARMEB__ #define xh r0 @@ -44,6 +45,7 @@ */ ENTRY(__do_div64) +UNWIND(.fnstart) @ Test for easy paths first. subs ip, r4, #1 @@ -189,7 +191,12 @@ ENTRY(__do_div64) moveq yh, xh moveq xh, #0 moveq pc, lr +UNWIND(.fnend) +UNWIND(.fnstart) +UNWIND(.pad #4) +UNWIND(.save {lr}) +Ldiv0_64: @ Division by 0: str lr, [sp, #-8]! bl __div0 @@ -200,4 +207,5 @@ ENTRY(__do_div64) mov xh, #0 ldr pc, [sp], #8 +UNWIND(.fnend) ENDPROC(__do_div64) diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 8b9b13649f81..025f742dd4df 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -17,6 +17,7 @@ #include <linux/sched.h> #include <linux/hardirq.h> /* for in_atomic() */ #include <linux/gfp.h> +#include <linux/highmem.h> #include <asm/current.h> #include <asm/page.h> diff --git a/arch/arm/mach-at91/Makefile.boot b/arch/arm/mach-at91/Makefile.boot index 3462b815054a..9ab5a3e5f4f1 100644 --- a/arch/arm/mach-at91/Makefile.boot +++ b/arch/arm/mach-at91/Makefile.boot @@ -4,15 +4,15 @@ # INITRD_PHYS must be in RAM ifeq ($(CONFIG_ARCH_AT91CAP9),y) - zreladdr-y := 0x70008000 + zreladdr-y += 0x70008000 params_phys-y := 0x70000100 initrd_phys-y := 0x70410000 else ifeq ($(CONFIG_ARCH_AT91SAM9G45),y) - zreladdr-y := 0x70008000 + zreladdr-y += 0x70008000 params_phys-y := 0x70000100 initrd_phys-y := 0x70410000 else - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 initrd_phys-y := 0x20410000 endif diff --git a/arch/arm/mach-bcmring/Makefile.boot b/arch/arm/mach-bcmring/Makefile.boot index fb53b283bebb..aef2467757fa 100644 --- a/arch/arm/mach-bcmring/Makefile.boot +++ b/arch/arm/mach-bcmring/Makefile.boot @@ -1,6 +1,6 @@ # Address where decompressor will be written and eventually executed. # # default to SDRAM -zreladdr-y := $(CONFIG_BCM_ZRELADDR) +zreladdr-y += $(CONFIG_BCM_ZRELADDR) params_phys-y := 0x00000800 diff --git a/arch/arm/mach-bcmring/arch.c b/arch/arm/mach-bcmring/arch.c index a604b9ebb501..31a143592c81 100644 --- a/arch/arm/mach-bcmring/arch.c +++ b/arch/arm/mach-bcmring/arch.c @@ -136,8 +136,8 @@ static void __init bcmring_init_machine(void) * *****************************************************************************/ -static void __init bcmring_fixup(struct machine_desc *desc, - struct tag *t, char **cmdline, struct meminfo *mi) { +static void __init bcmring_fixup(struct tag *t, char **cmdline, + struct meminfo *mi) { #ifdef CONFIG_BLK_DEV_INITRD printk(KERN_NOTICE "bcmring_fixup\n"); t->hdr.tag = ATAG_CORE; diff --git a/arch/arm/mach-clps711x/Makefile.boot b/arch/arm/mach-clps711x/Makefile.boot index a51fcef64fe0..9398e859b5af 100644 --- a/arch/arm/mach-clps711x/Makefile.boot +++ b/arch/arm/mach-clps711x/Makefile.boot @@ -1,5 +1,5 @@ # The standard locations for stuff on CLPS711x type processors - zreladdr-y := 0xc0028000 + zreladdr-y += 0xc0028000 params_phys-y := 0xc0000100 # Should probably have some agreement on these... initrd_phys-$(CONFIG_ARCH_P720T) := 0xc0400000 diff --git a/arch/arm/mach-clps711x/clep7312.c b/arch/arm/mach-clps711x/clep7312.c index 67b5abb4a60a..0a2e74feb24a 100644 --- a/arch/arm/mach-clps711x/clep7312.c +++ b/arch/arm/mach-clps711x/clep7312.c @@ -26,8 +26,7 @@ #include "common.h" static void __init -fixup_clep7312(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_clep7312(struct tag *tags, char **cmdline, struct meminfo *mi) { mi->nr_banks=1; mi->bank[0].start = 0xc0000000; diff --git a/arch/arm/mach-clps711x/edb7211-arch.c b/arch/arm/mach-clps711x/edb7211-arch.c index 98ca5b2e940d..725a7a54ba42 100644 --- a/arch/arm/mach-clps711x/edb7211-arch.c +++ b/arch/arm/mach-clps711x/edb7211-arch.c @@ -37,8 +37,7 @@ static void __init edb7211_reserve(void) } static void __init -fixup_edb7211(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_edb7211(struct tag *tags, char **cmdline, struct meminfo *mi) { /* * Bank start addresses are not present in the information diff --git a/arch/arm/mach-clps711x/fortunet.c b/arch/arm/mach-clps711x/fortunet.c index b1cb479e71e9..1947b30f9b8c 100644 --- a/arch/arm/mach-clps711x/fortunet.c +++ b/arch/arm/mach-clps711x/fortunet.c @@ -57,8 +57,7 @@ typedef struct tag_IMAGE_PARAMS #define IMAGE_PARAMS_PHYS 0xC01F0000 static void __init -fortunet_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fortunet_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) { IMAGE_PARAMS *ip = phys_to_virt(IMAGE_PARAMS_PHYS); *cmdline = phys_to_virt(ip->command_line); diff --git a/arch/arm/mach-clps711x/p720t.c b/arch/arm/mach-clps711x/p720t.c index cefbce0480b9..3f796e0d3284 100644 --- a/arch/arm/mach-clps711x/p720t.c +++ b/arch/arm/mach-clps711x/p720t.c @@ -56,8 +56,7 @@ static struct map_desc p720t_io_desc[] __initdata = { }; static void __init -fixup_p720t(struct machine_desc *desc, struct tag *tag, - char **cmdline, struct meminfo *mi) +fixup_p720t(struct tag *tag, char **cmdline, struct meminfo *mi) { /* * Our bootloader doesn't setup any tags (yet). diff --git a/arch/arm/mach-cns3xxx/Makefile.boot b/arch/arm/mach-cns3xxx/Makefile.boot index 777012865220..d079de0b6e3b 100644 --- a/arch/arm/mach-cns3xxx/Makefile.boot +++ b/arch/arm/mach-cns3xxx/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00C00000 diff --git a/arch/arm/mach-davinci/Makefile.boot b/arch/arm/mach-davinci/Makefile.boot index db97ef2c6477..04a6c4e67b14 100644 --- a/arch/arm/mach-davinci/Makefile.boot +++ b/arch/arm/mach-davinci/Makefile.boot @@ -2,12 +2,12 @@ ifeq ($(CONFIG_ARCH_DAVINCI_DA8XX),y) ifeq ($(CONFIG_ARCH_DAVINCI_DMx),y) $(error Cannot enable DaVinci and DA8XX platforms concurrently) else - zreladdr-y := 0xc0008000 + zreladdr-y += 0xc0008000 params_phys-y := 0xc0000100 initrd_phys-y := 0xc0800000 endif else - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x80800000 endif diff --git a/arch/arm/mach-dove/Makefile.boot b/arch/arm/mach-dove/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-dove/Makefile.boot +++ b/arch/arm/mach-dove/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ebsa110/Makefile.boot b/arch/arm/mach-ebsa110/Makefile.boot index 232126044935..83cf07c38ada 100644 --- a/arch/arm/mach-ebsa110/Makefile.boot +++ b/arch/arm/mach-ebsa110/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000400 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ebsa110/include/mach/io.h b/arch/arm/mach-ebsa110/include/mach/io.h index f68daa632af0..44679db672fb 100644 --- a/arch/arm/mach-ebsa110/include/mach/io.h +++ b/arch/arm/mach-ebsa110/include/mach/io.h @@ -13,8 +13,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffff - u8 __inb8(unsigned int port); void __outb8(u8 val, unsigned int port); diff --git a/arch/arm/mach-ep93xx/Makefile.boot b/arch/arm/mach-ep93xx/Makefile.boot index 0ad33f15c622..d3113a71cb40 100644 --- a/arch/arm/mach-ep93xx/Makefile.boot +++ b/arch/arm/mach-ep93xx/Makefile.boot @@ -1,14 +1,14 @@ - zreladdr-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET) := 0x00008000 + zreladdr-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET) += 0x00008000 params_phys-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET) := 0x00000100 - zreladdr-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET) := 0xc0008000 + zreladdr-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET) += 0xc0008000 params_phys-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET) := 0xc0000100 - zreladdr-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET) := 0xd0008000 + zreladdr-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET) += 0xd0008000 params_phys-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET) := 0xd0000100 - zreladdr-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET) := 0xe0008000 + zreladdr-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET) += 0xe0008000 params_phys-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET) := 0xe0000100 - zreladdr-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET) := 0xf0008000 + zreladdr-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET) += 0xf0008000 params_phys-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET) := 0xf0000100 diff --git a/arch/arm/mach-exynos4/Kconfig b/arch/arm/mach-exynos4/Kconfig index 0c77ab99fa16..fc1f92dfbea8 100644 --- a/arch/arm/mach-exynos4/Kconfig +++ b/arch/arm/mach-exynos4/Kconfig @@ -12,6 +12,7 @@ if ARCH_EXYNOS4 config CPU_EXYNOS4210 bool select S3C_PL330_DMA + select ARM_CPU_SUSPEND if PM help Enable EXYNOS4210 CPU support diff --git a/arch/arm/mach-exynos4/Makefile.boot b/arch/arm/mach-exynos4/Makefile.boot index d65956ffb43d..b9862e22bf10 100644 --- a/arch/arm/mach-exynos4/Makefile.boot +++ b/arch/arm/mach-exynos4/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x40008000 + zreladdr-y += 0x40008000 params_phys-y := 0x40000100 diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c index df6ef1b2f98b..0c90896ad9a0 100644 --- a/arch/arm/mach-exynos4/platsmp.c +++ b/arch/arm/mach-exynos4/platsmp.c @@ -193,12 +193,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "EXYNOS4: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index c8e7afcf14ec..f643ef819da6 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -4,8 +4,8 @@ menu "Footbridge Implementations" config ARCH_CATS bool "CATS" - select CLKSRC_I8253 select CLKEVT_I8253 + select CLKSRC_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA @@ -61,8 +61,8 @@ config ARCH_EBSA285_HOST config ARCH_NETWINDER bool "NetWinder" - select CLKSRC_I8253 select CLKEVT_I8253 + select CLKSRC_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA diff --git a/arch/arm/mach-footbridge/Makefile.boot b/arch/arm/mach-footbridge/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-footbridge/Makefile.boot +++ b/arch/arm/mach-footbridge/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-footbridge/cats-hw.c b/arch/arm/mach-footbridge/cats-hw.c index 5b1a8db779be..206ff2f39d6c 100644 --- a/arch/arm/mach-footbridge/cats-hw.c +++ b/arch/arm/mach-footbridge/cats-hw.c @@ -76,8 +76,7 @@ __initcall(cats_hw_init); * hard reboots fail on early boards. */ static void __init -fixup_cats(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_cats(struct tag *tags, char **cmdline, struct meminfo *mi) { screen_info.orig_video_lines = 25; screen_info.orig_video_points = 16; diff --git a/arch/arm/mach-footbridge/include/mach/io.h b/arch/arm/mach-footbridge/include/mach/io.h index 32e4cc397c28..15a70396c27d 100644 --- a/arch/arm/mach-footbridge/include/mach/io.h +++ b/arch/arm/mach-footbridge/include/mach/io.h @@ -23,8 +23,6 @@ #define PCIO_SIZE 0x00100000 #define PCIO_BASE MMU_IO(0xff000000, 0x7c000000) -#define IO_SPACE_LIMIT 0xffff - /* * Translation of various region addresses to virtual addresses */ diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c index 06e514f372d0..4cbc2e65ce3a 100644 --- a/arch/arm/mach-footbridge/netwinder-hw.c +++ b/arch/arm/mach-footbridge/netwinder-hw.c @@ -631,8 +631,7 @@ __initcall(nw_hw_init); * the parameter page. */ static void __init -fixup_netwinder(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_netwinder(struct tag *tags, char **cmdline, struct meminfo *mi) { #ifdef CONFIG_ISAPNP extern int isapnp_disable; diff --git a/arch/arm/mach-gemini/Makefile.boot b/arch/arm/mach-gemini/Makefile.boot index 22a52c228d93..683f52b20e3d 100644 --- a/arch/arm/mach-gemini/Makefile.boot +++ b/arch/arm/mach-gemini/Makefile.boot @@ -1,9 +1,9 @@ ifeq ($(CONFIG_GEMINI_MEM_SWAP),y) - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 else - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x10800000 endif diff --git a/arch/arm/mach-h720x/Makefile.boot b/arch/arm/mach-h720x/Makefile.boot index 52984017bd91..d875a7094dfe 100644 --- a/arch/arm/mach-h720x/Makefile.boot +++ b/arch/arm/mach-h720x/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-$(CONFIG_ARCH_H720X) := 0x40008000 + zreladdr-$(CONFIG_ARCH_H720X) += 0x40008000 diff --git a/arch/arm/mach-imx/Makefile.boot b/arch/arm/mach-imx/Makefile.boot index ebee18b3884c..dbe61201bcd8 100644 --- a/arch/arm/mach-imx/Makefile.boot +++ b/arch/arm/mach-imx/Makefile.boot @@ -1,19 +1,19 @@ -zreladdr-$(CONFIG_ARCH_MX1) := 0x08008000 +zreladdr-$(CONFIG_ARCH_MX1) += 0x08008000 params_phys-$(CONFIG_ARCH_MX1) := 0x08000100 initrd_phys-$(CONFIG_ARCH_MX1) := 0x08800000 -zreladdr-$(CONFIG_MACH_MX21) := 0xC0008000 +zreladdr-$(CONFIG_MACH_MX21) += 0xC0008000 params_phys-$(CONFIG_MACH_MX21) := 0xC0000100 initrd_phys-$(CONFIG_MACH_MX21) := 0xC0800000 -zreladdr-$(CONFIG_ARCH_MX25) := 0x80008000 +zreladdr-$(CONFIG_ARCH_MX25) += 0x80008000 params_phys-$(CONFIG_ARCH_MX25) := 0x80000100 initrd_phys-$(CONFIG_ARCH_MX25) := 0x80800000 -zreladdr-$(CONFIG_MACH_MX27) := 0xA0008000 +zreladdr-$(CONFIG_MACH_MX27) += 0xA0008000 params_phys-$(CONFIG_MACH_MX27) := 0xA0000100 initrd_phys-$(CONFIG_MACH_MX27) := 0xA0800000 -zreladdr-$(CONFIG_ARCH_MX3) := 0x80008000 +zreladdr-$(CONFIG_ARCH_MX3) += 0x80008000 params_phys-$(CONFIG_ARCH_MX3) := 0x80000100 initrd_phys-$(CONFIG_ARCH_MX3) := 0x80800000 diff --git a/arch/arm/mach-integrator/Makefile.boot b/arch/arm/mach-integrator/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-integrator/Makefile.boot +++ b/arch/arm/mach-integrator/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c index 77315b995681..82ebc8d772d3 100644 --- a/arch/arm/mach-integrator/core.c +++ b/arch/arm/mach-integrator/core.c @@ -126,6 +126,10 @@ static struct clk_lookup lookups[] = { { /* Bus clock */ .con_id = "apb_pclk", .clk = &dummy_apb_pclk, + }, { + /* Integrator/AP timer frequency */ + .dev_id = "ap_timer", + .clk = &clk24mhz, }, { /* UART0 */ .dev_id = "mb:16", .clk = &uartclk, diff --git a/arch/arm/mach-integrator/include/mach/io.h b/arch/arm/mach-integrator/include/mach/io.h index f21bb5493dd9..37beed3fa3ed 100644 --- a/arch/arm/mach-integrator/include/mach/io.h +++ b/arch/arm/mach-integrator/include/mach/io.h @@ -20,8 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffff - /* * WARNING: this has to mirror definitions in platform.h */ diff --git a/arch/arm/mach-integrator/include/mach/platform.h b/arch/arm/mach-integrator/include/mach/platform.h index 5e6ea5cfea6e..ec467baade09 100644 --- a/arch/arm/mach-integrator/include/mach/platform.h +++ b/arch/arm/mach-integrator/include/mach/platform.h @@ -13,9 +13,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -/* DO NOT EDIT!! - this file automatically generated - * from .s file by awk -f s2h.awk - */ /************************************************************************** * * Copyright © ARM Limited 1998. All rights reserved. * ***********************************************************************/ @@ -399,15 +396,6 @@ #define INTEGRATOR_TIMER1_BASE (INTEGRATOR_CT_BASE + 0x100) #define INTEGRATOR_TIMER2_BASE (INTEGRATOR_CT_BASE + 0x200) -#define TICKS_PER_uSEC 24 - -/* - * These are useconds NOT ticks. - * - */ -#define mSEC_1 1000 -#define mSEC_10 (mSEC_1 * 10) - #define INTEGRATOR_CSR_BASE 0x10000000 #define INTEGRATOR_CSR_SIZE 0x10000000 diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index 8cdc730dcb3a..f2119908a0b3 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/mtd/physmap.h> +#include <linux/clk.h> #include <video/vga.h> #include <mach/hardware.h> @@ -322,27 +323,16 @@ static void __init ap_init(void) #define TIMER1_VA_BASE IO_ADDRESS(INTEGRATOR_TIMER1_BASE) #define TIMER2_VA_BASE IO_ADDRESS(INTEGRATOR_TIMER2_BASE) -/* - * How long is the timer interval? - */ -#define TIMER_INTERVAL (TICKS_PER_uSEC * mSEC_10) -#if TIMER_INTERVAL >= 0x100000 -#define TICKS2USECS(x) (256 * (x) / TICKS_PER_uSEC) -#elif TIMER_INTERVAL >= 0x10000 -#define TICKS2USECS(x) (16 * (x) / TICKS_PER_uSEC) -#else -#define TICKS2USECS(x) ((x) / TICKS_PER_uSEC) -#endif - static unsigned long timer_reload; -static void integrator_clocksource_init(u32 khz) +static void integrator_clocksource_init(unsigned long inrate) { void __iomem *base = (void __iomem *)TIMER2_VA_BASE; u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC; + unsigned long rate = inrate; - if (khz >= 1500) { - khz /= 16; + if (rate >= 1500000) { + rate /= 16; ctrl |= TIMER_CTRL_DIV16; } @@ -350,7 +340,7 @@ static void integrator_clocksource_init(u32 khz) writel(ctrl, base + TIMER_CTRL); clocksource_mmio_init(base + TIMER_VALUE, "timer2", - khz * 1000, 200, 16, clocksource_mmio_readl_down); + rate, 200, 16, clocksource_mmio_readl_down); } static void __iomem * const clkevt_base = (void __iomem *)TIMER1_VA_BASE; @@ -374,15 +364,29 @@ static void clkevt_set_mode(enum clock_event_mode mode, struct clock_event_devic { u32 ctrl = readl(clkevt_base + TIMER_CTRL) & ~TIMER_CTRL_ENABLE; - BUG_ON(mode == CLOCK_EVT_MODE_ONESHOT); + /* Disable timer */ + writel(ctrl, clkevt_base + TIMER_CTRL); - if (mode == CLOCK_EVT_MODE_PERIODIC) { - writel(ctrl, clkevt_base + TIMER_CTRL); + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + /* Enable the timer and start the periodic tick */ writel(timer_reload, clkevt_base + TIMER_LOAD); ctrl |= TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE; + writel(ctrl, clkevt_base + TIMER_CTRL); + break; + case CLOCK_EVT_MODE_ONESHOT: + /* Leave the timer disabled, .set_next_event will enable it */ + ctrl &= ~TIMER_CTRL_PERIODIC; + writel(ctrl, clkevt_base + TIMER_CTRL); + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + case CLOCK_EVT_MODE_RESUME: + default: + /* Just leave in disabled state */ + break; } - writel(ctrl, clkevt_base + TIMER_CTRL); } static int clkevt_set_next_event(unsigned long next, struct clock_event_device *evt) @@ -398,12 +402,10 @@ static int clkevt_set_next_event(unsigned long next, struct clock_event_device * static struct clock_event_device integrator_clockevent = { .name = "timer1", - .shift = 34, - .features = CLOCK_EVT_FEAT_PERIODIC, + .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, .set_mode = clkevt_set_mode, .set_next_event = clkevt_set_next_event, .rating = 300, - .cpumask = cpu_all_mask, }; static struct irqaction integrator_timer_irq = { @@ -413,29 +415,27 @@ static struct irqaction integrator_timer_irq = { .dev_id = &integrator_clockevent, }; -static void integrator_clockevent_init(u32 khz) +static void integrator_clockevent_init(unsigned long inrate) { - struct clock_event_device *evt = &integrator_clockevent; + unsigned long rate = inrate; unsigned int ctrl = 0; - if (khz * 1000 > 0x100000 * HZ) { - khz /= 256; + /* Calculate and program a divisor */ + if (rate > 0x100000 * HZ) { + rate /= 256; ctrl |= TIMER_CTRL_DIV256; - } else if (khz * 1000 > 0x10000 * HZ) { - khz /= 16; + } else if (rate > 0x10000 * HZ) { + rate /= 16; ctrl |= TIMER_CTRL_DIV16; } - - timer_reload = khz * 1000 / HZ; + timer_reload = rate / HZ; writel(ctrl, clkevt_base + TIMER_CTRL); - evt->irq = IRQ_TIMERINT1; - evt->mult = div_sc(khz, NSEC_PER_MSEC, evt->shift); - evt->max_delta_ns = clockevent_delta2ns(0xffff, evt); - evt->min_delta_ns = clockevent_delta2ns(0xf, evt); - setup_irq(IRQ_TIMERINT1, &integrator_timer_irq); - clockevents_register_device(evt); + clockevents_config_and_register(&integrator_clockevent, + rate, + 1, + 0xffffU); } /* @@ -443,14 +443,20 @@ static void integrator_clockevent_init(u32 khz) */ static void __init ap_init_timer(void) { - u32 khz = TICKS_PER_uSEC * 1000; + struct clk *clk; + unsigned long rate; + + clk = clk_get_sys("ap_timer", NULL); + BUG_ON(IS_ERR(clk)); + clk_enable(clk); + rate = clk_get_rate(clk); writel(0, TIMER0_VA_BASE + TIMER_CTRL); writel(0, TIMER1_VA_BASE + TIMER_CTRL); writel(0, TIMER2_VA_BASE + TIMER_CTRL); - integrator_clocksource_init(khz); - integrator_clockevent_init(khz); + integrator_clocksource_init(rate); + integrator_clockevent_init(rate); } static struct sys_timer ap_timer = { diff --git a/arch/arm/mach-iop13xx/Makefile.boot b/arch/arm/mach-iop13xx/Makefile.boot index 0b0e19fdfe6c..3a8c38c3189c 100644 --- a/arch/arm/mach-iop13xx/Makefile.boot +++ b/arch/arm/mach-iop13xx/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-iop32x/Makefile.boot b/arch/arm/mach-iop32x/Makefile.boot index 47000dccd61f..0a833b11e38c 100644 --- a/arch/arm/mach-iop32x/Makefile.boot +++ b/arch/arm/mach-iop32x/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0xa0008000 + zreladdr-y += 0xa0008000 params_phys-y := 0xa0000100 initrd_phys-y := 0xa0800000 diff --git a/arch/arm/mach-iop33x/Makefile.boot b/arch/arm/mach-iop33x/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-iop33x/Makefile.boot +++ b/arch/arm/mach-iop33x/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ixp2000/Makefile.boot b/arch/arm/mach-ixp2000/Makefile.boot index d84c5807a43d..9c7af91d93da 100644 --- a/arch/arm/mach-ixp2000/Makefile.boot +++ b/arch/arm/mach-ixp2000/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-ixp23xx/Makefile.boot b/arch/arm/mach-ixp23xx/Makefile.boot index d5561ad15bad..44fb4a717c3f 100644 --- a/arch/arm/mach-ixp23xx/Makefile.boot +++ b/arch/arm/mach-ixp23xx/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-ixp4xx/Makefile.boot b/arch/arm/mach-ixp4xx/Makefile.boot index d84c5807a43d..9c7af91d93da 100644 --- a/arch/arm/mach-ixp4xx/Makefile.boot +++ b/arch/arm/mach-ixp4xx/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index 2131832ee6ba..85245e48099c 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -397,7 +397,8 @@ void __init ixp4xx_pci_preinit(void) local_write_config(PCI_BASE_ADDRESS_0, 4, PHYS_OFFSET); local_write_config(PCI_BASE_ADDRESS_1, 4, PHYS_OFFSET + SZ_16M); local_write_config(PCI_BASE_ADDRESS_2, 4, PHYS_OFFSET + SZ_32M); - local_write_config(PCI_BASE_ADDRESS_3, 4, PHYS_OFFSET + SZ_48M); + local_write_config(PCI_BASE_ADDRESS_3, 4, + PHYS_OFFSET + SZ_32M + SZ_16M); /* * Enable CSR window at 64 MiB to allow PCI masters diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h index 57b5410c31f4..ffb9d6afb89f 100644 --- a/arch/arm/mach-ixp4xx/include/mach/io.h +++ b/arch/arm/mach-ixp4xx/include/mach/io.h @@ -17,8 +17,6 @@ #include <mach/hardware.h> -#define IO_SPACE_LIMIT 0x0000ffff - extern int (*ixp4xx_pci_read)(u32 addr, u32 cmd, u32* data); extern int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data); diff --git a/arch/arm/mach-kirkwood/Makefile.boot b/arch/arm/mach-kirkwood/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-kirkwood/Makefile.boot +++ b/arch/arm/mach-kirkwood/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ks8695/Makefile.boot b/arch/arm/mach-ks8695/Makefile.boot index 48eb2cb3ac77..c9b0bebcf237 100644 --- a/arch/arm/mach-ks8695/Makefile.boot +++ b/arch/arm/mach-ks8695/Makefile.boot @@ -3,6 +3,6 @@ # PARAMS_PHYS must be within 4MB of ZRELADDR # INITRD_PHYS must be in RAM - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-lpc32xx/Makefile.boot b/arch/arm/mach-lpc32xx/Makefile.boot index b796b41ebf8f..2cfe0ee635c5 100644 --- a/arch/arm/mach-lpc32xx/Makefile.boot +++ b/arch/arm/mach-lpc32xx/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x82000000 diff --git a/arch/arm/mach-mmp/Makefile.boot b/arch/arm/mach-mmp/Makefile.boot index 574a4aa8321a..5edf03e2beed 100644 --- a/arch/arm/mach-mmp/Makefile.boot +++ b/arch/arm/mach-mmp/Makefile.boot @@ -1 +1 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c index 06b5fa853c93..49c5d6d843d6 100644 --- a/arch/arm/mach-mmp/aspenite.c +++ b/arch/arm/mach-mmp/aspenite.c @@ -160,7 +160,7 @@ static struct mtd_partition aspenite_nand_partitions[] = { }, { .name = "filesystem", .offset = MTDPART_OFS_APPEND, - .size = SZ_48M, + .size = SZ_32M + SZ_16M, .mask_flags = 0, } }; diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c index 6bd37a27e5fc..176515a76989 100644 --- a/arch/arm/mach-mmp/ttc_dkb.c +++ b/arch/arm/mach-mmp/ttc_dkb.c @@ -93,7 +93,7 @@ static struct mtd_partition ttc_dkb_onenand_partitions[] = { }, { .name = "filesystem", .offset = MTDPART_OFS_APPEND, - .size = SZ_48M, + .size = SZ_32M + SZ_16M, .mask_flags = 0, } }; diff --git a/arch/arm/mach-msm/Makefile.boot b/arch/arm/mach-msm/Makefile.boot index 24dfbf8c07c4..9b803a578b4d 100644 --- a/arch/arm/mach-msm/Makefile.boot +++ b/arch/arm/mach-msm/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x10800000 diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c index 18a3c97bc863..f81ef1f9d46f 100644 --- a/arch/arm/mach-msm/board-halibut.c +++ b/arch/arm/mach-msm/board-halibut.c @@ -78,8 +78,8 @@ static void __init halibut_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init halibut_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init halibut_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks=1; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c index 7a9a03eb189c..1df15aa3c66d 100644 --- a/arch/arm/mach-msm/board-mahimahi.c +++ b/arch/arm/mach-msm/board-mahimahi.c @@ -53,8 +53,8 @@ static void __init mahimahi_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init mahimahi_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init mahimahi_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c index b7a84966b711..d1e4cc83b1e6 100644 --- a/arch/arm/mach-msm/board-msm7x30.c +++ b/arch/arm/mach-msm/board-msm7x30.c @@ -24,6 +24,7 @@ #include <linux/smsc911x.h> #include <linux/usb/msm_hsusb.h> #include <linux/clkdev.h> +#include <linux/memblock.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -42,6 +43,21 @@ extern struct sys_timer msm_timer; +static void __init msm7x30_fixup(struct machine_desc *desc, struct tag *tag, + char **cmdline, struct meminfo *mi) +{ + for (; tag->hdr.size; tag = tag_next(tag)) + if (tag->hdr.tag == ATAG_MEM && tag->u.mem.start == 0x200000) { + tag->u.mem.start = 0; + tag->u.mem.size += SZ_2M; + } +} + +static void __init msm7x30_reserve(void) +{ + memblock_remove(0x0, SZ_2M); +} + static int hsusb_phy_init_seq[] = { 0x30, 0x32, /* Enable and set Pre-Emphasis Depth to 20% */ 0x02, 0x36, /* Disable CDR Auto Reset feature */ @@ -107,6 +123,8 @@ static void __init msm7x30_map_io(void) MACHINE_START(MSM7X30_SURF, "QCT MSM7X30 SURF") .boot_params = PLAT_PHYS_OFFSET + 0x100, + .fixup = msm7x30_fixup, + .reserve = msm7x30_reserve, .map_io = msm7x30_map_io, .init_irq = msm7x30_init_irq, .init_machine = msm7x30_init, @@ -115,6 +133,8 @@ MACHINE_END MACHINE_START(MSM7X30_FFA, "QCT MSM7X30 FFA") .boot_params = PLAT_PHYS_OFFSET + 0x100, + .fixup = msm7x30_fixup, + .reserve = msm7x30_reserve, .map_io = msm7x30_map_io, .init_irq = msm7x30_init_irq, .init_machine = msm7x30_init, @@ -123,6 +143,8 @@ MACHINE_END MACHINE_START(MSM7X30_FLUID, "QCT MSM7X30 FLUID") .boot_params = PLAT_PHYS_OFFSET + 0x100, + .fixup = msm7x30_fixup, + .reserve = msm7x30_reserve, .map_io = msm7x30_map_io, .init_irq = msm7x30_init_irq, .init_machine = msm7x30_init, diff --git a/arch/arm/mach-msm/board-msm8960.c b/arch/arm/mach-msm/board-msm8960.c index 35c7ceeb3f29..b04468e7d00e 100644 --- a/arch/arm/mach-msm/board-msm8960.c +++ b/arch/arm/mach-msm/board-msm8960.c @@ -20,16 +20,34 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/clkdev.h> +#include <linux/memblock.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> #include <asm/hardware/gic.h> +#include <asm/setup.h> #include <mach/board.h> #include <mach/msm_iomap.h> #include "devices.h" +static void __init msm8960_fixup(struct machine_desc *desc, struct tag *tag, + char **cmdline, struct meminfo *mi) +{ + for (; tag->hdr.size; tag = tag_next(tag)) + if (tag->hdr.tag == ATAG_MEM && + tag->u.mem.start == 0x40200000) { + tag->u.mem.start = 0x40000000; + tag->u.mem.size += SZ_2M; + } +} + +static void __init msm8960_reserve(void) +{ + memblock_remove(0x40000000, SZ_2M); +} + static void __init msm8960_map_io(void) { msm_map_msm8960_io(); @@ -76,6 +94,8 @@ static void __init msm8960_rumi3_init(void) } MACHINE_START(MSM8960_SIM, "QCT MSM8960 SIMULATOR") + .fixup = msm8960_fixup, + .reserve = msm8960_reserve, .map_io = msm8960_map_io, .init_irq = msm8960_init_irq, .timer = &msm_timer, @@ -83,6 +103,8 @@ MACHINE_START(MSM8960_SIM, "QCT MSM8960 SIMULATOR") MACHINE_END MACHINE_START(MSM8960_RUMI3, "QCT MSM8960 RUMI3") + .fixup = msm8960_fixup, + .reserve = msm8960_reserve, .map_io = msm8960_map_io, .init_irq = msm8960_init_irq, .timer = &msm_timer, diff --git a/arch/arm/mach-msm/board-msm8x60.c b/arch/arm/mach-msm/board-msm8x60.c index 1163b6fd05d2..9221f54778be 100644 --- a/arch/arm/mach-msm/board-msm8x60.c +++ b/arch/arm/mach-msm/board-msm8x60.c @@ -20,14 +20,31 @@ #include <linux/platform_device.h> #include <linux/io.h> #include <linux/irq.h> +#include <linux/memblock.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> #include <asm/hardware/gic.h> +#include <asm/setup.h> #include <mach/board.h> #include <mach/msm_iomap.h> +static void __init msm8x60_fixup(struct machine_desc *desc, struct tag *tag, + char **cmdline, struct meminfo *mi) +{ + for (; tag->hdr.size; tag = tag_next(tag)) + if (tag->hdr.tag == ATAG_MEM && + tag->u.mem.start == 0x40200000) { + tag->u.mem.start = 0x40000000; + tag->u.mem.size += SZ_2M; + } +} + +static void __init msm8x60_reserve(void) +{ + memblock_remove(0x40000000, SZ_2M); +} static void __init msm8x60_map_io(void) { @@ -65,6 +82,8 @@ static void __init msm8x60_init(void) } MACHINE_START(MSM8X60_RUMI3, "QCT MSM8X60 RUMI3") + .fixup = msm8x60_fixup, + .reserve = msm8x60_reserve, .map_io = msm8x60_map_io, .init_irq = msm8x60_init_irq, .init_machine = msm8x60_init, @@ -72,6 +91,8 @@ MACHINE_START(MSM8X60_RUMI3, "QCT MSM8X60 RUMI3") MACHINE_END MACHINE_START(MSM8X60_SURF, "QCT MSM8X60 SURF") + .fixup = msm8x60_fixup, + .reserve = msm8x60_reserve, .map_io = msm8x60_map_io, .init_irq = msm8x60_init_irq, .init_machine = msm8x60_init, @@ -79,6 +100,8 @@ MACHINE_START(MSM8X60_SURF, "QCT MSM8X60 SURF") MACHINE_END MACHINE_START(MSM8X60_SIM, "QCT MSM8X60 SIMULATOR") + .fixup = msm8x60_fixup, + .reserve = msm8x60_reserve, .map_io = msm8x60_map_io, .init_irq = msm8x60_init_irq, .init_machine = msm8x60_init, @@ -86,6 +109,8 @@ MACHINE_START(MSM8X60_SIM, "QCT MSM8X60 SIMULATOR") MACHINE_END MACHINE_START(MSM8X60_FFA, "QCT MSM8X60 FFA") + .fixup = msm8x60_fixup, + .reserve = msm8x60_reserve, .map_io = msm8x60_map_io, .init_irq = msm8x60_init_irq, .init_machine = msm8x60_init, diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c index 68f930f07d77..c6e043c896aa 100644 --- a/arch/arm/mach-msm/board-sapphire.c +++ b/arch/arm/mach-msm/board-sapphire.c @@ -77,8 +77,8 @@ static struct map_desc sapphire_io_desc[] __initdata = { } }; -static void __init sapphire_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init sapphire_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { int smi_sz = parse_tag_smi((const struct tag *)tags); diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c index 814386772c66..7acd2021ada9 100644 --- a/arch/arm/mach-msm/board-trout.c +++ b/arch/arm/mach-msm/board-trout.c @@ -48,8 +48,8 @@ static void __init trout_init_irq(void) msm_init_irq(); } -static void __init trout_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init trout_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 1; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-msm/include/mach/memory.h b/arch/arm/mach-msm/include/mach/memory.h index f2f8d299ba95..58d5e7eec431 100644 --- a/arch/arm/mach-msm/include/mach/memory.h +++ b/arch/arm/mach-msm/include/mach/memory.h @@ -22,11 +22,11 @@ #elif defined(CONFIG_ARCH_QSD8X50) #define PLAT_PHYS_OFFSET UL(0x20000000) #elif defined(CONFIG_ARCH_MSM7X30) -#define PLAT_PHYS_OFFSET UL(0x00200000) +#define PLAT_PHYS_OFFSET UL(0x00000000) #elif defined(CONFIG_ARCH_MSM8X60) -#define PLAT_PHYS_OFFSET UL(0x40200000) +#define PLAT_PHYS_OFFSET UL(0x40000000) #elif defined(CONFIG_ARCH_MSM8960) -#define PLAT_PHYS_OFFSET UL(0x40200000) +#define PLAT_PHYS_OFFSET UL(0x40000000) #else #define PLAT_PHYS_OFFSET UL(0x10000000) #endif diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 1a1af9e56250..727659520912 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -156,6 +156,12 @@ void __init smp_init_cpus(void) { unsigned int i, ncores = get_core_count(); + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; i++) set_cpu_possible(i, true); diff --git a/arch/arm/mach-mv78xx0/Makefile.boot b/arch/arm/mach-mv78xx0/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-mv78xx0/Makefile.boot +++ b/arch/arm/mach-mv78xx0/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-mx5/Makefile.boot b/arch/arm/mach-mx5/Makefile.boot index e928be1b6757..ca207ca305ec 100644 --- a/arch/arm/mach-mx5/Makefile.boot +++ b/arch/arm/mach-mx5/Makefile.boot @@ -1,9 +1,9 @@ - zreladdr-$(CONFIG_ARCH_MX50) := 0x70008000 + zreladdr-$(CONFIG_ARCH_MX50) += 0x70008000 params_phys-$(CONFIG_ARCH_MX50) := 0x70000100 initrd_phys-$(CONFIG_ARCH_MX50) := 0x70800000 - zreladdr-$(CONFIG_ARCH_MX51) := 0x90008000 + zreladdr-$(CONFIG_ARCH_MX51) += 0x90008000 params_phys-$(CONFIG_ARCH_MX51) := 0x90000100 initrd_phys-$(CONFIG_ARCH_MX51) := 0x90800000 - zreladdr-$(CONFIG_ARCH_MX53) := 0x70008000 + zreladdr-$(CONFIG_ARCH_MX53) += 0x70008000 params_phys-$(CONFIG_ARCH_MX53) := 0x70000100 initrd_phys-$(CONFIG_ARCH_MX53) := 0x70800000 diff --git a/arch/arm/mach-mxs/Makefile.boot b/arch/arm/mach-mxs/Makefile.boot index eb541e0291da..07b11fe6453f 100644 --- a/arch/arm/mach-mxs/Makefile.boot +++ b/arch/arm/mach-mxs/Makefile.boot @@ -1 +1 @@ -zreladdr-y := 0x40008000 +zreladdr-y += 0x40008000 diff --git a/arch/arm/mach-netx/Makefile.boot b/arch/arm/mach-netx/Makefile.boot index b81cf6aff0ac..534a4d27055e 100644 --- a/arch/arm/mach-netx/Makefile.boot +++ b/arch/arm/mach-netx/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 diff --git a/arch/arm/mach-nomadik/Makefile.boot b/arch/arm/mach-nomadik/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-nomadik/Makefile.boot +++ b/arch/arm/mach-nomadik/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-nuc93x/Makefile.boot b/arch/arm/mach-nuc93x/Makefile.boot index a057b546b6e5..6c3d421c2d11 100644 --- a/arch/arm/mach-nuc93x/Makefile.boot +++ b/arch/arm/mach-nuc93x/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-omap1/Makefile.boot b/arch/arm/mach-omap1/Makefile.boot index 292d56c5a888..13bda8dbd604 100644 --- a/arch/arm/mach-omap1/Makefile.boot +++ b/arch/arm/mach-omap1/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x10800000 diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 57b66d590c52..89bfb49389f2 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -36,6 +36,7 @@ config ARCH_OMAP3 select ARM_L1_CACHE_SHIFT_6 if !ARCH_OMAP4 select ARCH_HAS_OPP select PM_OPP if PM + select ARM_CPU_SUSPEND if PM config ARCH_OMAP4 bool "TI OMAP4" @@ -50,6 +51,7 @@ config ARCH_OMAP4 select ARCH_HAS_OPP select PM_OPP if PM select USB_ARCH_HAS_EHCI + select ARM_CPU_SUSPEND if PM comment "OMAP Core Type" depends on ARCH_OMAP2 diff --git a/arch/arm/mach-omap2/Makefile.boot b/arch/arm/mach-omap2/Makefile.boot index 565aff7f37a9..b03e562acc60 100644 --- a/arch/arm/mach-omap2/Makefile.boot +++ b/arch/arm/mach-omap2/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x80800000 diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index ce65e9329c7b..889464dc7b2d 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -109,12 +109,10 @@ void __init smp_init_cpus(void) ncores = scu_get_core_count(scu_base); /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "OMAP4: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-orion5x/Makefile.boot b/arch/arm/mach-orion5x/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-orion5x/Makefile.boot +++ b/arch/arm/mach-orion5x/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 0ab531d047fc..22ace0bf2f92 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -308,8 +308,8 @@ void __init orion5x_init(void) * Many orion-based systems have buggy bootloader implementations. * This is a common fixup for bogus memory tags. */ -void __init tag_fixup_mem32(struct machine_desc *mdesc, struct tag *t, - char **from, struct meminfo *meminfo) +void __init tag_fixup_mem32(struct tag *t, char **from, + struct meminfo *meminfo) { for (; t->hdr.size; t = tag_next(t)) if (t->hdr.tag == ATAG_MEM && diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h index 3e5499dda49a..909489f4d23e 100644 --- a/arch/arm/mach-orion5x/common.h +++ b/arch/arm/mach-orion5x/common.h @@ -53,11 +53,9 @@ int orion5x_pci_sys_setup(int nr, struct pci_sys_data *sys); struct pci_bus *orion5x_pci_sys_scan_bus(int nr, struct pci_sys_data *sys); int orion5x_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin); -struct machine_desc; struct meminfo; struct tag; -extern void __init tag_fixup_mem32(struct machine_desc *, struct tag *, - char **, struct meminfo *); +extern void __init tag_fixup_mem32(struct tag *, char **, struct meminfo *); #endif diff --git a/arch/arm/mach-pnx4008/Makefile.boot b/arch/arm/mach-pnx4008/Makefile.boot index 44c7117e20dd..9fa19baa7f2e 100644 --- a/arch/arm/mach-pnx4008/Makefile.boot +++ b/arch/arm/mach-pnx4008/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x80800000 diff --git a/arch/arm/mach-prima2/Makefile.boot b/arch/arm/mach-prima2/Makefile.boot index d023db3ae4ff..c77a4883a4ee 100644 --- a/arch/arm/mach-prima2/Makefile.boot +++ b/arch/arm/mach-prima2/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-pxa/Makefile.boot b/arch/arm/mach-pxa/Makefile.boot index 1ead67178eca..2c1ae92f2106 100644 --- a/arch/arm/mach-pxa/Makefile.boot +++ b/arch/arm/mach-pxa/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0xa0008000 + zreladdr-y += 0xa0008000 diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c index b6a51340270b..d940e8a72270 100644 --- a/arch/arm/mach-pxa/cm-x300.c +++ b/arch/arm/mach-pxa/cm-x300.c @@ -839,8 +839,8 @@ static void __init cm_x300_init(void) cm_x300_init_bl(); } -static void __init cm_x300_fixup(struct machine_desc *mdesc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init cm_x300_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { /* Make sure that mi->bank[0].start = PHYS_ADDR */ for (; tags->hdr.size; tags = tag_next(tags)) diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index 185a37cad254..3e9483b06053 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -705,8 +705,8 @@ static void __init corgi_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init fixup_corgi(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init fixup_corgi(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks=1; diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c index b4599ec9d619..e4a1f4dc89ff 100644 --- a/arch/arm/mach-pxa/eseries.c +++ b/arch/arm/mach-pxa/eseries.c @@ -41,8 +41,7 @@ #include "clock.h" /* Only e800 has 128MB RAM */ -void __init eseries_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) { mi->nr_banks=1; mi->bank[0].start = 0xa0000000; diff --git a/arch/arm/mach-pxa/eseries.h b/arch/arm/mach-pxa/eseries.h index 5930f5e2a123..be921965e91a 100644 --- a/arch/arm/mach-pxa/eseries.h +++ b/arch/arm/mach-pxa/eseries.h @@ -1,5 +1,4 @@ -void __init eseries_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi); +void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi); extern struct pxa2xx_udc_mach_info e7xx_udc_mach_info; extern struct pxaficp_platform_data e7xx_ficp_platform_data; diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c index b09e848eb6c6..ca6075717824 100644 --- a/arch/arm/mach-pxa/irq.c +++ b/arch/arm/mach-pxa/irq.c @@ -19,6 +19,8 @@ #include <linux/io.h> #include <linux/irq.h> +#include <asm/exception.h> + #include <mach/hardware.h> #include <mach/irqs.h> #include <mach/gpio.h> diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c index a113ea9ab4ab..948ce3e729fa 100644 --- a/arch/arm/mach-pxa/poodle.c +++ b/arch/arm/mach-pxa/poodle.c @@ -454,8 +454,8 @@ static void __init poodle_init(void) poodle_init_spi(); } -static void __init fixup_poodle(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init fixup_poodle(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks=1; diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c index df4356e8acae..72001ec6e7b5 100644 --- a/arch/arm/mach-pxa/saar.c +++ b/arch/arm/mach-pxa/saar.c @@ -540,7 +540,7 @@ static struct mtd_partition saar_onenand_partitions[] = { }, { .name = "filesystem", .offset = MTDPART_OFS_APPEND, - .size = SZ_48M, + .size = SZ_32M + SZ_16M, .mask_flags = 0, } }; diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 438c7b5e451f..d8dec9113aad 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -970,8 +970,8 @@ static void __init spitz_init(void) spitz_i2c_init(); } -static void __init spitz_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init spitz_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks = 1; diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index 9f69a2682693..402b0c96613b 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -960,8 +960,8 @@ static void __init tosa_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init fixup_tosa(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init fixup_tosa(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks=1; diff --git a/arch/arm/mach-realview/Makefile.boot b/arch/arm/mach-realview/Makefile.boot index d97e003d3df4..d2c3d788f688 100644 --- a/arch/arm/mach-realview/Makefile.boot +++ b/arch/arm/mach-realview/Makefile.boot @@ -1,9 +1,9 @@ ifeq ($(CONFIG_REALVIEW_HIGH_PHYS_OFFSET),y) - zreladdr-y := 0x70008000 + zreladdr-y += 0x70008000 params_phys-y := 0x70000100 initrd_phys-y := 0x70800000 else - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 endif diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 5c23450d2d1d..d5ed5d4f77d6 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -517,8 +517,7 @@ void __init realview_timer_init(unsigned int timer_irq) /* * Setup the memory banks. */ -void realview_fixup(struct machine_desc *mdesc, struct tag *tags, char **from, - struct meminfo *meminfo) +void realview_fixup(struct tag *tags, char **from, struct meminfo *meminfo) { /* * Most RealView platforms have 512MB contiguous RAM at 0x70000000. diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h index 5c83d1e87a03..47259c89a75e 100644 --- a/arch/arm/mach-realview/core.h +++ b/arch/arm/mach-realview/core.h @@ -63,8 +63,8 @@ extern int realview_flash_register(struct resource *res, u32 num); extern int realview_eth_register(const char *name, struct resource *res); extern int realview_usb_register(struct resource *res); extern void realview_init_early(void); -extern void realview_fixup(struct machine_desc *mdesc, struct tag *tags, - char **from, struct meminfo *meminfo); +extern void realview_fixup(struct tag *tags, char **from, + struct meminfo *meminfo); extern void (*realview_reset)(char); #endif diff --git a/arch/arm/mach-realview/include/mach/board-pb1176.h b/arch/arm/mach-realview/include/mach/board-pb1176.h index 002ab5d8c11c..2a15fef94730 100644 --- a/arch/arm/mach-realview/include/mach/board-pb1176.h +++ b/arch/arm/mach-realview/include/mach/board-pb1176.h @@ -70,6 +70,7 @@ #define REALVIEW_DC1176_GIC_CPU_BASE 0x10120000 /* GIC CPU interface, on devchip */ #define REALVIEW_DC1176_GIC_DIST_BASE 0x10121000 /* GIC distributor, on devchip */ +#define REALVIEW_DC1176_ROM_BASE 0x10200000 /* 16KiB NRAM preudo-ROM, on devchip */ #define REALVIEW_PB1176_GIC_CPU_BASE 0x10040000 /* GIC CPU interface, on FPGA */ #define REALVIEW_PB1176_GIC_DIST_BASE 0x10041000 /* GIC distributor, on FPGA */ #define REALVIEW_PB1176_L220_BASE 0x10110000 /* L220 registers */ diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c index 4ae943bafa92..e83c654a58d0 100644 --- a/arch/arm/mach-realview/platsmp.c +++ b/arch/arm/mach-realview/platsmp.c @@ -52,12 +52,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "Realview: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c index ad5671acb66a..865d440fcf58 100644 --- a/arch/arm/mach-realview/realview_pb1176.c +++ b/arch/arm/mach-realview/realview_pb1176.c @@ -26,6 +26,8 @@ #include <linux/amba/pl061.h> #include <linux/amba/mmci.h> #include <linux/amba/pl022.h> +#include <linux/mtd/physmap.h> +#include <linux/mtd/partitions.h> #include <linux/io.h> #include <mach/hardware.h> @@ -204,22 +206,48 @@ static struct amba_device *amba_devs[] __initdata = { * RealView PB1176 platform devices */ static struct resource realview_pb1176_flash_resources[] = { - [0] = { + { .start = REALVIEW_PB1176_FLASH_BASE, .end = REALVIEW_PB1176_FLASH_BASE + REALVIEW_PB1176_FLASH_SIZE - 1, .flags = IORESOURCE_MEM, }, - [1] = { +#ifdef CONFIG_REALVIEW_PB1176_SECURE_FLASH + { .start = REALVIEW_PB1176_SEC_FLASH_BASE, .end = REALVIEW_PB1176_SEC_FLASH_BASE + REALVIEW_PB1176_SEC_FLASH_SIZE - 1, .flags = IORESOURCE_MEM, }, -}; -#ifdef CONFIG_REALVIEW_PB1176_SECURE_FLASH -#define PB1176_FLASH_BLOCKS 2 -#else -#define PB1176_FLASH_BLOCKS 1 #endif +}; + +static struct physmap_flash_data pb1176_rom_pdata = { + .probe_type = "map_rom", + .width = 4, + .nr_parts = 0, +}; + +static struct resource pb1176_rom_resources[] = { + /* + * This exposes the PB1176 DevChip ROM as an MTD ROM mapping. + * The reference manual states that this is actually a pseudo-ROM + * programmed in NVRAM. + */ + { + .start = REALVIEW_DC1176_ROM_BASE, + .end = REALVIEW_DC1176_ROM_BASE + SZ_16K - 1, + .flags = IORESOURCE_MEM, + } +}; + +static struct platform_device pb1176_rom_device = { + .name = "physmap-flash", + .id = -1, + .num_resources = ARRAY_SIZE(pb1176_rom_resources), + .resource = pb1176_rom_resources, + .dev = { + .platform_data = &pb1176_rom_pdata, + }, +}; static struct resource realview_pb1176_smsc911x_resources[] = { [0] = { @@ -316,8 +344,7 @@ static void realview_pb1176_reset(char mode) __raw_writel(REALVIEW_PB1176_SYS_SOFT_RESET, reset_ctrl); } -static void realview_pb1176_fixup(struct machine_desc *mdesc, - struct tag *tags, char **from, +static void realview_pb1176_fixup(struct tag *tags, char **from, struct meminfo *meminfo) { /* @@ -338,7 +365,8 @@ static void __init realview_pb1176_init(void) #endif realview_flash_register(realview_pb1176_flash_resources, - PB1176_FLASH_BLOCKS); + ARRAY_SIZE(realview_pb1176_flash_resources)); + platform_device_register(&pb1176_rom_device); realview_eth_register(NULL, realview_pb1176_smsc911x_resources); platform_device_register(&realview_i2c_device); realview_usb_register(realview_pb1176_isp1761_resources); diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c index 363b0ab56150..3e1eb2eb8132 100644 --- a/arch/arm/mach-realview/realview_pbx.c +++ b/arch/arm/mach-realview/realview_pbx.c @@ -319,8 +319,8 @@ static struct sys_timer realview_pbx_timer = { .init = realview_pbx_timer_init, }; -static void realview_pbx_fixup(struct machine_desc *mdesc, struct tag *tags, - char **from, struct meminfo *meminfo) +static void realview_pbx_fixup(struct tag *tags, char **from, + struct meminfo *meminfo) { #ifdef CONFIG_SPARSEMEM /* @@ -335,7 +335,7 @@ static void realview_pbx_fixup(struct machine_desc *mdesc, struct tag *tags, meminfo->bank[2].size = SZ_256M; meminfo->nr_banks = 3; #else - realview_fixup(mdesc, tags, from, meminfo); + realview_fixup(tags, from, meminfo); #endif } diff --git a/arch/arm/mach-rpc/Makefile.boot b/arch/arm/mach-rpc/Makefile.boot index 9c9e7685ec7c..ae2df0d7d037 100644 --- a/arch/arm/mach-rpc/Makefile.boot +++ b/arch/arm/mach-rpc/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x18000000 diff --git a/arch/arm/mach-rpc/include/mach/hardware.h b/arch/arm/mach-rpc/include/mach/hardware.h index dde6b3c0e299..050d63c74cc1 100644 --- a/arch/arm/mach-rpc/include/mach/hardware.h +++ b/arch/arm/mach-rpc/include/mach/hardware.h @@ -36,7 +36,7 @@ #define EASI_SIZE 0x08000000 /* EASI I/O */ #define EASI_START 0x08000000 -#define EASI_BASE 0xe5000000 +#define EASI_BASE IOMEM(0xe5000000) #define IO_START 0x03000000 /* I/O */ #define IO_SIZE 0x01000000 @@ -51,21 +51,20 @@ /* * IO Addresses */ -#define VIDC_BASE IOMEM(0xe0400000) -#define EXPMASK_BASE 0xe0360000 -#define IOMD_BASE IOMEM(0xe0200000) -#define IOC_BASE IOMEM(0xe0200000) -#define PCIO_BASE IOMEM(0xe0010000) -#define FLOPPYDMA_BASE IOMEM(0xe002a000) +#define ECARD_EASI_BASE (EASI_BASE) +#define VIDC_BASE (IO_BASE + 0x00400000) +#define EXPMASK_BASE (IO_BASE + 0x00360000) +#define ECARD_IOC4_BASE (IO_BASE + 0x00270000) +#define ECARD_IOC_BASE (IO_BASE + 0x00240000) +#define IOMD_BASE (IO_BASE + 0x00200000) +#define IOC_BASE (IO_BASE + 0x00200000) +#define ECARD_MEMC8_BASE (IO_BASE + 0x0002b000) +#define FLOPPYDMA_BASE (IO_BASE + 0x0002a000) +#define PCIO_BASE (IO_BASE + 0x00010000) +#define ECARD_MEMC_BASE (IO_BASE + 0x00000000) #define vidc_writel(val) __raw_writel(val, VIDC_BASE) -#define IO_EC_EASI_BASE 0x81400000 -#define IO_EC_IOC4_BASE 0x8009c000 -#define IO_EC_IOC_BASE 0x80090000 -#define IO_EC_MEMC8_BASE 0x8000ac00 -#define IO_EC_MEMC_BASE 0x80000000 - #define NETSLOT_BASE 0x0302b000 #define NETSLOT_SIZE 0x00001000 diff --git a/arch/arm/mach-rpc/include/mach/io.h b/arch/arm/mach-rpc/include/mach/io.h index 20da7f486e51..695f4ed2e11b 100644 --- a/arch/arm/mach-rpc/include/mach/io.h +++ b/arch/arm/mach-rpc/include/mach/io.h @@ -15,195 +15,18 @@ #include <mach/hardware.h> -#define IO_SPACE_LIMIT 0xffffffff +#define IO_SPACE_LIMIT 0xffff /* - * We use two different types of addressing - PC style addresses, and ARM - * addresses. PC style accesses the PC hardware with the normal PC IO - * addresses, eg 0x3f8 for serial#1. ARM addresses are 0x80000000+ - * and are translated to the start of IO. Note that all addresses are - * shifted left! - */ -#define __PORT_PCIO(x) (!((x) & 0x80000000)) - -/* - * Dynamic IO functions. - */ -static inline void __outb (unsigned int value, unsigned int port) -{ - unsigned long temp; - __asm__ __volatile__( - "tst %2, #0x80000000\n\t" - "mov %0, %4\n\t" - "addeq %0, %0, %3\n\t" - "strb %1, [%0, %2, lsl #2] @ outb" - : "=&r" (temp) - : "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) - : "cc"); -} - -static inline void __outw (unsigned int value, unsigned int port) -{ - unsigned long temp; - __asm__ __volatile__( - "tst %2, #0x80000000\n\t" - "mov %0, %4\n\t" - "addeq %0, %0, %3\n\t" - "str %1, [%0, %2, lsl #2] @ outw" - : "=&r" (temp) - : "r" (value|value<<16), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) - : "cc"); -} - -static inline void __outl (unsigned int value, unsigned int port) -{ - unsigned long temp; - __asm__ __volatile__( - "tst %2, #0x80000000\n\t" - "mov %0, %4\n\t" - "addeq %0, %0, %3\n\t" - "str %1, [%0, %2, lsl #2] @ outl" - : "=&r" (temp) - : "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) - : "cc"); -} - -#define DECLARE_DYN_IN(sz,fnsuffix,instr) \ -static inline unsigned sz __in##fnsuffix (unsigned int port) \ -{ \ - unsigned long temp, value; \ - __asm__ __volatile__( \ - "tst %2, #0x80000000\n\t" \ - "mov %0, %4\n\t" \ - "addeq %0, %0, %3\n\t" \ - "ldr" instr " %1, [%0, %2, lsl #2] @ in" #fnsuffix \ - : "=&r" (temp), "=r" (value) \ - : "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) \ - : "cc"); \ - return (unsigned sz)value; \ -} - -static inline void __iomem *__deprecated __ioaddr(unsigned int port) -{ - void __iomem *ret; - if (__PORT_PCIO(port)) - ret = PCIO_BASE; - else - ret = IO_BASE; - return ret + (port << 2); -} - -#define DECLARE_IO(sz,fnsuffix,instr) \ - DECLARE_DYN_IN(sz,fnsuffix,instr) - -DECLARE_IO(char,b,"b") -DECLARE_IO(short,w,"") -DECLARE_IO(int,l,"") - -#undef DECLARE_IO -#undef DECLARE_DYN_IN - -/* - * Constant address IO functions + * We need PC style IO addressing for: + * - floppy (at 0x3f2,0x3f4,0x3f5,0x3f7) + * - parport (at 0x278-0x27a, 0x27b-0x27f, 0x778-0x77a) + * - 8250 serial (only for compile) * - * These have to be macros for the 'J' constraint to work - - * +/-4096 immediate operand. + * These peripherals are found in an area of MMIO which looks very much + * like an ISA bus, but with registers at the low byte of each word. */ -#define __outbc(value,port) \ -({ \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "strb %0, [%1, %2] @ outbc" \ - : : "r" (value), "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "strb %0, [%1, %2] @ outbc" \ - : : "r" (value), "r" (IO_BASE), "r" ((port) << 2)); \ -}) - -#define __inbc(port) \ -({ \ - unsigned char result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldrb %0, [%1, %2] @ inbc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "ldrb %0, [%1, %2] @ inbc" \ - : "=r" (result) : "r" (IO_BASE), "r" ((port) << 2)); \ - result; \ -}) - -#define __outwc(value,port) \ -({ \ - unsigned long __v = value; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outwc" \ - : : "r" (__v|__v<<16), "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outwc" \ - : : "r" (__v|__v<<16), "r" (IO_BASE), "r" ((port) << 2)); \ -}) - -#define __inwc(port) \ -({ \ - unsigned short result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inwc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inwc" \ - : "=r" (result) : "r" (IO_BASE), "r" ((port) << 2)); \ - result & 0xffff; \ -}) - -#define __outlc(value,port) \ -({ \ - unsigned long __v = value; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outlc" \ - : : "r" (__v), "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outlc" \ - : : "r" (__v), "r" (IO_BASE), "r" ((port) << 2)); \ -}) - -#define __inlc(port) \ -({ \ - unsigned long result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inlc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inlc" \ - : "=r" (result) : "r" (IO_BASE), "r" ((port) << 2)); \ - result; \ -}) - -#define inb(p) (__builtin_constant_p((p)) ? __inbc(p) : __inb(p)) -#define inw(p) (__builtin_constant_p((p)) ? __inwc(p) : __inw(p)) -#define inl(p) (__builtin_constant_p((p)) ? __inlc(p) : __inl(p)) -#define outb(v,p) (__builtin_constant_p((p)) ? __outbc(v,p) : __outb(v,p)) -#define outw(v,p) (__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p)) -#define outl(v,p) (__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p)) - -/* the following macro is deprecated */ -#define ioaddr(port) ((unsigned long)__ioaddr((port))) - -#define insb(p,d,l) __raw_readsb(__ioaddr(p),d,l) -#define insw(p,d,l) __raw_readsw(__ioaddr(p),d,l) - -#define outsb(p,d,l) __raw_writesb(__ioaddr(p),d,l) -#define outsw(p,d,l) __raw_writesw(__ioaddr(p),d,l) +#define __io(a) (PCIO_BASE + ((a) << 2)) /* * 1:1 mapping for ioremapped regions. diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c index 580b3c73d2c7..1e0e60d04622 100644 --- a/arch/arm/mach-rpc/riscpc.c +++ b/arch/arm/mach-rpc/riscpc.c @@ -74,7 +74,7 @@ static struct map_desc rpc_io_desc[] __initdata = { .length = IO_SIZE , .type = MT_DEVICE }, { /* EASI space */ - .virtual = EASI_BASE, + .virtual = (unsigned long)EASI_BASE, .pfn = __phys_to_pfn(EASI_START), .length = EASI_SIZE, .type = MT_DEVICE diff --git a/arch/arm/mach-s3c2410/Makefile.boot b/arch/arm/mach-s3c2410/Makefile.boot index 58c1dd7f8e1d..4457605ba04a 100644 --- a/arch/arm/mach-s3c2410/Makefile.boot +++ b/arch/arm/mach-s3c2410/Makefile.boot @@ -1,7 +1,7 @@ ifeq ($(CONFIG_PM_H1940),y) - zreladdr-y := 0x30108000 + zreladdr-y += 0x30108000 params_phys-y := 0x30100100 else - zreladdr-y := 0x30008000 + zreladdr-y += 0x30008000 params_phys-y := 0x30000100 endif diff --git a/arch/arm/mach-s3c2410/include/mach/io.h b/arch/arm/mach-s3c2410/include/mach/io.h index 9813dbf2ae4f..118749f37c4c 100644 --- a/arch/arm/mach-s3c2410/include/mach/io.h +++ b/arch/arm/mach-s3c2410/include/mach/io.h @@ -199,8 +199,6 @@ DECLARE_IO(int,l,"") #define outw(v,p) (__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p)) #define outl(v,p) (__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p)) #define __ioaddr(p) (__builtin_constant_p((p)) ? __ioaddr(p) : __ioaddrc(p)) -/* the following macro is deprecated */ -#define ioaddr(port) __ioaddr((port)) #define insb(p,d,l) __raw_readsb(__ioaddr(p),d,l) #define insw(p,d,l) __raw_readsw(__ioaddr(p),d,l) diff --git a/arch/arm/mach-s3c2410/s3c2410.c b/arch/arm/mach-s3c2410/s3c2410.c index f1d3bd8f6f17..343a540d86a9 100644 --- a/arch/arm/mach-s3c2410/s3c2410.c +++ b/arch/arm/mach-s3c2410/s3c2410.c @@ -170,7 +170,9 @@ int __init s3c2410_init(void) { printk("S3C2410: Initialising architecture\n"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2410_pm_syscore_ops); +#endif register_syscore_ops(&s3c24xx_irq_syscore_ops); return sysdev_register(&s3c2410_sysdev); diff --git a/arch/arm/mach-s3c2412/mach-smdk2413.c b/arch/arm/mach-s3c2412/mach-smdk2413.c index 834cfb61bcfe..3391713e0c92 100644 --- a/arch/arm/mach-s3c2412/mach-smdk2413.c +++ b/arch/arm/mach-s3c2412/mach-smdk2413.c @@ -92,8 +92,7 @@ static struct platform_device *smdk2413_devices[] __initdata = { &s3c_device_usbgadget, }; -static void __init smdk2413_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, +static void __init smdk2413_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) { if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) { diff --git a/arch/arm/mach-s3c2412/mach-vstms.c b/arch/arm/mach-s3c2412/mach-vstms.c index 83544ebe20ac..b6ed4573553a 100644 --- a/arch/arm/mach-s3c2412/mach-vstms.c +++ b/arch/arm/mach-s3c2412/mach-vstms.c @@ -129,9 +129,8 @@ static struct platform_device *vstms_devices[] __initdata = { &s3c_device_nand, }; -static void __init vstms_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init vstms_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) { mi->nr_banks=1; diff --git a/arch/arm/mach-s3c2412/s3c2412.c b/arch/arm/mach-s3c2412/s3c2412.c index ef0958d3e5c6..57a1e01e4e50 100644 --- a/arch/arm/mach-s3c2412/s3c2412.c +++ b/arch/arm/mach-s3c2412/s3c2412.c @@ -245,7 +245,9 @@ int __init s3c2412_init(void) { printk("S3C2412: Initialising architecture\n"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2412_pm_syscore_ops); +#endif register_syscore_ops(&s3c24xx_irq_syscore_ops); return sysdev_register(&s3c2412_sysdev); diff --git a/arch/arm/mach-s3c2416/s3c2416.c b/arch/arm/mach-s3c2416/s3c2416.c index 494ce913dc95..20b3fdfb3051 100644 --- a/arch/arm/mach-s3c2416/s3c2416.c +++ b/arch/arm/mach-s3c2416/s3c2416.c @@ -97,7 +97,9 @@ int __init s3c2416_init(void) s3c_fb_setname("s3c2443-fb"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2416_pm_syscore_ops); +#endif register_syscore_ops(&s3c24xx_irq_syscore_ops); return sysdev_register(&s3c2416_sysdev); diff --git a/arch/arm/mach-s3c2440/s3c2440.c b/arch/arm/mach-s3c2440/s3c2440.c index ce99ff72838d..2270d3360216 100644 --- a/arch/arm/mach-s3c2440/s3c2440.c +++ b/arch/arm/mach-s3c2440/s3c2440.c @@ -55,7 +55,9 @@ int __init s3c2440_init(void) /* register suspend/resume handlers */ +#ifdef CONFIG_PM register_syscore_ops(&s3c2410_pm_syscore_ops); +#endif register_syscore_ops(&s3c244x_pm_syscore_ops); register_syscore_ops(&s3c24xx_irq_syscore_ops); diff --git a/arch/arm/mach-s3c2440/s3c2442.c b/arch/arm/mach-s3c2440/s3c2442.c index 9ad99f8016a1..6f2b65e6e068 100644 --- a/arch/arm/mach-s3c2440/s3c2442.c +++ b/arch/arm/mach-s3c2440/s3c2442.c @@ -169,7 +169,9 @@ int __init s3c2442_init(void) { printk("S3C2442: Initialising architecture\n"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2410_pm_syscore_ops); +#endif register_syscore_ops(&s3c244x_pm_syscore_ops); register_syscore_ops(&s3c24xx_irq_syscore_ops); diff --git a/arch/arm/mach-s3c64xx/Makefile.boot b/arch/arm/mach-s3c64xx/Makefile.boot index ba41fdc0a586..c642333af3ed 100644 --- a/arch/arm/mach-s3c64xx/Makefile.boot +++ b/arch/arm/mach-s3c64xx/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x50008000 + zreladdr-y += 0x50008000 params_phys-y := 0x50000100 diff --git a/arch/arm/mach-s5p64x0/Makefile.boot b/arch/arm/mach-s5p64x0/Makefile.boot index ff90aa13bd67..79ece4055b02 100644 --- a/arch/arm/mach-s5p64x0/Makefile.boot +++ b/arch/arm/mach-s5p64x0/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 diff --git a/arch/arm/mach-s5pc100/Makefile.boot b/arch/arm/mach-s5pc100/Makefile.boot index ff90aa13bd67..79ece4055b02 100644 --- a/arch/arm/mach-s5pc100/Makefile.boot +++ b/arch/arm/mach-s5pc100/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 diff --git a/arch/arm/mach-s5pv210/Makefile.boot b/arch/arm/mach-s5pv210/Makefile.boot index ff90aa13bd67..79ece4055b02 100644 --- a/arch/arm/mach-s5pv210/Makefile.boot +++ b/arch/arm/mach-s5pv210/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 diff --git a/arch/arm/mach-sa1100/Makefile b/arch/arm/mach-sa1100/Makefile index 41252d22e659..00631787e80a 100644 --- a/arch/arm/mach-sa1100/Makefile +++ b/arch/arm/mach-sa1100/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_SA1100_PLEB) += pleb.o obj-$(CONFIG_SA1100_SHANNON) += shannon.o obj-$(CONFIG_SA1100_SIMPAD) += simpad.o -led-$(CONFIG_SA1100_SIMPAD) += leds-simpad.o # LEDs support obj-$(CONFIG_LEDS) += $(led-y) diff --git a/arch/arm/mach-sa1100/Makefile.boot b/arch/arm/mach-sa1100/Makefile.boot index a56ad0417cf2..5a616f6e5612 100644 --- a/arch/arm/mach-sa1100/Makefile.boot +++ b/arch/arm/mach-sa1100/Makefile.boot @@ -1,6 +1,7 @@ - zreladdr-y := 0xc0008000 ifeq ($(CONFIG_ARCH_SA1100),y) - zreladdr-$(CONFIG_SA1111) := 0xc0208000 + zreladdr-$(CONFIG_SA1111) += 0xc0208000 +else + zreladdr-y += 0xc0008000 endif params_phys-y := 0xc0000100 initrd_phys-y := 0xc0800000 diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index 26257df19b63..6290ce28b883 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -301,8 +301,7 @@ static void __init get_assabet_scr(void) } static void __init -fixup_assabet(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_assabet(struct tag *tags, char **cmdline, struct meminfo *mi) { /* This must be done before any call to machine_has_neponset() */ map_sa1100_gpio_regs(); diff --git a/arch/arm/mach-sa1100/include/mach/io.h b/arch/arm/mach-sa1100/include/mach/io.h index d8b43f3dcd2d..dfc27ff08344 100644 --- a/arch/arm/mach-sa1100/include/mach/io.h +++ b/arch/arm/mach-sa1100/include/mach/io.h @@ -10,11 +10,9 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffffffff - /* - * We don't actually have real ISA nor PCI buses, but there is so many - * drivers out there that might just work if we fake them... + * __io() is required to be an equivalent mapping to __mem_pci() for + * SOC_COMMON to work. */ #define __io(a) __typesafe_io(a) #define __mem_pci(a) (a) diff --git a/arch/arm/mach-sa1100/include/mach/simpad.h b/arch/arm/mach-sa1100/include/mach/simpad.h index 9296c4513ce1..db28118103eb 100644 --- a/arch/arm/mach-sa1100/include/mach/simpad.h +++ b/arch/arm/mach-sa1100/include/mach/simpad.h @@ -48,32 +48,80 @@ #define GPIO_SMART_CARD GPIO_GPIO10 #define IRQ_GPIO_SMARD_CARD IRQ_GPIO10 -// CS3 Latch is write only, a shadow is necessary +/*--- ucb1x00 GPIO ---*/ +#define SIMPAD_UCB1X00_GPIO_BASE (GPIO_MAX + 1) +#define SIMPAD_UCB1X00_GPIO_PROG1 (SIMPAD_UCB1X00_GPIO_BASE) +#define SIMPAD_UCB1X00_GPIO_PROG2 (SIMPAD_UCB1X00_GPIO_BASE + 1) +#define SIMPAD_UCB1X00_GPIO_UP (SIMPAD_UCB1X00_GPIO_BASE + 2) +#define SIMPAD_UCB1X00_GPIO_DOWN (SIMPAD_UCB1X00_GPIO_BASE + 3) +#define SIMPAD_UCB1X00_GPIO_LEFT (SIMPAD_UCB1X00_GPIO_BASE + 4) +#define SIMPAD_UCB1X00_GPIO_RIGHT (SIMPAD_UCB1X00_GPIO_BASE + 5) +#define SIMPAD_UCB1X00_GPIO_6 (SIMPAD_UCB1X00_GPIO_BASE + 6) +#define SIMPAD_UCB1X00_GPIO_7 (SIMPAD_UCB1X00_GPIO_BASE + 7) +#define SIMPAD_UCB1X00_GPIO_HEADSET (SIMPAD_UCB1X00_GPIO_BASE + 8) +#define SIMPAD_UCB1X00_GPIO_SPEAKER (SIMPAD_UCB1X00_GPIO_BASE + 9) + +/*--- CS3 Latch ---*/ +#define SIMPAD_CS3_GPIO_BASE (GPIO_MAX + 11) +#define SIMPAD_CS3_VCC_5V_EN (SIMPAD_CS3_GPIO_BASE) +#define SIMPAD_CS3_VCC_3V_EN (SIMPAD_CS3_GPIO_BASE + 1) +#define SIMPAD_CS3_EN1 (SIMPAD_CS3_GPIO_BASE + 2) +#define SIMPAD_CS3_EN0 (SIMPAD_CS3_GPIO_BASE + 3) +#define SIMPAD_CS3_DISPLAY_ON (SIMPAD_CS3_GPIO_BASE + 4) +#define SIMPAD_CS3_PCMCIA_BUFF_DIS (SIMPAD_CS3_GPIO_BASE + 5) +#define SIMPAD_CS3_MQ_RESET (SIMPAD_CS3_GPIO_BASE + 6) +#define SIMPAD_CS3_PCMCIA_RESET (SIMPAD_CS3_GPIO_BASE + 7) +#define SIMPAD_CS3_DECT_POWER_ON (SIMPAD_CS3_GPIO_BASE + 8) +#define SIMPAD_CS3_IRDA_SD (SIMPAD_CS3_GPIO_BASE + 9) +#define SIMPAD_CS3_RS232_ON (SIMPAD_CS3_GPIO_BASE + 10) +#define SIMPAD_CS3_SD_MEDIAQ (SIMPAD_CS3_GPIO_BASE + 11) +#define SIMPAD_CS3_LED2_ON (SIMPAD_CS3_GPIO_BASE + 12) +#define SIMPAD_CS3_IRDA_MODE (SIMPAD_CS3_GPIO_BASE + 13) +#define SIMPAD_CS3_ENABLE_5V (SIMPAD_CS3_GPIO_BASE + 14) +#define SIMPAD_CS3_RESET_SIMCARD (SIMPAD_CS3_GPIO_BASE + 15) + +#define SIMPAD_CS3_PCMCIA_BVD1 (SIMPAD_CS3_GPIO_BASE + 16) +#define SIMPAD_CS3_PCMCIA_BVD2 (SIMPAD_CS3_GPIO_BASE + 17) +#define SIMPAD_CS3_PCMCIA_VS1 (SIMPAD_CS3_GPIO_BASE + 18) +#define SIMPAD_CS3_PCMCIA_VS2 (SIMPAD_CS3_GPIO_BASE + 19) +#define SIMPAD_CS3_LOCK_IND (SIMPAD_CS3_GPIO_BASE + 20) +#define SIMPAD_CS3_CHARGING_STATE (SIMPAD_CS3_GPIO_BASE + 21) +#define SIMPAD_CS3_PCMCIA_SHORT (SIMPAD_CS3_GPIO_BASE + 22) +#define SIMPAD_CS3_GPIO_23 (SIMPAD_CS3_GPIO_BASE + 23) -#define CS3BUSTYPE unsigned volatile long #define CS3_BASE 0xf1000000 -#define VCC_5V_EN 0x0001 // For 5V PCMCIA -#define VCC_3V_EN 0x0002 // FOR 3.3V PCMCIA -#define EN1 0x0004 // This is only for EPROM's -#define EN0 0x0008 // Both should be enable for 3.3V or 5V -#define DISPLAY_ON 0x0010 -#define PCMCIA_BUFF_DIS 0x0020 -#define MQ_RESET 0x0040 -#define PCMCIA_RESET 0x0080 -#define DECT_POWER_ON 0x0100 -#define IRDA_SD 0x0200 // Shutdown for powersave -#define RS232_ON 0x0400 -#define SD_MEDIAQ 0x0800 // Shutdown for powersave -#define LED2_ON 0x1000 -#define IRDA_MODE 0x2000 // Fast/Slow IrDA mode -#define ENABLE_5V 0x4000 // Enable 5V circuit -#define RESET_SIMCARD 0x8000 - -#define RS232_ENABLE 0x0440 -#define PCMCIAMASK 0x402f - - +long simpad_get_cs3_ro(void); +long simpad_get_cs3_shadow(void); +void simpad_set_cs3_bit(int value); +void simpad_clear_cs3_bit(int value); + +#define VCC_5V_EN 0x0001 /* For 5V PCMCIA */ +#define VCC_3V_EN 0x0002 /* FOR 3.3V PCMCIA */ +#define EN1 0x0004 /* This is only for EPROM's */ +#define EN0 0x0008 /* Both should be enable for 3.3V or 5V */ +#define DISPLAY_ON 0x0010 +#define PCMCIA_BUFF_DIS 0x0020 +#define MQ_RESET 0x0040 +#define PCMCIA_RESET 0x0080 +#define DECT_POWER_ON 0x0100 +#define IRDA_SD 0x0200 /* Shutdown for powersave */ +#define RS232_ON 0x0400 +#define SD_MEDIAQ 0x0800 /* Shutdown for powersave */ +#define LED2_ON 0x1000 +#define IRDA_MODE 0x2000 /* Fast/Slow IrDA mode */ +#define ENABLE_5V 0x4000 /* Enable 5V circuit */ +#define RESET_SIMCARD 0x8000 + +#define PCMCIA_BVD1 0x01 +#define PCMCIA_BVD2 0x02 +#define PCMCIA_VS1 0x04 +#define PCMCIA_VS2 0x08 +#define LOCK_IND 0x10 +#define CHARGING_STATE 0x20 +#define PCMCIA_SHORT 0x40 + +/*--- Battery ---*/ struct simpad_battery { unsigned char ac_status; /* line connected yes/no */ unsigned char status; /* battery loading yes/no */ diff --git a/arch/arm/mach-sa1100/leds-simpad.c b/arch/arm/mach-sa1100/leds-simpad.c deleted file mode 100644 index d50f4eeaa12e..000000000000 --- a/arch/arm/mach-sa1100/leds-simpad.c +++ /dev/null @@ -1,100 +0,0 @@ -/* - * linux/arch/arm/mach-sa1100/leds-simpad.c - * - * Author: Juergen Messerer <juergen.messerer@siemens.ch> - */ -#include <linux/init.h> - -#include <mach/hardware.h> -#include <asm/leds.h> -#include <asm/system.h> -#include <mach/simpad.h> - -#include "leds.h" - - -#define LED_STATE_ENABLED 1 -#define LED_STATE_CLAIMED 2 - -static unsigned int led_state; -static unsigned int hw_led_state; - -#define LED_GREEN (1) -#define LED_MASK (1) - -extern void set_cs3_bit(int value); -extern void clear_cs3_bit(int value); - -void simpad_leds_event(led_event_t evt) -{ - switch (evt) - { - case led_start: - hw_led_state = LED_GREEN; - led_state = LED_STATE_ENABLED; - break; - - case led_stop: - led_state &= ~LED_STATE_ENABLED; - break; - - case led_claim: - led_state |= LED_STATE_CLAIMED; - hw_led_state = LED_GREEN; - break; - - case led_release: - led_state &= ~LED_STATE_CLAIMED; - hw_led_state = LED_GREEN; - break; - -#ifdef CONFIG_LEDS_TIMER - case led_timer: - if (!(led_state & LED_STATE_CLAIMED)) - hw_led_state ^= LED_GREEN; - break; -#endif - -#ifdef CONFIG_LEDS_CPU - case led_idle_start: - break; - - case led_idle_end: - break; -#endif - - case led_halted: - break; - - case led_green_on: - if (led_state & LED_STATE_CLAIMED) - hw_led_state |= LED_GREEN; - break; - - case led_green_off: - if (led_state & LED_STATE_CLAIMED) - hw_led_state &= ~LED_GREEN; - break; - - case led_amber_on: - break; - - case led_amber_off: - break; - - case led_red_on: - break; - - case led_red_off: - break; - - default: - break; - } - - if (led_state & LED_STATE_ENABLED) - set_cs3_bit(LED2_ON); - else - clear_cs3_bit(LED2_ON); -} - diff --git a/arch/arm/mach-sa1100/leds.c b/arch/arm/mach-sa1100/leds.c index bbfe197fb4d6..5fe71a0f1053 100644 --- a/arch/arm/mach-sa1100/leds.c +++ b/arch/arm/mach-sa1100/leds.c @@ -42,8 +42,6 @@ sa1100_leds_init(void) leds_event = adsbitsy_leds_event; if (machine_is_pt_system3()) leds_event = system3_leds_event; - if (machine_is_simpad()) - leds_event = simpad_leds_event; /* what about machine registry? including led, apm... -zecke */ leds_event(led_start); return 0; diff --git a/arch/arm/mach-sa1100/leds.h b/arch/arm/mach-sa1100/leds.h index 68cc9f773d6d..776b6020f550 100644 --- a/arch/arm/mach-sa1100/leds.h +++ b/arch/arm/mach-sa1100/leds.h @@ -11,4 +11,3 @@ extern void pfs168_leds_event(led_event_t evt); extern void graphicsmaster_leds_event(led_event_t evt); extern void adsbitsy_leds_event(led_event_t evt); extern void system3_leds_event(led_event_t evt); -extern void simpad_leds_event(led_event_t evt); diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c index cfb76077bd25..34659f354bef 100644 --- a/arch/arm/mach-sa1100/simpad.c +++ b/arch/arm/mach-sa1100/simpad.c @@ -13,6 +13,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/io.h> +#include <linux/gpio.h> #include <asm/irq.h> #include <mach/hardware.h> @@ -28,35 +29,92 @@ #include <linux/serial_core.h> #include <linux/ioport.h> +#include <linux/input.h> +#include <linux/gpio_keys.h> +#include <linux/leds.h> +#include <linux/i2c-gpio.h> #include "generic.h" -long cs3_shadow; +/* + * CS3 support + */ -long get_cs3_shadow(void) +static long cs3_shadow; +static spinlock_t cs3_lock; +static struct gpio_chip cs3_gpio; + +long simpad_get_cs3_ro(void) +{ + return readl(CS3_BASE); +} +EXPORT_SYMBOL(simpad_get_cs3_ro); + +long simpad_get_cs3_shadow(void) { return cs3_shadow; } +EXPORT_SYMBOL(simpad_get_cs3_shadow); -void set_cs3(long value) +static void __simpad_write_cs3(void) { - *(CS3BUSTYPE *)(CS3_BASE) = cs3_shadow = value; + writel(cs3_shadow, CS3_BASE); } -void set_cs3_bit(int value) +void simpad_set_cs3_bit(int value) { + unsigned long flags; + + spin_lock_irqsave(&cs3_lock, flags); cs3_shadow |= value; - *(CS3BUSTYPE *)(CS3_BASE) = cs3_shadow; + __simpad_write_cs3(); + spin_unlock_irqrestore(&cs3_lock, flags); } +EXPORT_SYMBOL(simpad_set_cs3_bit); -void clear_cs3_bit(int value) +void simpad_clear_cs3_bit(int value) { + unsigned long flags; + + spin_lock_irqsave(&cs3_lock, flags); cs3_shadow &= ~value; - *(CS3BUSTYPE *)(CS3_BASE) = cs3_shadow; + __simpad_write_cs3(); + spin_unlock_irqrestore(&cs3_lock, flags); } +EXPORT_SYMBOL(simpad_clear_cs3_bit); + +static void cs3_gpio_set(struct gpio_chip *chip, unsigned offset, int value) +{ + if (offset > 15) + return; + if (value) + simpad_set_cs3_bit(1 << offset); + else + simpad_clear_cs3_bit(1 << offset); +}; + +static int cs3_gpio_get(struct gpio_chip *chip, unsigned offset) +{ + if (offset > 15) + return simpad_get_cs3_ro() & (1 << (offset - 16)); + return simpad_get_cs3_shadow() & (1 << offset); +}; -EXPORT_SYMBOL(set_cs3_bit); -EXPORT_SYMBOL(clear_cs3_bit); +static int cs3_gpio_direction_input(struct gpio_chip *chip, unsigned offset) +{ + if (offset > 15) + return 0; + return -EINVAL; +}; + +static int cs3_gpio_direction_output(struct gpio_chip *chip, unsigned offset, + int value) +{ + if (offset > 15) + return -EINVAL; + cs3_gpio_set(chip, offset, value); + return 0; +}; static struct map_desc simpad_io_desc[] __initdata = { { /* MQ200 */ @@ -64,9 +122,9 @@ static struct map_desc simpad_io_desc[] __initdata = { .pfn = __phys_to_pfn(0x4b800000), .length = 0x00800000, .type = MT_DEVICE - }, { /* Paules CS3, write only */ - .virtual = 0xf1000000, - .pfn = __phys_to_pfn(0x18000000), + }, { /* Simpad CS3 */ + .virtual = CS3_BASE, + .pfn = __phys_to_pfn(SA1100_CS3_PHYS), .length = 0x00100000, .type = MT_DEVICE }, @@ -78,12 +136,12 @@ static void simpad_uart_pm(struct uart_port *port, u_int state, u_int oldstate) if (port->mapbase == (u_int)&Ser1UTCR0) { if (state) { - clear_cs3_bit(RS232_ON); - clear_cs3_bit(DECT_POWER_ON); + simpad_clear_cs3_bit(RS232_ON); + simpad_clear_cs3_bit(DECT_POWER_ON); }else { - set_cs3_bit(RS232_ON); - set_cs3_bit(DECT_POWER_ON); + simpad_set_cs3_bit(RS232_ON); + simpad_set_cs3_bit(DECT_POWER_ON); } } } @@ -132,6 +190,7 @@ static struct resource simpad_flash_resources [] = { static struct mcp_plat_data simpad_mcp_data = { .mccr0 = MCCR0_ADM, .sclk_rate = 11981000, + .gpio_base = SIMPAD_UCB1X00_GPIO_BASE, }; @@ -142,9 +201,10 @@ static void __init simpad_map_io(void) iotable_init(simpad_io_desc, ARRAY_SIZE(simpad_io_desc)); - set_cs3_bit (EN1 | EN0 | LED2_ON | DISPLAY_ON | RS232_ON | - ENABLE_5V | RESET_SIMCARD | DECT_POWER_ON); - + /* Initialize CS3 */ + cs3_shadow = (EN1 | EN0 | LED2_ON | DISPLAY_ON | + RS232_ON | ENABLE_5V | RESET_SIMCARD | DECT_POWER_ON); + __simpad_write_cs3(); /* Spinlocks not yet initialized */ sa1100_register_uart_fns(&simpad_port_fns); sa1100_register_uart(0, 3); /* serial interface */ @@ -170,13 +230,14 @@ static void __init simpad_map_io(void) static void simpad_power_off(void) { - local_irq_disable(); // was cli - set_cs3(0x800); /* only SD_MEDIAQ */ + local_irq_disable(); + cs3_shadow = SD_MEDIAQ; + __simpad_write_cs3(); /* Bypass spinlock here */ /* disable internal oscillator, float CS lines */ PCFR = (PCFR_OPDE | PCFR_FP | PCFR_FS); - /* enable wake-up on GPIO0 (Assabet...) */ - PWER = GFER = GRER = 1; + /* enable wake-up on GPIO0 */ + PWER = GFER = GRER = PWER_GPIO0; /* * set scratchpad to zero, just in case it is used as a * restart address by the bootloader. @@ -192,6 +253,91 @@ static void simpad_power_off(void) } +/* + * gpio_keys +*/ + +static struct gpio_keys_button simpad_button_table[] = { + { KEY_POWER, IRQ_GPIO_POWER_BUTTON, 1, "power button" }, +}; + +static struct gpio_keys_platform_data simpad_keys_data = { + .buttons = simpad_button_table, + .nbuttons = ARRAY_SIZE(simpad_button_table), +}; + +static struct platform_device simpad_keys = { + .name = "gpio-keys", + .dev = { + .platform_data = &simpad_keys_data, + }, +}; + +static struct gpio_keys_button simpad_polled_button_table[] = { + { KEY_PROG1, SIMPAD_UCB1X00_GPIO_PROG1, 1, "prog1 button" }, + { KEY_PROG2, SIMPAD_UCB1X00_GPIO_PROG2, 1, "prog2 button" }, + { KEY_UP, SIMPAD_UCB1X00_GPIO_UP, 1, "up button" }, + { KEY_DOWN, SIMPAD_UCB1X00_GPIO_DOWN, 1, "down button" }, + { KEY_LEFT, SIMPAD_UCB1X00_GPIO_LEFT, 1, "left button" }, + { KEY_RIGHT, SIMPAD_UCB1X00_GPIO_RIGHT, 1, "right button" }, +}; + +static struct gpio_keys_platform_data simpad_polled_keys_data = { + .buttons = simpad_polled_button_table, + .nbuttons = ARRAY_SIZE(simpad_polled_button_table), + .poll_interval = 50, +}; + +static struct platform_device simpad_polled_keys = { + .name = "gpio-keys-polled", + .dev = { + .platform_data = &simpad_polled_keys_data, + }, +}; + +/* + * GPIO LEDs + */ + +static struct gpio_led simpad_leds[] = { + { + .name = "simpad:power", + .gpio = SIMPAD_CS3_LED2_ON, + .active_low = 0, + .default_trigger = "default-on", + }, +}; + +static struct gpio_led_platform_data simpad_led_data = { + .num_leds = ARRAY_SIZE(simpad_leds), + .leds = simpad_leds, +}; + +static struct platform_device simpad_gpio_leds = { + .name = "leds-gpio", + .id = 0, + .dev = { + .platform_data = &simpad_led_data, + }, +}; + +/* + * i2c + */ +static struct i2c_gpio_platform_data simpad_i2c_data = { + .sda_pin = GPIO_GPIO21, + .scl_pin = GPIO_GPIO25, + .udelay = 10, + .timeout = HZ, +}; + +static struct platform_device simpad_i2c = { + .name = "i2c-gpio", + .id = 0, + .dev = { + .platform_data = &simpad_i2c_data, + }, +}; /* * MediaQ Video Device @@ -202,7 +348,11 @@ static struct platform_device simpad_mq200fb = { }; static struct platform_device *devices[] __initdata = { - &simpad_mq200fb + &simpad_keys, + &simpad_polled_keys, + &simpad_mq200fb, + &simpad_gpio_leds, + &simpad_i2c, }; @@ -211,6 +361,19 @@ static int __init simpad_init(void) { int ret; + spin_lock_init(&cs3_lock); + + cs3_gpio.label = "simpad_cs3"; + cs3_gpio.base = SIMPAD_CS3_GPIO_BASE; + cs3_gpio.ngpio = 24; + cs3_gpio.set = cs3_gpio_set; + cs3_gpio.get = cs3_gpio_get; + cs3_gpio.direction_input = cs3_gpio_direction_input; + cs3_gpio.direction_output = cs3_gpio_direction_output; + ret = gpiochip_add(&cs3_gpio); + if (ret) + printk(KERN_WARNING "simpad: Unable to register cs3 GPIO device"); + pm_power_off = simpad_power_off; sa11x0_register_mtd(&simpad_flash_data, simpad_flash_resources, diff --git a/arch/arm/mach-shark/Makefile.boot b/arch/arm/mach-shark/Makefile.boot index 4320f8b92771..e40e24e4ca34 100644 --- a/arch/arm/mach-shark/Makefile.boot +++ b/arch/arm/mach-shark/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x08008000 + zreladdr-y += 0x08008000 diff --git a/arch/arm/mach-shmobile/Makefile.boot b/arch/arm/mach-shmobile/Makefile.boot index 1c08ee9de86a..498efd99338d 100644 --- a/arch/arm/mach-shmobile/Makefile.boot +++ b/arch/arm/mach-shmobile/Makefile.boot @@ -1,7 +1,7 @@ __ZRELADDR := $(shell /bin/bash -c 'printf "0x%08x" \ $$[$(CONFIG_MEMORY_START) + 0x8000]') - zreladdr-y := $(__ZRELADDR) + zreladdr-y += $(__ZRELADDR) # Unsupported legacy stuff # diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index 66f980625a33..e4e485fa2532 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -56,6 +56,12 @@ void __init smp_init_cpus(void) unsigned int ncores = shmobile_smp_get_core_count(); unsigned int i; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; i++) set_cpu_possible(i, true); diff --git a/arch/arm/mach-spear3xx/Makefile.boot b/arch/arm/mach-spear3xx/Makefile.boot index 7a1f3c0eadb8..4674a4c221db 100644 --- a/arch/arm/mach-spear3xx/Makefile.boot +++ b/arch/arm/mach-spear3xx/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-spear6xx/Makefile.boot b/arch/arm/mach-spear6xx/Makefile.boot index 7a1f3c0eadb8..4674a4c221db 100644 --- a/arch/arm/mach-spear6xx/Makefile.boot +++ b/arch/arm/mach-spear6xx/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-tcc8k/Makefile.boot b/arch/arm/mach-tcc8k/Makefile.boot index f135c9deae10..5e02d4156b04 100644 --- a/arch/arm/mach-tcc8k/Makefile.boot +++ b/arch/arm/mach-tcc8k/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 initrd_phys-y := 0x20800000 diff --git a/arch/arm/mach-tegra/Makefile.boot b/arch/arm/mach-tegra/Makefile.boot index 428ad122be03..5e870d29eca1 100644 --- a/arch/arm/mach-tegra/Makefile.boot +++ b/arch/arm/mach-tegra/Makefile.boot @@ -1,4 +1,4 @@ -zreladdr-$(CONFIG_ARCH_TEGRA_2x_SOC) := 0x00008000 +zreladdr-$(CONFIG_ARCH_TEGRA_2x_SOC) += 0x00008000 params_phys-$(CONFIG_ARCH_TEGRA_2x_SOC) := 0x00000100 initrd_phys-$(CONFIG_ARCH_TEGRA_2x_SOC) := 0x00800000 diff --git a/arch/arm/mach-tegra/board-harmony.c b/arch/arm/mach-tegra/board-harmony.c index 846cd7d69e3e..c78ce41cca16 100644 --- a/arch/arm/mach-tegra/board-harmony.c +++ b/arch/arm/mach-tegra/board-harmony.c @@ -123,8 +123,8 @@ static struct platform_device *harmony_devices[] __initdata = { &harmony_audio_device, }; -static void __init tegra_harmony_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init tegra_harmony_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-tegra/board-paz00.c b/arch/arm/mach-tegra/board-paz00.c index ea2f79c9879b..5e6bc7719642 100644 --- a/arch/arm/mach-tegra/board-paz00.c +++ b/arch/arm/mach-tegra/board-paz00.c @@ -84,8 +84,8 @@ static void paz00_usb_init(void) platform_device_register(&tegra_ehci3_device); } -static void __init tegra_paz00_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init tegra_paz00_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 1; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-tegra/board-trimslice.c b/arch/arm/mach-tegra/board-trimslice.c index 89a6d2adc1de..652c3404d0e2 100644 --- a/arch/arm/mach-tegra/board-trimslice.c +++ b/arch/arm/mach-tegra/board-trimslice.c @@ -126,8 +126,8 @@ static void trimslice_usb_init(void) platform_device_register(&tegra_ehci1_device); } -static void __init tegra_trimslice_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init tegra_trimslice_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 0886cbccddee..7d2b5d03c1df 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -114,10 +114,10 @@ void __init smp_init_cpus(void) { unsigned int i, ncores = scu_get_core_count(scu_base); - if (ncores > NR_CPUS) { - printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-u300/Makefile.boot b/arch/arm/mach-u300/Makefile.boot index 6fbfc6ea2d35..69357affbd77 100644 --- a/arch/arm/mach-u300/Makefile.boot +++ b/arch/arm/mach-u300/Makefile.boot @@ -4,10 +4,10 @@ # INITRD_PHYS must be in RAM ifdef CONFIG_MACH_U300_SINGLE_RAM - zreladdr-y := 0x28E08000 + zreladdr-y += 0x28E08000 params_phys-y := 0x28E00100 else - zreladdr-y := 0x48008000 + zreladdr-y += 0x48008000 params_phys-y := 0x48000100 endif diff --git a/arch/arm/mach-ux500/Makefile.boot b/arch/arm/mach-ux500/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-ux500/Makefile.boot +++ b/arch/arm/mach-ux500/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index a33df5f4c27a..eb5199102cfa 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -156,12 +156,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "U8500: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-versatile/Makefile.boot b/arch/arm/mach-versatile/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-versatile/Makefile.boot +++ b/arch/arm/mach-versatile/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-vexpress/Makefile.boot b/arch/arm/mach-vexpress/Makefile.boot index 07c2d9c457ec..8630b3d10a4d 100644 --- a/arch/arm/mach-vexpress/Makefile.boot +++ b/arch/arm/mach-vexpress/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x60008000 + zreladdr-y += 0x60008000 params_phys-y := 0x60000100 initrd_phys-y := 0x60800000 diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index bfd32f52c2db..2b1e836a76ed 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -221,6 +221,12 @@ static void ct_ca9x4_init_cpu_map(void) { int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU)); + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; ++i) set_cpu_possible(i, true); diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c index ea4cbfb90a66..3668cf91d2de 100644 --- a/arch/arm/mach-vexpress/hotplug.c +++ b/arch/arm/mach-vexpress/hotplug.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <asm/cacheflush.h> +#include <asm/system.h> extern volatile int pen_release; @@ -62,13 +63,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) * code will have already disabled interrupts */ for (;;) { - /* - * here's the WFI - */ - asm(".word 0xe320f003\n" - : - : - : "memory", "cc"); + wfi(); if (pen_release == cpu) { /* diff --git a/arch/arm/mach-vexpress/include/mach/io.h b/arch/arm/mach-vexpress/include/mach/io.h index 748bb524ee71..13522d86685e 100644 --- a/arch/arm/mach-vexpress/include/mach/io.h +++ b/arch/arm/mach-vexpress/include/mach/io.h @@ -20,8 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffffffff - #define __io(a) __typesafe_io(a) #define __mem_pci(a) (a) diff --git a/arch/arm/mach-vt8500/Makefile.boot b/arch/arm/mach-vt8500/Makefile.boot index a8acc4e24902..b79c41cdfdff 100644 --- a/arch/arm/mach-vt8500/Makefile.boot +++ b/arch/arm/mach-vt8500/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x01000000 diff --git a/arch/arm/mach-vt8500/include/mach/io.h b/arch/arm/mach-vt8500/include/mach/io.h index 9077239f78c9..46181eecf273 100644 --- a/arch/arm/mach-vt8500/include/mach/io.h +++ b/arch/arm/mach-vt8500/include/mach/io.h @@ -20,8 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffff - #define __io(a) __typesafe_io((a) + 0xf0000000) #define __mem_pci(a) (a) diff --git a/arch/arm/mach-w90x900/Makefile.boot b/arch/arm/mach-w90x900/Makefile.boot index a057b546b6e5..6c3d421c2d11 100644 --- a/arch/arm/mach-w90x900/Makefile.boot +++ b/arch/arm/mach-w90x900/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-zynq/Makefile.boot b/arch/arm/mach-zynq/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-zynq/Makefile.boot +++ b/arch/arm/mach-zynq/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index cfbcf8b95599..c335c76e0d88 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -86,16 +86,6 @@ core_param(alignment, ai_usermode, int, 0600); #define UM_FIXUP (1 << 1) #define UM_SIGNAL (1 << 2) -#ifdef CONFIG_PROC_FS -static const char *usermode_action[] = { - "ignored", - "warn", - "fixup", - "fixup+warn", - "signal", - "signal+warn" -}; - /* Return true if and only if the ARMv6 unaligned access model is in use. */ static bool cpu_is_v6_unaligned(void) { @@ -123,6 +113,16 @@ static int safe_usermode(int new_usermode, bool warn) return new_usermode; } +#ifdef CONFIG_PROC_FS +static const char *usermode_action[] = { + "ignored", + "warn", + "fixup", + "fixup+warn", + "signal", + "signal+warn" +}; + static int alignment_proc_show(struct seq_file *m, void *v) { seq_printf(m, "User:\t\t%lu\n", ai_user); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 9ecfdb511951..3f9b9980478e 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,9 +16,12 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/err.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <asm/cacheflush.h> #include <asm/hardware/cache-l2x0.h> @@ -30,11 +33,19 @@ static DEFINE_SPINLOCK(l2x0_lock); static uint32_t l2x0_way_mask; /* Bitmask of active ways */ static uint32_t l2x0_size; +struct l2x0_regs l2x0_saved_regs; + +struct l2x0_of_data { + void (*setup)(const struct device_node *, __u32 *, __u32 *); + void (*save)(void); + void (*resume)(void); +}; + static inline void cache_wait_way(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) - ; + cpu_relax(); } #ifdef CONFIG_CACHE_PL310 @@ -277,7 +288,7 @@ static void l2x0_disable(void) spin_unlock_irqrestore(&l2x0_lock, flags); } -static void __init l2x0_unlock(__u32 cache_id) +static void l2x0_unlock(__u32 cache_id) { int lockregs; int i; @@ -353,6 +364,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + l2x0_saved_regs.aux_ctrl = aux; + l2x0_inv_all(); /* enable L2X0 */ @@ -372,3 +385,202 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n", ways, cache_id, aux, l2x0_size); } + +#ifdef CONFIG_OF +static void __init l2x0_of_setup(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask) +{ + u32 data[2] = { 0, 0 }; + u32 tag = 0; + u32 dirty = 0; + u32 val = 0, mask = 0; + + of_property_read_u32(np, "arm,tag-latency", &tag); + if (tag) { + mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; + val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; + } + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1]) { + mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | + L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; + val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | + ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); + } + + of_property_read_u32(np, "arm,dirty-latency", &dirty); + if (dirty) { + mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; + val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static void __init pl310_of_setup(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask) +{ + u32 data[3] = { 0, 0, 0 }; + u32 tag[3] = { 0, 0, 0 }; + u32 filter[2] = { 0, 0 }; + + of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); + if (tag[0] && tag[1] && tag[2]) + writel_relaxed( + ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | + ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | + ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), + l2x0_base + L2X0_TAG_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1] && data[2]) + writel_relaxed( + ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | + ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | + ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), + l2x0_base + L2X0_DATA_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,filter-ranges", + filter, ARRAY_SIZE(filter)); + if (filter[1]) { + writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), + l2x0_base + L2X0_ADDR_FILTER_END); + writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN, + l2x0_base + L2X0_ADDR_FILTER_START); + } +} + +static void __init pl310_save(void) +{ + u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base + + L2X0_TAG_LATENCY_CTRL); + l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base + + L2X0_DATA_LATENCY_CTRL); + l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base + + L2X0_ADDR_FILTER_END); + l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base + + L2X0_ADDR_FILTER_START); + + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { + /* + * From r2p0, there is Prefetch offset/control register + */ + l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base + + L2X0_PREFETCH_CTRL); + /* + * From r3p0, there is Power control register + */ + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) + l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base + + L2X0_POWER_CTRL); + } +} + +static void l2x0_resume(void) +{ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* restore aux ctrl and enable l2 */ + l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID)); + + writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base + + L2X0_AUX_CTRL); + + l2x0_inv_all(); + + writel_relaxed(1, l2x0_base + L2X0_CTRL); + } +} + +static void pl310_resume(void) +{ + u32 l2x0_revision; + + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* restore pl310 setup */ + writel_relaxed(l2x0_saved_regs.tag_latency, + l2x0_base + L2X0_TAG_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.data_latency, + l2x0_base + L2X0_DATA_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.filter_end, + l2x0_base + L2X0_ADDR_FILTER_END); + writel_relaxed(l2x0_saved_regs.filter_start, + l2x0_base + L2X0_ADDR_FILTER_START); + + l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { + writel_relaxed(l2x0_saved_regs.prefetch_ctrl, + l2x0_base + L2X0_PREFETCH_CTRL); + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) + writel_relaxed(l2x0_saved_regs.pwr_ctrl, + l2x0_base + L2X0_POWER_CTRL); + } + } + + l2x0_resume(); +} + +static const struct l2x0_of_data pl310_data = { + pl310_of_setup, + pl310_save, + pl310_resume, +}; + +static const struct l2x0_of_data l2x0_data = { + l2x0_of_setup, + NULL, + l2x0_resume, +}; + +static const struct of_device_id l2x0_ids[] __initconst = { + { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data }, + { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data }, + { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data }, + {} +}; + +int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask) +{ + struct device_node *np; + struct l2x0_of_data *data; + struct resource res; + + np = of_find_matching_node(NULL, l2x0_ids); + if (!np) + return -ENODEV; + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + l2x0_base = ioremap(res.start, resource_size(&res)); + if (!l2x0_base) + return -ENOMEM; + + l2x0_saved_regs.phy_base = res.start; + + data = of_match_node(l2x0_ids, np)->data; + + /* L2 configuration can only be changed if the cache is disabled */ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + if (data->setup) + data->setup(np, &aux_val, &aux_mask); + } + + if (data->save) + data->save(); + + l2x0_init(l2x0_base, aux_val, aux_mask); + + outer_cache.resume = data->resume; + return 0; +} +#endif diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c3ff82f92d9c..235eb775fc78 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -123,8 +123,8 @@ static void __dma_free_buffer(struct page *page, size_t size) #endif #define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) -#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT) -#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT) +#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PMD_SHIFT) +#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PMD_SHIFT) /* * These are the page tables (2MB each) covering uncached, DMA consistent allocations @@ -183,7 +183,7 @@ static int __init consistent_init(void) } consistent_pte[i++] = pte; - base += (1 << PGDIR_SHIFT); + base += PMD_SIZE; } while (base < CONSISTENT_END); return ret; diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 3b5ea68acbb8..aa33949fef60 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -20,6 +20,7 @@ #include <linux/highmem.h> #include <linux/perf_event.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index cc7e2d8be9aa..f8037ba338ac 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -496,6 +496,13 @@ static void __init free_unused_memmap(struct meminfo *mi) */ bank_start = min(bank_start, ALIGN(prev_bank_end, PAGES_PER_SECTION)); +#else + /* + * Align down here since the VM subsystem insists that the + * memmap entries are valid from the bank start aligned to + * MAX_ORDER_NR_PAGES. + */ + bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES); #endif /* * If we had a previous bank, and there is a space diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index ab506272b2d3..bdb248c4f55c 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -289,6 +289,27 @@ __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype) } EXPORT_SYMBOL(__arm_ioremap); +/* + * Remap an arbitrary physical address space into the kernel virtual + * address space as memory. Needed when the kernel wants to execute + * code in external memory. This is needed for reprogramming source + * clocks that would affect normal memory for example. Please see + * CONFIG_GENERIC_ALLOCATOR for allocating external memory. + */ +void __iomem * +__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached) +{ + unsigned int mtype; + + if (cached) + mtype = MT_MEMORY; + else + mtype = MT_MEMORY_NONCACHED; + + return __arm_ioremap_caller(phys_addr, size, mtype, + __builtin_return_address(0)); +} + void __iounmap(volatile void __iomem *io_addr) { void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 010566799c80..ad7cce3bc431 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; - unsigned int prot_l1; - unsigned int prot_sect; + pmdval_t prot_l1; + pmdval_t prot_sect; unsigned int domain; }; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 594d677b92c8..226f1804be12 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -60,7 +60,7 @@ EXPORT_SYMBOL(pgprot_kernel); struct cachepolicy { const char policy[16]; unsigned int cr_mask; - unsigned int pmd; + pmdval_t pmd; pteval_t pte; }; @@ -288,7 +288,7 @@ static void __init build_mem_type_table(void) { struct cachepolicy *cp; unsigned int cr = get_cr(); - unsigned int user_pgprot, kern_pgprot, vecs_pgprot; + pteval_t user_pgprot, kern_pgprot, vecs_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -863,14 +863,14 @@ static inline void prepare_page_table(void) /* * Clear out all the mappings below the kernel image. */ - for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE) + for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); #ifdef CONFIG_XIP_KERNEL /* The XIP kernel is mapped in the module area -- skip over it */ - addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK; + addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK; #endif - for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE) + for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); /* @@ -885,10 +885,12 @@ static inline void prepare_page_table(void) * memory bank, up to the end of the vmalloc region. */ for (addr = __phys_to_virt(end); - addr < VMALLOC_END; addr += PGDIR_SIZE) + addr < VMALLOC_END; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); } +#define SWAPPER_PG_DIR_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) + /* * Reserve the special regions of memory */ @@ -898,7 +900,7 @@ void __init arm_mm_memblock_reserve(void) * Reserve the page tables. These are already in use, * and can only be in node 0. */ - memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t)); + memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE); #ifdef CONFIG_SA1111 /* @@ -926,7 +928,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) */ vectors_page = early_alloc(PAGE_SIZE); - for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE) + for (addr = VMALLOC_END; addr; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); /* diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 9049c0764db2..9591c8e9fb8c 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -218,7 +218,7 @@ ENDPROC(cpu_v7_set_pte_ext) /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size .equ cpu_v7_suspend_size, 4 * 9 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index bb8f4a6b3e37..5b605a9eb091 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -14,6 +14,7 @@ config ARCH_OMAP1 select CLKDEV_LOOKUP select CLKSRC_MMIO select GENERIC_IRQ_CHIP + select HAVE_IDE help "Systems based on omap7xx, omap15xx or omap16xx" diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c index f88216d23991..c65eb791d1bb 100644 --- a/arch/arm/plat-s5p/irq-gpioint.c +++ b/arch/arm/plat-s5p/irq-gpioint.c @@ -163,9 +163,9 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip) ct->chip.irq_mask = irq_gc_mask_set_bit; ct->chip.irq_unmask = irq_gc_mask_clr_bit; ct->chip.irq_set_type = s5p_gpioint_set_type, - ct->regs.ack = PEND_OFFSET + REG_OFFSET(chip->group); - ct->regs.mask = MASK_OFFSET + REG_OFFSET(chip->group); - ct->regs.type = CON_OFFSET + REG_OFFSET(chip->group); + ct->regs.ack = PEND_OFFSET + REG_OFFSET(group - bank->start); + ct->regs.mask = MASK_OFFSET + REG_OFFSET(group - bank->start); + ct->regs.type = CON_OFFSET + REG_OFFSET(group - bank->start); irq_setup_generic_chip(gc, IRQ_MSK(chip->chip.ngpio), IRQ_GC_INIT_MASK_CACHE, IRQ_NOREQUEST | IRQ_NOPROBE, 0); diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 62cc8f981171..5bdeef969847 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,10 +12,9 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# XXX: This is a cut-down version of the file; it contains only machines that -# XXX: are in mainline or have been submitted to the machine database within -# XXX: the last 12 months. If your entry is missing please email rmk at -# XXX: <linux@arm.linux.org.uk> +# This is a cut-down version of the file; it contains only machines that +# are merged into mainline or have been edited in the machine database +# within the last 12 months. References to machine_is_NAME() do not count! # # Last update: Sat May 7 08:48:24 2011 # @@ -65,6 +64,7 @@ h7201 ARCH_H7201 H7201 161 h7202 ARCH_H7202 H7202 162 iq80321 ARCH_IQ80321 IQ80321 169 ks8695 ARCH_KS8695 KS8695 180 +karo ARCH_KARO KARO 190 smdk2410 ARCH_SMDK2410 SMDK2410 193 ceiva ARCH_CEIVA CEIVA 200 voiceblue MACH_VOICEBLUE VOICEBLUE 218 @@ -188,6 +188,7 @@ omap_2430sdp MACH_OMAP_2430SDP OMAP_2430SDP 900 davinci_evm MACH_DAVINCI_EVM DAVINCI_EVM 901 palmz72 MACH_PALMZ72 PALMZ72 904 nxdb500 MACH_NXDB500 NXDB500 905 +apf9328 MACH_APF9328 APF9328 906 palmt5 MACH_PALMT5 PALMT5 917 palmtc MACH_PALMTC PALMTC 918 omap_apollon MACH_OMAP_APOLLON OMAP_APOLLON 919 @@ -271,10 +272,12 @@ pcm038 MACH_PCM038 PCM038 1551 ts_x09 MACH_TS209 TS209 1565 at91cap9adk MACH_AT91CAP9ADK AT91CAP9ADK 1566 mx31moboard MACH_MX31MOBOARD MX31MOBOARD 1574 +vision_ep9307 MACH_VISION_EP9307 VISION_EP9307 1578 terastation_pro2 MACH_TERASTATION_PRO2 TERASTATION_PRO2 1584 linkstation_pro MACH_LINKSTATION_PRO LINKSTATION_PRO 1585 e350 MACH_E350 E350 1596 ts409 MACH_TS409 TS409 1601 +rsi_ews MACH_RSI_EWS RSI_EWS 1609 cm_x300 MACH_CM_X300 CM_X300 1616 at91sam9g20ek MACH_AT91SAM9G20EK AT91SAM9G20EK 1624 smdk6410 MACH_SMDK6410 SMDK6410 1626 @@ -331,6 +334,7 @@ smdkc100 MACH_SMDKC100 SMDKC100 1826 tavorevb MACH_TAVOREVB TAVOREVB 1827 saar MACH_SAAR SAAR 1828 at91sam9m10g45ek MACH_AT91SAM9M10G45EK AT91SAM9M10G45EK 1830 +usb_a9g20 MACH_USB_A9G20 USB_A9G20 1841 mxlads MACH_MXLADS MXLADS 1851 linkstation_mini MACH_LINKSTATION_MINI LINKSTATION_MINI 1858 afeb9260 MACH_AFEB9260 AFEB9260 1859 @@ -369,6 +373,7 @@ pcm043 MACH_PCM043 PCM043 2072 sheevaplug MACH_SHEEVAPLUG SHEEVAPLUG 2097 avengers_lite MACH_AVENGERS_LITE AVENGERS_LITE 2104 mx51_babbage MACH_MX51_BABBAGE MX51_BABBAGE 2125 +tx37 MACH_TX37 TX37 2127 rd78x00_masa MACH_RD78X00_MASA RD78X00_MASA 2135 dm355_leopard MACH_DM355_LEOPARD DM355_LEOPARD 2138 ts219 MACH_TS219 TS219 2139 @@ -379,6 +384,7 @@ omap_4430sdp MACH_OMAP_4430SDP OMAP_4430SDP 2160 magx_zn5 MACH_MAGX_ZN5 MAGX_ZN5 2162 btmavb101 MACH_BTMAVB101 BTMAVB101 2172 btmawb101 MACH_BTMAWB101 BTMAWB101 2173 +tx25 MACH_TX25 TX25 2177 omap3_torpedo MACH_OMAP3_TORPEDO OMAP3_TORPEDO 2178 anw6410 MACH_ANW6410 ANW6410 2183 imx27_visstrim_m10 MACH_IMX27_VISSTRIM_M10 IMX27_VISSTRIM_M10 2187 @@ -423,6 +429,7 @@ raumfeld_rc MACH_RAUMFELD_RC RAUMFELD_RC 2413 raumfeld_connector MACH_RAUMFELD_CONNECTOR RAUMFELD_CONNECTOR 2414 raumfeld_speaker MACH_RAUMFELD_SPEAKER RAUMFELD_SPEAKER 2415 tnetv107x MACH_TNETV107X TNETV107X 2418 +mx51_m2id MACH_MX51_M2ID MX51_M2ID 2428 smdkv210 MACH_SMDKV210 SMDKV210 2456 omap_zoom3 MACH_OMAP_ZOOM3 OMAP_ZOOM3 2464 omap_3630sdp MACH_OMAP_3630SDP OMAP_3630SDP 2465 @@ -433,14 +440,17 @@ omapl138_hawkboard MACH_OMAPL138_HAWKBOARD OMAPL138_HAWKBOARD 2495 ts41x MACH_TS41X TS41X 2502 phy3250 MACH_PHY3250 PHY3250 2511 mini6410 MACH_MINI6410 MINI6410 2520 +tx51 MACH_TX51 TX51 2529 mx28evk MACH_MX28EVK MX28EVK 2531 smartq5 MACH_SMARTQ5 SMARTQ5 2534 davinci_dm6467tevm MACH_DAVINCI_DM6467TEVM DAVINCI_DM6467TEVM 2548 mxt_td60 MACH_MXT_TD60 MXT_TD60 2550 riot_bei2 MACH_RIOT_BEI2 RIOT_BEI2 2576 riot_x37 MACH_RIOT_X37 RIOT_X37 2578 +pca101 MACH_PCA101 PCA101 2595 capc7117 MACH_CAPC7117 CAPC7117 2612 icontrol MACH_ICONTROL ICONTROL 2624 +gplugd MACH_GPLUGD GPLUGD 2625 qsd8x50a_st1_5 MACH_QSD8X50A_ST1_5 QSD8X50A_ST1_5 2627 mx23evk MACH_MX23EVK MX23EVK 2629 ap4evb MACH_AP4EVB AP4EVB 2630 @@ -1113,3 +1123,5 @@ blissc MACH_BLISSC BLISSC 3491 thales_adc MACH_THALES_ADC THALES_ADC 3492 ubisys_p9d_evp MACH_UBISYS_P9D_EVP UBISYS_P9D_EVP 3493 atdgp318 MACH_ATDGP318 ATDGP318 3494 +smdk4212 MACH_SMDK4212 SMDK4212 3638 +smdk4412 MACH_SMDK4412 SMDK4412 3765 diff --git a/arch/arm/vfp/Makefile b/arch/arm/vfp/Makefile index 6de73aab0195..a81404c09d5d 100644 --- a/arch/arm/vfp/Makefile +++ b/arch/arm/vfp/Makefile @@ -7,7 +7,7 @@ # ccflags-y := -DDEBUG # asflags-y := -DDEBUG -KBUILD_AFLAGS :=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp) +KBUILD_AFLAGS :=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft) LDFLAGS +=--no-warn-mismatch obj-y += vfp.o diff --git a/arch/m68k/kernel/vmlinux.lds_no.S b/arch/m68k/kernel/vmlinux.lds_no.S index 7dc4087a9545..4e2389340837 100644 --- a/arch/m68k/kernel/vmlinux.lds_no.S +++ b/arch/m68k/kernel/vmlinux.lds_no.S @@ -77,7 +77,6 @@ SECTIONS { *(.rodata) *(.rodata.*) *(__vermagic) /* Kernel version magic */ - *(__markers_strings) *(.rodata1) *(.rodata.str1.1) diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c index 900d899f3323..f92190c159b4 100644 --- a/arch/m68k/mac/macints.c +++ b/arch/m68k/mac/macints.c @@ -370,7 +370,7 @@ int mac_irq_pending(unsigned int irq) break; case 4: if (psc_present) - psc_irq_pending(irq); + return psc_irq_pending(irq); break; } return 0; diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index e023fc6b37e5..eb915551de69 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -304,35 +304,41 @@ static void via_write_pram(int offset, __u8 data) static long via_read_time(void) { union { - __u8 cdata[4]; - long idata; + __u8 cdata[4]; + long idata; } result, last_result; - int ct; + int count = 1; + + via_pram_command(0x81, &last_result.cdata[3]); + via_pram_command(0x85, &last_result.cdata[2]); + via_pram_command(0x89, &last_result.cdata[1]); + via_pram_command(0x8D, &last_result.cdata[0]); /* * The NetBSD guys say to loop until you get the same reading * twice in a row. */ - ct = 0; - do { - if (++ct > 10) { - printk("via_read_time: couldn't get valid time, " - "last read = 0x%08lx and 0x%08lx\n", - last_result.idata, result.idata); - break; - } - - last_result.idata = result.idata; - result.idata = 0; - + while (1) { via_pram_command(0x81, &result.cdata[3]); via_pram_command(0x85, &result.cdata[2]); via_pram_command(0x89, &result.cdata[1]); via_pram_command(0x8D, &result.cdata[0]); - } while (result.idata != last_result.idata); - return result.idata - RTC_OFFSET; + if (result.idata == last_result.idata) + return result.idata - RTC_OFFSET; + + if (++count > 10) + break; + + last_result.idata = result.idata; + } + + pr_err("via_read_time: failed to read a stable value; " + "got 0x%08lx then 0x%08lx\n", + last_result.idata, result.idata); + + return 0; } /* diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h index 1407c07bdade..f6ae2b2b6870 100644 --- a/arch/sparc/include/asm/pgtsrmmu.h +++ b/arch/sparc/include/asm/pgtsrmmu.h @@ -280,7 +280,7 @@ static inline unsigned long srmmu_hwprobe(unsigned long vaddr) return retval; } #else -#define srmmu_hwprobe(addr) (srmmu_swprobe(addr, 0) & SRMMU_PTE_PMASK) +#define srmmu_hwprobe(addr) srmmu_swprobe(addr, 0) #endif static inline int diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 1e94f946570e..8aa0d4408586 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -230,7 +230,8 @@ static void pci_parse_of_addrs(struct platform_device *op, res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; } else if (i == dev->rom_base_reg) { res = &dev->resource[PCI_ROM_RESOURCE]; - flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE; + flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE + | IORESOURCE_SIZEALIGN; } else { printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i); continue; diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 1ba95aff5d59..2caa556db86d 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -273,10 +273,7 @@ void do_sigreturn32(struct pt_regs *regs) case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32); } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: @@ -377,10 +374,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) case 1: set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32); } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -782,6 +776,7 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; if (ka->sa.sa_flags & SA_SIGINFO) @@ -792,12 +787,10 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked,signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -881,7 +874,7 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 04ede8f04add..8ce247ac04cc 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -62,12 +62,13 @@ struct rt_signal_frame { static int _sigpause_common(old_sigset_t set) { - set &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, set); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + set &= _BLOCKABLE; + siginitset(&blocked, set); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -139,10 +140,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) goto segv_and_exit; sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv_and_exit: @@ -209,10 +207,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -470,6 +465,7 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; if (ka->sa.sa_flags & SA_SIGINFO) @@ -480,12 +476,10 @@ handle_signal(unsigned long signr, struct k_sigaction *ka, if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked, signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -581,7 +575,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) */ if (test_thread_flag(TIF_RESTORE_SIGMASK)) { clear_thread_flag(TIF_RESTORE_SIGMASK); - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 47509df3b893..a2b81598d905 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -70,10 +70,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) goto do_sigsegv; } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); } if (test_thread_flag(TIF_32BIT)) { pc &= 0xffffffff; @@ -242,12 +239,13 @@ struct rt_signal_frame { static long _sigpause_common(old_sigset_t set) { - set &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, set); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + set &= _BLOCKABLE; + siginitset(&blocked, set); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -327,10 +325,7 @@ void do_rt_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -484,18 +479,17 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; err = setup_rt_frame(ka, regs, signr, oldset, (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked,signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -601,7 +595,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c index e485a6804998..13c2169822a8 100644 --- a/arch/sparc/mm/leon_mm.c +++ b/arch/sparc/mm/leon_mm.c @@ -162,7 +162,7 @@ ready: printk(KERN_INFO "swprobe: padde %x\n", paddr_calc); if (paddr) *paddr = paddr_calc; - return paddrbase; + return pte; } void leon_flush_icache_all(void) diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S index fc94607f0bd5..aecc8ed5f39b 100644 --- a/arch/tile/kernel/intvec_32.S +++ b/arch/tile/kernel/intvec_32.S @@ -21,7 +21,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/irqflags.h> -#include <linux/atomic.h> +#include <asm/atomic_32.h> #include <asm/asm-offsets.h> #include <hv/hypervisor.h> #include <arch/abi.h> diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S index 1f75a2a56101..30638042691d 100644 --- a/arch/tile/lib/atomic_asm_32.S +++ b/arch/tile/lib/atomic_asm_32.S @@ -70,7 +70,7 @@ */ #include <linux/linkage.h> -#include <linux/atomic.h> +#include <asm/atomic_32.h> #include <asm/page.h> #include <asm/processor.h> diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 7ff4669580cf..c34f96c2f7a0 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -12,6 +12,7 @@ #include <asm/pgtable.h> #include <xen/interface/xen.h> +#include <xen/grant_table.h> #include <xen/features.h> /* Xen machine address */ @@ -48,14 +49,11 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e); extern int m2p_add_override(unsigned long mfn, struct page *page, - bool clear_pte); + struct gnttab_map_grant_ref *kmap_op); extern int m2p_remove_override(struct page *page, bool clear_pte); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); -#ifdef CONFIG_XEN_DEBUG_FS -extern int p2m_dump_show(struct seq_file *m, void *v); -#endif static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index f1a6244d7d93..794bc95134cd 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -75,8 +75,10 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); /* * Undefined/reserved opcodes, conditional jump, Opcode Extension * Groups, and some special opcodes can not boost. + * This is non-const to keep gcc from statically optimizing it out, as + * variable_test_bit makes gcc think only *(unsigned long*) is used. */ -static const u32 twobyte_is_boostable[256 / 32] = { +static u32 twobyte_is_boostable[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */ diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 18ae83dd1cd7..b56c65de384d 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -56,7 +56,7 @@ DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), }; -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; +static enum { EMULATE, NATIVE, NONE } vsyscall_mode = NATIVE; static int __init vsyscall_setup(char *str) { diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 30326443ab81..87488b93a65c 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -63,9 +63,8 @@ static void __init find_early_table_space(unsigned long end, int use_pse, #ifdef CONFIG_X86_32 /* for fixmap */ tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); - - good_end = max_pfn_mapped << PAGE_SHIFT; #endif + good_end = max_pfn_mapped << PAGE_SHIFT; base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); if (base == MEMBLOCK_ERROR) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 1017c7bee388..492ade8c978e 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -175,8 +175,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) "pcifront-msi-x" : "pcifront-msi", DOMID_SELF); - if (irq < 0) + if (irq < 0) { + ret = irq; goto free; + } i++; } kfree(v); @@ -221,8 +223,10 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (msg.data != XEN_PIRQ_MSI_DATA || xen_irq_from_pirq(pirq) < 0) { pirq = xen_allocate_pirq_msi(dev, msidesc); - if (pirq < 0) + if (pirq < 0) { + irq = -ENODEV; goto error; + } xen_msi_compose_msg(dev, pirq, &msg); __write_msi_msg(msidesc, &msg); dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); @@ -244,10 +248,12 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) error: dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); - return -ENODEV; + return irq; } #ifdef CONFIG_XEN_DOM0 +static bool __read_mostly pci_seg_supported = true; + static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { int ret = 0; @@ -265,10 +271,11 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) memset(&map_irq, 0, sizeof(map_irq)); map_irq.domid = domid; - map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.type = MAP_PIRQ_TYPE_MSI_SEG; map_irq.index = -1; map_irq.pirq = -1; - map_irq.bus = dev->bus->number; + map_irq.bus = dev->bus->number | + (pci_domain_nr(dev->bus) << 16); map_irq.devfn = dev->devfn; if (type == PCI_CAP_ID_MSIX) { @@ -285,7 +292,20 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) map_irq.entry_nr = msidesc->msi_attrib.entry_nr; } - ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); + ret = -EINVAL; + if (pci_seg_supported) + ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, + &map_irq); + if (ret == -EINVAL && !pci_domain_nr(dev->bus)) { + map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.index = -1; + map_irq.pirq = -1; + map_irq.bus = dev->bus->number; + ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, + &map_irq); + if (ret != -EINVAL) + pci_seg_supported = false; + } if (ret) { dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n", ret, domid); diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 58425adc22c6..fe73276e026b 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -678,38 +678,40 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) pentry = (struct sfi_device_table_entry *)sb->pentry; for (i = 0; i < num; i++, pentry++) { - if (pentry->irq != (u8)0xff) { /* native RTE case */ + int irq = pentry->irq; + + if (irq != (u8)0xff) { /* native RTE case */ /* these SPI2 devices are not exposed to system as PCI * devices, but they have separate RTE entry in IOAPIC * so we have to enable them one by one here */ - ioapic = mp_find_ioapic(pentry->irq); + ioapic = mp_find_ioapic(irq); irq_attr.ioapic = ioapic; - irq_attr.ioapic_pin = pentry->irq; + irq_attr.ioapic_pin = irq; irq_attr.trigger = 1; irq_attr.polarity = 1; - io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr); + io_apic_set_pci_routing(NULL, irq, &irq_attr); } else - pentry->irq = 0; /* No irq */ + irq = 0; /* No irq */ switch (pentry->type) { case SFI_DEV_TYPE_IPC: /* ID as IRQ is a hack that will go away */ - pdev = platform_device_alloc(pentry->name, pentry->irq); + pdev = platform_device_alloc(pentry->name, irq); if (pdev == NULL) { pr_err("out of memory for SFI platform device '%s'.\n", pentry->name); continue; } - install_irq_resource(pdev, pentry->irq); + install_irq_resource(pdev, irq); pr_debug("info[%2d]: IPC bus, name = %16.16s, " - "irq = 0x%2x\n", i, pentry->name, pentry->irq); + "irq = 0x%2x\n", i, pentry->name, irq); sfi_handle_ipc_dev(pdev); break; case SFI_DEV_TYPE_SPI: memset(&spi_info, 0, sizeof(spi_info)); strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN); - spi_info.irq = pentry->irq; + spi_info.irq = irq; spi_info.bus_num = pentry->host_num; spi_info.chip_select = pentry->addr; spi_info.max_speed_hz = pentry->max_freq; @@ -726,7 +728,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) memset(&i2c_info, 0, sizeof(i2c_info)); bus = pentry->host_num; strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN); - i2c_info.irq = pentry->irq; + i2c_info.irq = irq; i2c_info.addr = pentry->addr; pr_debug("info[%2d]: I2C bus = %d, name = %16.16s, " "irq = 0x%2x, addr = 0x%x\n", i, bus, diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 5cc821cb2e09..26c731a106af 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -25,8 +25,7 @@ config XEN_PRIVILEGED_GUEST config XEN_PVHVM def_bool y - depends on XEN - depends on X86_LOCAL_APIC + depends on XEN && PCI && X86_LOCAL_APIC config XEN_MAX_DOMAIN_MEMORY int @@ -49,11 +48,3 @@ config XEN_DEBUG_FS help Enable statistics output and various tuning options in debugfs. Enabling this option may incur a significant performance overhead. - -config XEN_DEBUG - bool "Enable Xen debug checks" - depends on XEN - default n - help - Enable various WARN_ON checks in the Xen MMU code. - Enabling this option WILL incur a significant performance overhead. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2d69617950f7..da8afd576a6b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -251,6 +251,7 @@ static void __init xen_init_cpuid_mask(void) ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ ax = 1; + cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); xsave_mask = diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3dd53f997b11..87f6673b1207 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -495,41 +495,6 @@ static pte_t xen_make_pte(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); -#ifdef CONFIG_XEN_DEBUG -pte_t xen_make_pte_debug(pteval_t pte) -{ - phys_addr_t addr = (pte & PTE_PFN_MASK); - phys_addr_t other_addr; - bool io_page = false; - pte_t _pte; - - if (pte & _PAGE_IOMAP) - io_page = true; - - _pte = xen_make_pte(pte); - - if (!addr) - return _pte; - - if (io_page && - (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { - other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; - WARN_ONCE(addr != other_addr, - "0x%lx is using VM_IO, but it is 0x%lx!\n", - (unsigned long)addr, (unsigned long)other_addr); - } else { - pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; - other_addr = (_pte.pte & PTE_PFN_MASK); - WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set), - "0x%lx is missing VM_IO (and wasn't fixed)!\n", - (unsigned long)addr); - } - - return _pte; -} -PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug); -#endif - static pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); @@ -1992,9 +1957,6 @@ void __init xen_ident_map_ISA(void) static void __init xen_post_allocator_init(void) { -#ifdef CONFIG_XEN_DEBUG - pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug); -#endif pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2404,17 +2366,3 @@ out: return err; } EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); - -#ifdef CONFIG_XEN_DEBUG_FS -static int p2m_dump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, p2m_dump_show, NULL); -} - -static const struct file_operations p2m_dump_fops = { - .open = p2m_dump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58efeb9d5440..1b267e75158d 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -161,7 +161,9 @@ #include <asm/xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#include <xen/grant_table.h> +#include "multicalls.h" #include "xen-ops.h" static void __init m2p_override_init(void); @@ -676,7 +678,8 @@ static unsigned long mfn_hash(unsigned long mfn) } /* Add an MFN override for a particular page */ -int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) +int m2p_add_override(unsigned long mfn, struct page *page, + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; unsigned long pfn; @@ -692,16 +695,28 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) "m2p_add_override: pfn %lx not mapped", pfn)) return -EINVAL; } - - page->private = mfn; + WARN_ON(PagePrivate(page)); + SetPagePrivate(page); + set_page_private(page, mfn); page->index = pfn_to_mfn(pfn); if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) return -ENOMEM; - if (clear_pte && !PageHighMem(page)) - /* Just zap old mapping for now */ - pte_clear(&init_mm, address, ptep); + if (kmap_op != NULL) { + if (!PageHighMem(page)) { + struct multicall_space mcs = + xen_mc_entry(sizeof(*kmap_op)); + + MULTI_grant_table_op(mcs.mc, + GNTTABOP_map_grant_ref, kmap_op, 1); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + } + /* let's use dev_bus_addr to record the old mfn instead */ + kmap_op->dev_bus_addr = page->index; + page->index = (unsigned long) kmap_op; + } spin_lock_irqsave(&m2p_override_lock, flags); list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); spin_unlock_irqrestore(&m2p_override_lock, flags); @@ -735,13 +750,56 @@ int m2p_remove_override(struct page *page, bool clear_pte) spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); - set_phys_to_machine(pfn, page->index); + WARN_ON(!PagePrivate(page)); + ClearPagePrivate(page); - if (clear_pte && !PageHighMem(page)) - set_pte_at(&init_mm, address, ptep, - pfn_pte(pfn, PAGE_KERNEL)); - /* No tlb flush necessary because the caller already - * left the pte unmapped. */ + if (clear_pte) { + struct gnttab_map_grant_ref *map_op = + (struct gnttab_map_grant_ref *) page->index; + set_phys_to_machine(pfn, map_op->dev_bus_addr); + if (!PageHighMem(page)) { + struct multicall_space mcs; + struct gnttab_unmap_grant_ref *unmap_op; + + /* + * It might be that we queued all the m2p grant table + * hypercalls in a multicall, then m2p_remove_override + * get called before the multicall has actually been + * issued. In this case handle is going to -1 because + * it hasn't been modified yet. + */ + if (map_op->handle == -1) + xen_mc_flush(); + /* + * Now if map_op->handle is negative it means that the + * hypercall actually returned an error. + */ + if (map_op->handle == GNTST_general_error) { + printk(KERN_WARNING "m2p_remove_override: " + "pfn %lx mfn %lx, failed to modify kernel mappings", + pfn, mfn); + return -1; + } + + mcs = xen_mc_entry( + sizeof(struct gnttab_unmap_grant_ref)); + unmap_op = mcs.args; + unmap_op->host_addr = map_op->host_addr; + unmap_op->handle = map_op->handle; + unmap_op->dev_bus_addr = 0; + + MULTI_grant_table_op(mcs.mc, + GNTTABOP_unmap_grant_ref, unmap_op, 1); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + + set_pte_at(&init_mm, address, ptep, + pfn_pte(pfn, PAGE_KERNEL)); + __flush_tlb_single(address); + map_op->host_addr = 0; + } + } else + set_phys_to_machine(pfn, page->index); return 0; } @@ -758,7 +816,7 @@ struct page *m2p_find_override(unsigned long mfn) spin_lock_irqsave(&m2p_override_lock, flags); list_for_each_entry(p, bucket, lru) { - if (p->private == mfn) { + if (page_private(p) == mfn) { ret = p; break; } @@ -782,17 +840,21 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) EXPORT_SYMBOL_GPL(m2p_find_override_pfn); #ifdef CONFIG_XEN_DEBUG_FS - -int p2m_dump_show(struct seq_file *m, void *v) +#include <linux/debugfs.h> +#include "debugfs.h" +static int p2m_dump_show(struct seq_file *m, void *v) { static const char * const level_name[] = { "top", "middle", - "entry", "abnormal" }; - static const char * const type_name[] = { "identity", "missing", - "pfn", "abnormal"}; + "entry", "abnormal", "error"}; #define TYPE_IDENTITY 0 #define TYPE_MISSING 1 #define TYPE_PFN 2 #define TYPE_UNKNOWN 3 + static const char * const type_name[] = { + [TYPE_IDENTITY] = "identity", + [TYPE_MISSING] = "missing", + [TYPE_PFN] = "pfn", + [TYPE_UNKNOWN] = "abnormal"}; unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0; unsigned int uninitialized_var(prev_level); unsigned int uninitialized_var(prev_type); @@ -856,4 +918,32 @@ int p2m_dump_show(struct seq_file *m, void *v) #undef TYPE_PFN #undef TYPE_UNKNOWN } -#endif + +static int p2m_dump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, p2m_dump_show, NULL); +} + +static const struct file_operations p2m_dump_fops = { + .open = p2m_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *d_mmu_debug; + +static int __init xen_p2m_debugfs(void) +{ + struct dentry *d_xen = xen_init_debugfs(); + + if (d_xen == NULL) + return -ENOMEM; + + d_mmu_debug = debugfs_create_dir("mmu", d_xen); + + debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops); + return 0; +} +fs_initcall(xen_p2m_debugfs); +#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 46d6d21dbdbe..38d0af4fefec 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -37,7 +37,10 @@ extern void xen_syscall_target(void); extern void xen_syscall32_target(void); /* Amount of extra memory space we add to the e820 ranges */ -phys_addr_t xen_extra_mem_start, xen_extra_mem_size; +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +/* Number of pages released from the initial allocation. */ +unsigned long xen_released_pages; /* * The maximum amount of extra memory compared to the base size. The @@ -51,48 +54,47 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(unsigned long pages) +static void __init xen_add_extra_mem(u64 start, u64 size) { unsigned long pfn; + int i; - u64 size = (u64)pages * PAGE_SIZE; - u64 extra_start = xen_extra_mem_start + xen_extra_mem_size; - - if (!pages) - return; - - e820_add_region(extra_start, size, E820_RAM); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - - memblock_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA"); + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].size == 0) { + xen_extra_mem[i].start = start; + xen_extra_mem[i].size = size; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) { + xen_extra_mem[i].size += size; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - xen_extra_mem_size += size; + memblock_x86_reserve_range(start, start + size, "XEN EXTRA"); - xen_max_p2m_pfn = PFN_DOWN(extra_start + size); + xen_max_p2m_pfn = PFN_DOWN(start + size); - for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++) + for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } -static unsigned long __init xen_release_chunk(phys_addr_t start_addr, - phys_addr_t end_addr) +static unsigned long __init xen_release_chunk(unsigned long start, + unsigned long end) { struct xen_memory_reservation reservation = { .address_bits = 0, .extent_order = 0, .domid = DOMID_SELF }; - unsigned long start, end; unsigned long len = 0; unsigned long pfn; int ret; - start = PFN_UP(start_addr); - end = PFN_DOWN(end_addr); - - if (end <= start) - return 0; - for(pfn = start; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -117,72 +119,52 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr, return len; } -static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, - const struct e820map *e820) +static unsigned long __init xen_set_identity_and_release( + const struct e820entry *list, size_t map_size, unsigned long nr_pages) { - phys_addr_t max_addr = PFN_PHYS(max_pfn); - phys_addr_t last_end = ISA_END_ADDRESS; + phys_addr_t start = 0; unsigned long released = 0; - int i; - - /* Free any unused memory above the low 1Mbyte. */ - for (i = 0; i < e820->nr_map && last_end < max_addr; i++) { - phys_addr_t end = e820->map[i].addr; - end = min(max_addr, end); - - if (last_end < end) - released += xen_release_chunk(last_end, end); - last_end = max(last_end, e820->map[i].addr + e820->map[i].size); - } - - if (last_end < max_addr) - released += xen_release_chunk(last_end, max_addr); - - printk(KERN_INFO "released %lu pages of unused memory\n", released); - return released; -} - -static unsigned long __init xen_set_identity(const struct e820entry *list, - ssize_t map_size) -{ - phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS; - phys_addr_t start_pci = last; - const struct e820entry *entry; unsigned long identity = 0; + const struct e820entry *entry; int i; + /* + * Combine non-RAM regions and gaps until a RAM region (or the + * end of the map) is reached, then set the 1:1 map and + * release the pages (if available) in those non-RAM regions. + * + * The combined non-RAM regions are rounded to a whole number + * of pages so any partial pages are accessible via the 1:1 + * mapping. This is needed for some BIOSes that put (for + * example) the DMI tables in a reserved region that begins on + * a non-page boundary. + */ for (i = 0, entry = list; i < map_size; i++, entry++) { - phys_addr_t start = entry->addr; - phys_addr_t end = start + entry->size; + phys_addr_t end = entry->addr + entry->size; - if (start < last) - start = last; + if (entry->type == E820_RAM || i == map_size - 1) { + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); - if (end <= start) - continue; + if (entry->type == E820_RAM) + end_pfn = PFN_UP(entry->addr); - /* Skip over the 1MB region. */ - if (last > end) - continue; + if (start_pfn < end_pfn) { + if (start_pfn < nr_pages) + released += xen_release_chunk( + start_pfn, min(end_pfn, nr_pages)); - if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) { - if (start > start_pci) identity += set_phys_range_identity( - PFN_UP(start_pci), PFN_DOWN(start)); - - /* Without saving 'last' we would gooble RAM too - * at the end of the loop. */ - last = end; - start_pci = end; - continue; + start_pfn, end_pfn); + } + start = end; } - start_pci = min(start, start_pci); - last = end; } - if (last > start_pci) - identity += set_phys_range_identity( - PFN_UP(start_pci), PFN_DOWN(last)); - return identity; + + printk(KERN_INFO "Released %lu pages of unused memory\n", released); + printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity); + + return released; } static unsigned long __init xen_get_max_pages(void) @@ -197,21 +179,32 @@ static unsigned long __init xen_get_max_pages(void) return min(max_pages, MAX_DOMAIN_PAGES); } +static void xen_align_and_add_e820_region(u64 start, u64 size, int type) +{ + u64 end = start + size; + + /* Align RAM regions to page boundaries. */ + if (type == E820_RAM) { + start = PAGE_ALIGN(start); + end &= ~((u64)PAGE_SIZE - 1); + } + + e820_add_region(start, end - start, type); +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { static struct e820entry map[E820MAX] __initdata; - static struct e820entry map_raw[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; unsigned long long mem_end; int rc; struct xen_memory_map memmap; + unsigned long max_pages; unsigned long extra_pages = 0; - unsigned long extra_limit; - unsigned long identity_pages = 0; int i; int op; @@ -237,58 +230,65 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); - memcpy(map_raw, map, sizeof(map)); - e820.nr_map = 0; - xen_extra_mem_start = mem_end; - for (i = 0; i < memmap.nr_entries; i++) { - unsigned long long end; - - /* Guard against non-page aligned E820 entries. */ - if (map[i].type == E820_RAM) - map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE; - - end = map[i].addr + map[i].size; - if (map[i].type == E820_RAM && end > mem_end) { - /* RAM off the end - may be partially included */ - u64 delta = min(map[i].size, end - mem_end); - - map[i].size -= delta; - end -= delta; - - extra_pages += PFN_DOWN(delta); - /* - * Set RAM below 4GB that is not for us to be unusable. - * This prevents "System RAM" address space from being - * used as potential resource for I/O address (happens - * when 'allocate_resource' is called). - */ - if (delta && - (xen_initial_domain() && end < 0x100000000ULL)) - e820_add_region(end, delta, E820_UNUSABLE); + /* Make sure the Xen-supplied memory map is well-ordered. */ + sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); + + max_pages = xen_get_max_pages(); + if (max_pages > max_pfn) + extra_pages += max_pages - max_pfn; + + /* + * Set P2M for all non-RAM pages and E820 gaps to be identity + * type PFNs. Any RAM pages that would be made inaccesible by + * this are first released. + */ + xen_released_pages = xen_set_identity_and_release( + map, memmap.nr_entries, max_pfn); + extra_pages += xen_released_pages; + + /* + * Clamp the amount of extra memory to a EXTRA_MEM_RATIO + * factor the base size. On non-highmem systems, the base + * size is the full initial memory allocation; on highmem it + * is limited to the max size of lowmem, so that it doesn't + * get completely filled. + * + * In principle there could be a problem in lowmem systems if + * the initial memory is also very large with respect to + * lowmem, but we won't try to deal with that here. + */ + extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages); + + i = 0; + while (i < memmap.nr_entries) { + u64 addr = map[i].addr; + u64 size = map[i].size; + u32 type = map[i].type; + + if (type == E820_RAM) { + if (addr < mem_end) { + size = min(size, mem_end - addr); + } else if (extra_pages) { + size = min(size, (u64)extra_pages * PAGE_SIZE); + extra_pages -= size / PAGE_SIZE; + xen_add_extra_mem(addr, size); + } else + type = E820_UNUSABLE; } - if (map[i].size > 0 && end > xen_extra_mem_start) - xen_extra_mem_start = end; + xen_align_and_add_e820_region(addr, size, type); - /* Add region if any remains */ - if (map[i].size > 0) - e820_add_region(map[i].addr, map[i].size, map[i].type); + map[i].addr += size; + map[i].size -= size; + if (map[i].size == 0) + i++; } - /* Align the balloon area so that max_low_pfn does not get set - * to be at the _end_ of the PCI gap at the far end (fee01000). - * Note that xen_extra_mem_start gets set in the loop above to be - * past the last E820 region. */ - if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) - xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we * reserve ISA memory anyway because too many things poke * about in there. - * - * In Dom0, the host E820 information can leave gaps in the - * ISA range, which would cause us to release those pages. To - * avoid this, we unconditionally reserve them here. */ e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_RESERVED); @@ -305,44 +305,6 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - extra_limit = xen_get_max_pages(); - if (max_pfn + extra_pages > extra_limit) { - if (extra_limit > max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; - } - - extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820); - - /* - * Clamp the amount of extra memory to a EXTRA_MEM_RATIO - * factor the base size. On non-highmem systems, the base - * size is the full initial memory allocation; on highmem it - * is limited to the max size of lowmem, so that it doesn't - * get completely filled. - * - * In principle there could be a problem in lowmem systems if - * the initial memory is also very large with respect to - * lowmem, but we won't try to deal with that here. - */ - extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), - max_pfn + extra_pages); - - if (extra_limit >= max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; - - xen_add_extra_mem(extra_pages); - - /* - * Set P2M for all non-RAM pages and E820 gaps to be identity - * type PFNs. We supply it with the non-sanitized version - * of the E820. - */ - identity_pages = xen_set_identity(map_raw, memmap.nr_entries); - printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages); return "Xen"; } diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c index be4425616931..7835b8fc94db 100644 --- a/crypto/ghash-generic.c +++ b/crypto/ghash-generic.c @@ -67,6 +67,9 @@ static int ghash_update(struct shash_desc *desc, struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); u8 *dst = dctx->buffer; + if (!ctx->gf128) + return -ENOKEY; + if (dctx->bytes) { int n = min(srclen, dctx->bytes); u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes); @@ -119,6 +122,9 @@ static int ghash_final(struct shash_desc *desc, u8 *dst) struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); u8 *buf = dctx->buffer; + if (!ctx->gf128) + return -ENOKEY; + ghash_flush(ctx, dctx); memcpy(dst, buf, GHASH_BLOCK_SIZE); diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 2330a9ad5e95..1540792b1e54 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -396,7 +396,7 @@ static int xen_blkbk_map(struct blkif_request *req, continue; ret = m2p_add_override(PFN_DOWN(map[i].dev_bus_addr), - blkbk->pending_page(pending_req, i), false); + blkbk->pending_page(pending_req, i), NULL); if (ret) { pr_alert(DRV_PFX "Failed to install M2P override for %lx (ret: %d)\n", (unsigned long)map[i].dev_bus_addr, ret); diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index 9ca5c021d0b6..361a1dff8f77 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -966,6 +966,9 @@ ssize_t tpm_show_durations(struct device *dev, struct device_attribute *attr, { struct tpm_chip *chip = dev_get_drvdata(dev); + if (chip->vendor.duration[TPM_LONG] == 0) + return 0; + return sprintf(buf, "%d %d %d [%s]\n", jiffies_to_usecs(chip->vendor.duration[TPM_SHORT]), jiffies_to_usecs(chip->vendor.duration[TPM_MEDIUM]), diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 0599854e2217..118ec12d2d5f 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -34,8 +34,8 @@ struct gpio_bank { u16 irq; u16 virtual_irq_start; int method; -#if defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP2PLUS) u32 suspend_wakeup; +#if defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP2PLUS) u32 saved_wakeup; #endif u32 non_wakeup_gpios; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index c43b8ff626a7..0550dcb85814 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -577,6 +577,7 @@ pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert) void pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert) { + *gpio_base = -1; } #endif diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index e88c64417a8a..14cc88aaf3a7 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -277,7 +277,12 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr, case ATOM_ARG_FB: idx = U8(*ptr); (*ptr)++; - val = gctx->scratch[((gctx->fb_base + idx) / 4)]; + if ((gctx->fb_base + (idx * 4)) > gctx->scratch_size_bytes) { + DRM_ERROR("ATOM: fb read beyond scratch region: %d vs. %d\n", + gctx->fb_base + (idx * 4), gctx->scratch_size_bytes); + val = 0; + } else + val = gctx->scratch[(gctx->fb_base / 4) + idx]; if (print) DEBUG("FB[0x%02X]", idx); break; @@ -531,7 +536,11 @@ static void atom_put_dst(atom_exec_context *ctx, int arg, uint8_t attr, case ATOM_ARG_FB: idx = U8(*ptr); (*ptr)++; - gctx->scratch[((gctx->fb_base + idx) / 4)] = val; + if ((gctx->fb_base + (idx * 4)) > gctx->scratch_size_bytes) { + DRM_ERROR("ATOM: fb write beyond scratch region: %d vs. %d\n", + gctx->fb_base + (idx * 4), gctx->scratch_size_bytes); + } else + gctx->scratch[(gctx->fb_base / 4) + idx] = val; DEBUG("FB[0x%02X]", idx); break; case ATOM_ARG_PLL: @@ -1370,11 +1379,13 @@ int atom_allocate_fb_scratch(struct atom_context *ctx) usage_bytes = firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb * 1024; } + ctx->scratch_size_bytes = 0; if (usage_bytes == 0) usage_bytes = 20 * 1024; /* allocate some scratch memory */ ctx->scratch = kzalloc(usage_bytes, GFP_KERNEL); if (!ctx->scratch) return -ENOMEM; + ctx->scratch_size_bytes = usage_bytes; return 0; } diff --git a/drivers/gpu/drm/radeon/atom.h b/drivers/gpu/drm/radeon/atom.h index a589a55b223e..93cfe2086ba0 100644 --- a/drivers/gpu/drm/radeon/atom.h +++ b/drivers/gpu/drm/radeon/atom.h @@ -137,6 +137,7 @@ struct atom_context { int cs_equal, cs_above; int io_mode; uint32_t *scratch; + int scratch_size_bytes; }; extern int atom_debug; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index c742944d3805..a515b2a09d85 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -466,7 +466,7 @@ static void atombios_crtc_program_ss(struct drm_crtc *crtc, return; } args.v2.ucEnable = enable; - if ((ss->percentage == 0) || (ss->type & ATOM_EXTERNAL_SS_MASK)) + if ((ss->percentage == 0) || (ss->type & ATOM_EXTERNAL_SS_MASK) || ASIC_IS_DCE41(rdev)) args.v2.ucEnable = ATOM_DISABLE; } else if (ASIC_IS_DCE3(rdev)) { args.v1.usSpreadSpectrumPercentage = cpu_to_le16(ss->percentage); diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index 8a171b21b453..eb3f6dc6df83 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -1638,7 +1638,17 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder) break; case 2: args.v2.ucCRTC = radeon_crtc->crtc_id; - args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder); + if (radeon_encoder_is_dp_bridge(encoder)) { + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); + + if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS) + args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS; + else if (connector->connector_type == DRM_MODE_CONNECTOR_VGA) + args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT; + else + args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder); + } else + args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder); switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: @@ -1756,10 +1766,15 @@ static int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder) if (ASIC_IS_DCE4(rdev)) { dig = radeon_encoder->enc_priv; if (ASIC_IS_DCE41(rdev)) { - if (dig->linkb) - return 1; - else - return 0; + /* ontario follows DCE4 */ + if (rdev->family == CHIP_PALM) { + if (dig->linkb) + return 1; + else + return 0; + } else + /* llano follows DCE3.2 */ + return radeon_crtc->crtc_id; } else { switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index ae3c6f5dd2b7..082fcaea583f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -321,7 +321,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type]; struct ttm_tt *ttm = bo->ttm; struct ttm_mem_reg *old_mem = &bo->mem; - struct ttm_mem_reg old_copy; + struct ttm_mem_reg old_copy = *old_mem; void *old_iomap; void *new_iomap; int ret; diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index f2b377c56a3a..36d7f270b14d 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -390,7 +390,7 @@ temp_from_reg(u16 reg, s16 regval) { if (is_word_sized(reg)) return LM75_TEMP_FROM_REG(regval); - return regval * 1000; + return ((s8)regval) * 1000; } static inline u16 @@ -398,7 +398,8 @@ temp_to_reg(u16 reg, long temp) { if (is_word_sized(reg)) return LM75_TEMP_TO_REG(temp); - return DIV_ROUND_CLOSEST(SENSORS_LIMIT(temp, -127000, 128000), 1000); + return (s8)DIV_ROUND_CLOSEST(SENSORS_LIMIT(temp, -127000, 128000), + 1000); } /* Some of analog inputs have internal scaling (2x), 8mV is ADC LSB */ @@ -1715,7 +1716,8 @@ static void w83627ehf_device_remove_files(struct device *dev) } /* Get the monitoring functions started */ -static inline void __devinit w83627ehf_init_device(struct w83627ehf_data *data) +static inline void __devinit w83627ehf_init_device(struct w83627ehf_data *data, + enum kinds kind) { int i; u8 tmp, diode; @@ -1746,10 +1748,16 @@ static inline void __devinit w83627ehf_init_device(struct w83627ehf_data *data) w83627ehf_write_value(data, W83627EHF_REG_VBAT, tmp | 0x01); /* Get thermal sensor types */ - diode = w83627ehf_read_value(data, W83627EHF_REG_DIODE); + switch (kind) { + case w83627ehf: + diode = w83627ehf_read_value(data, W83627EHF_REG_DIODE); + break; + default: + diode = 0x70; + } for (i = 0; i < 3; i++) { if ((tmp & (0x02 << i))) - data->temp_type[i] = (diode & (0x10 << i)) ? 1 : 2; + data->temp_type[i] = (diode & (0x10 << i)) ? 1 : 3; else data->temp_type[i] = 4; /* thermistor */ } @@ -2016,7 +2024,7 @@ static int __devinit w83627ehf_probe(struct platform_device *pdev) } /* Initialize the chip */ - w83627ehf_init_device(data); + w83627ehf_init_device(data, sio_data->kind); data->vrm = vid_which_vrm(); superio_enter(sio_data->sioreg); diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index 9827c5e686cb..811dbbd9306c 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -327,7 +327,7 @@ config BLK_DEV_OPTI621 select BLK_DEV_IDEPCI help This is a driver for the OPTi 82C621 EIDE controller. - Please read the comments at the top of <file:drivers/ide/pci/opti621.c>. + Please read the comments at the top of <file:drivers/ide/opti621.c>. config BLK_DEV_RZ1000 tristate "RZ1000 chipset bugfix/support" @@ -365,7 +365,7 @@ config BLK_DEV_ALI15X3 normal dual channel support. Please read the comments at the top of - <file:drivers/ide/pci/alim15x3.c>. + <file:drivers/ide/alim15x3.c>. If unsure, say N. @@ -528,7 +528,7 @@ config BLK_DEV_NS87415 This driver adds detection and support for the NS87415 chip (used mainly on SPARC64 and PA-RISC machines). - Please read the comments at the top of <file:drivers/ide/pci/ns87415.c>. + Please read the comments at the top of <file:drivers/ide/ns87415.c>. config BLK_DEV_PDC202XX_OLD tristate "PROMISE PDC202{46|62|65|67} support" @@ -547,7 +547,7 @@ config BLK_DEV_PDC202XX_OLD for more than one card. Please read the comments at the top of - <file:drivers/ide/pci/pdc202xx_old.c>. + <file:drivers/ide/pdc202xx_old.c>. If unsure, say N. @@ -593,7 +593,7 @@ config BLK_DEV_SIS5513 ATA100: SiS635, SiS645, SiS650, SiS730, SiS735, SiS740, SiS745, SiS750 - Please read the comments at the top of <file:drivers/ide/pci/sis5513.c>. + Please read the comments at the top of <file:drivers/ide/sis5513.c>. config BLK_DEV_SL82C105 tristate "Winbond SL82c105 support" @@ -616,7 +616,7 @@ config BLK_DEV_SLC90E66 look-a-like to the PIIX4 it should be a nice addition. Please read the comments at the top of - <file:drivers/ide/pci/slc90e66.c>. + <file:drivers/ide/slc90e66.c>. config BLK_DEV_TRM290 tristate "Tekram TRM290 chipset support" @@ -625,7 +625,7 @@ config BLK_DEV_TRM290 This driver adds support for bus master DMA transfers using the Tekram TRM290 PCI IDE chip. Volunteers are needed for further tweaking and development. - Please read the comments at the top of <file:drivers/ide/pci/trm290.c>. + Please read the comments at the top of <file:drivers/ide/trm290.c>. config BLK_DEV_VIA82CXXX tristate "VIA82CXXX chipset support" @@ -836,7 +836,7 @@ config BLK_DEV_ALI14XX of the ALI M1439/1443/1445/1487/1489 chipsets, and permits faster I/O speeds to be set as well. See the files <file:Documentation/ide/ide.txt> and - <file:drivers/ide/legacy/ali14xx.c> for more info. + <file:drivers/ide/ali14xx.c> for more info. config BLK_DEV_DTC2278 tristate "DTC-2278 support" @@ -847,7 +847,7 @@ config BLK_DEV_DTC2278 boot parameter. It enables support for the secondary IDE interface of the DTC-2278 card, and permits faster I/O speeds to be set as well. See the <file:Documentation/ide/ide.txt> and - <file:drivers/ide/legacy/dtc2278.c> files for more info. + <file:drivers/ide/dtc2278.c> files for more info. config BLK_DEV_HT6560B tristate "Holtek HT6560B support" @@ -858,7 +858,7 @@ config BLK_DEV_HT6560B boot parameter. It enables support for the secondary IDE interface of the Holtek card, and permits faster I/O speeds to be set as well. See the <file:Documentation/ide/ide.txt> and - <file:drivers/ide/legacy/ht6560b.c> files for more info. + <file:drivers/ide/ht6560b.c> files for more info. config BLK_DEV_QD65XX tristate "QDI QD65xx support" @@ -867,7 +867,7 @@ config BLK_DEV_QD65XX help This driver is enabled at runtime using the "qd65xx.probe" kernel boot parameter. It permits faster I/O speeds to be set. See the - <file:Documentation/ide/ide.txt> and <file:drivers/ide/legacy/qd65xx.c> + <file:Documentation/ide/ide.txt> and <file:drivers/ide/qd65xx.c> for more info. config BLK_DEV_UMC8672 @@ -879,7 +879,7 @@ config BLK_DEV_UMC8672 boot parameter. It enables support for the secondary IDE interface of the UMC-8672, and permits faster I/O speeds to be set as well. See the files <file:Documentation/ide/ide.txt> and - <file:drivers/ide/legacy/umc8672.c> for more info. + <file:drivers/ide/umc8672.c> for more info. endif diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index c621c98c99da..a88f3cbb100b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -306,6 +306,11 @@ static inline bool dma_pte_present(struct dma_pte *pte) return (pte->val & 3) != 0; } +static inline bool dma_pte_superpage(struct dma_pte *pte) +{ + return (pte->val & (1 << 7)); +} + static inline int first_pte_in_page(struct dma_pte *pte) { return !((unsigned long)pte & ~VTD_PAGE_MASK); @@ -404,6 +409,9 @@ static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; +int intel_iommu_gfx_mapped; +EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); + #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1)) static DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); @@ -577,17 +585,18 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain) static void domain_update_iommu_superpage(struct dmar_domain *domain) { - int i, mask = 0xf; + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu = NULL; + int mask = 0xf; if (!intel_iommu_superpage) { domain->iommu_superpage = 0; return; } - domain->iommu_superpage = 4; /* 1TiB */ - - for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) { - mask |= cap_super_page_val(g_iommus[i]->cap); + /* set iommu_superpage to the smallest common denominator */ + for_each_active_iommu(iommu, drhd) { + mask &= cap_super_page_val(iommu->cap); if (!mask) { break; } @@ -730,29 +739,23 @@ out: } static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, - unsigned long pfn, int large_level) + unsigned long pfn, int target_level) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; struct dma_pte *parent, *pte = NULL; int level = agaw_to_level(domain->agaw); - int offset, target_level; + int offset; BUG_ON(!domain->pgd); BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width); parent = domain->pgd; - /* Search pte */ - if (!large_level) - target_level = 1; - else - target_level = large_level; - while (level > 0) { void *tmp_page; offset = pfn_level_offset(pfn, level); pte = &parent[offset]; - if (!large_level && (pte->val & DMA_PTE_LARGE_PAGE)) + if (!target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte))) break; if (level == target_level) break; @@ -816,13 +819,14 @@ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain, } /* clear last level pte, a tlb flush should be followed */ -static void dma_pte_clear_range(struct dmar_domain *domain, +static int dma_pte_clear_range(struct dmar_domain *domain, unsigned long start_pfn, unsigned long last_pfn) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; unsigned int large_page = 1; struct dma_pte *first_pte, *pte; + int order; BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width); @@ -846,6 +850,9 @@ static void dma_pte_clear_range(struct dmar_domain *domain, (void *)pte - (void *)first_pte); } while (start_pfn && start_pfn <= last_pfn); + + order = (large_page - 1) * 9; + return order; } /* free page table pages. last level pte should already be cleared */ @@ -3226,9 +3233,6 @@ static void __init init_no_remapping_devices(void) } } - if (dmar_map_gfx) - return; - for_each_drhd_unit(drhd) { int i; if (drhd->ignored || drhd->include_all) @@ -3236,18 +3240,23 @@ static void __init init_no_remapping_devices(void) for (i = 0; i < drhd->devices_cnt; i++) if (drhd->devices[i] && - !IS_GFX_DEVICE(drhd->devices[i])) + !IS_GFX_DEVICE(drhd->devices[i])) break; if (i < drhd->devices_cnt) continue; - /* bypass IOMMU if it is just for gfx devices */ - drhd->ignored = 1; - for (i = 0; i < drhd->devices_cnt; i++) { - if (!drhd->devices[i]) - continue; - drhd->devices[i]->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + /* This IOMMU has *only* gfx devices. Either bypass it or + set the gfx_mapped flag, as appropriate */ + if (dmar_map_gfx) { + intel_iommu_gfx_mapped = 1; + } else { + drhd->ignored = 1; + for (i = 0; i < drhd->devices_cnt; i++) { + if (!drhd->devices[i]) + continue; + drhd->devices[i]->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + } } } } @@ -3568,6 +3577,8 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, found = 1; } + spin_unlock_irqrestore(&device_domain_lock, flags); + if (found == 0) { unsigned long tmp_flags; spin_lock_irqsave(&domain->iommu_lock, tmp_flags); @@ -3584,8 +3595,6 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, spin_unlock_irqrestore(&iommu->lock, tmp_flags); } } - - spin_unlock_irqrestore(&device_domain_lock, flags); } static void vm_domain_remove_all_dev_info(struct dmar_domain *domain) @@ -3739,6 +3748,7 @@ static int intel_iommu_domain_init(struct iommu_domain *domain) vm_domain_exit(dmar_domain); return -ENOMEM; } + domain_update_iommu_cap(dmar_domain); domain->priv = dmar_domain; return 0; @@ -3864,14 +3874,15 @@ static int intel_iommu_unmap(struct iommu_domain *domain, { struct dmar_domain *dmar_domain = domain->priv; size_t size = PAGE_SIZE << gfp_order; + int order; - dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT, + order = dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT, (iova + size - 1) >> VTD_PAGE_SHIFT); if (dmar_domain->max_addr == iova + size) dmar_domain->max_addr = iova; - return gfp_order; + return order; } static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, @@ -3950,7 +3961,11 @@ static void __devinit quirk_calpella_no_shadow_gtt(struct pci_dev *dev) if (!(ggc & GGC_MEMORY_VT_ENABLED)) { printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n"); dmar_map_gfx = 0; - } + } else if (dmar_map_gfx) { + /* we have to ensure the gfx device is idle before we flush */ + printk(KERN_INFO "DMAR: Disabling batched IOTLB flush on Ironlake\n"); + intel_iommu_strict = 1; + } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt); diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index f82147029636..32ac70861d66 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -628,6 +628,7 @@ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, job->kc = kc; job->fn = fn; job->context = context; + job->master_job = job; atomic_inc(&kc->nr_jobs); diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c index d72156517726..a5c9ed128b97 100644 --- a/drivers/media/video/v4l2-dev.c +++ b/drivers/media/video/v4l2-dev.c @@ -181,7 +181,7 @@ static void v4l2_device_release(struct device *cd) * TODO: In the long run all drivers that use v4l2_device should use the * v4l2_device release callback. This check will then be unnecessary. */ - if (v4l2_dev->release == NULL) + if (v4l2_dev && v4l2_dev->release == NULL) v4l2_dev = NULL; /* Release video_device and perform other diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h index e46df5331c55..9a7eb3b36cf3 100644 --- a/drivers/net/bnx2x/bnx2x.h +++ b/drivers/net/bnx2x/bnx2x.h @@ -239,13 +239,19 @@ void bnx2x_int_disable(struct bnx2x *bp); * FUNC_N_CLID_X = N * NUM_SPECIAL_CLIENTS + FUNC_0_CLID_X * */ -/* iSCSI L2 */ -#define BNX2X_ISCSI_ETH_CL_ID_IDX 1 -#define BNX2X_ISCSI_ETH_CID 49 +enum { + BNX2X_ISCSI_ETH_CL_ID_IDX, + BNX2X_FCOE_ETH_CL_ID_IDX, + BNX2X_MAX_CNIC_ETH_CL_ID_IDX, +}; -/* FCoE L2 */ -#define BNX2X_FCOE_ETH_CL_ID_IDX 2 -#define BNX2X_FCOE_ETH_CID 50 +#define BNX2X_CNIC_START_ETH_CID 48 +enum { + /* iSCSI L2 */ + BNX2X_ISCSI_ETH_CID = BNX2X_CNIC_START_ETH_CID, + /* FCoE L2 */ + BNX2X_FCOE_ETH_CID, +}; /** Additional rings budgeting */ #ifdef BCM_CNIC diff --git a/drivers/net/bnx2x/bnx2x_cmn.h b/drivers/net/bnx2x/bnx2x_cmn.h index 223bfeebc597..2dc1199239d0 100644 --- a/drivers/net/bnx2x/bnx2x_cmn.h +++ b/drivers/net/bnx2x/bnx2x_cmn.h @@ -1297,7 +1297,7 @@ static inline void bnx2x_init_txdata(struct bnx2x *bp, static inline u8 bnx2x_cnic_eth_cl_id(struct bnx2x *bp, u8 cl_idx) { return bp->cnic_base_cl_id + cl_idx + - (bp->pf_num >> 1) * NON_ETH_CONTEXT_USE; + (bp->pf_num >> 1) * BNX2X_MAX_CNIC_ETH_CL_ID_IDX; } static inline u8 bnx2x_cnic_fw_sb_id(struct bnx2x *bp) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6d79b78cfc75..de3d351ccb6b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1435,6 +1435,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) struct sk_buff *skb = *pskb; struct slave *slave; struct bonding *bond; + void (*recv_probe)(struct sk_buff *, struct bonding *, + struct slave *); skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) @@ -1448,11 +1450,12 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) if (bond->params.arp_interval) slave->dev->last_rx = jiffies; - if (bond->recv_probe) { + recv_probe = ACCESS_ONCE(bond->recv_probe); + if (recv_probe) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (likely(nskb)) { - bond->recv_probe(nskb, bond, slave); + recv_probe(nskb, bond, slave); dev_kfree_skb(nskb); } } diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 92feac68b66e..4cc6f44c2ba2 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -261,11 +261,13 @@ static netdev_tx_t mscan_start_xmit(struct sk_buff *skb, struct net_device *dev) void __iomem *data = ®s->tx.dsr1_0; u16 *payload = (u16 *)frame->data; - /* It is safe to write into dsr[dlc+1] */ - for (i = 0; i < (frame->can_dlc + 1) / 2; i++) { + for (i = 0; i < frame->can_dlc / 2; i++) { out_be16(data, *payload++); data += 2 + _MSCAN_RESERVED_DSR_SIZE; } + /* write remaining byte if necessary */ + if (frame->can_dlc & 1) + out_8(data, frame->data[frame->can_dlc - 1]); } out_8(®s->tx.dlr, frame->can_dlc); @@ -330,10 +332,13 @@ static void mscan_get_rx_frame(struct net_device *dev, struct can_frame *frame) void __iomem *data = ®s->rx.dsr1_0; u16 *payload = (u16 *)frame->data; - for (i = 0; i < (frame->can_dlc + 1) / 2; i++) { + for (i = 0; i < frame->can_dlc / 2; i++) { *payload++ = in_be16(data); data += 2 + _MSCAN_RESERVED_DSR_SIZE; } + /* read remaining byte if necessary */ + if (frame->can_dlc & 1) + frame->data[frame->can_dlc - 1] = in_8(data); } out_8(®s->canrflg, MSCAN_RXF); diff --git a/drivers/net/mlx4/en_tx.c b/drivers/net/mlx4/en_tx.c index 6e03de034ac7..f76ab6bf3096 100644 --- a/drivers/net/mlx4/en_tx.c +++ b/drivers/net/mlx4/en_tx.c @@ -172,7 +172,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, memset(ring->buf, 0, ring->buf_size); ring->qp_state = MLX4_QP_STATE_RST; - ring->doorbell_qpn = swab32(ring->qp.qpn << 8); + ring->doorbell_qpn = ring->qp.qpn << 8; mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn, ring->cqn, &ring->context); @@ -791,7 +791,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan(skb); if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tag) { - *(u32 *) (&tx_desc->ctrl.vlan_tag) |= ring->doorbell_qpn; + *(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn); op_own |= htonl((bf_index & 0xffff) << 8); /* Ensure new descirptor hits memory * before setting ownership of this descriptor to HW */ @@ -812,7 +812,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) wmb(); tx_desc->ctrl.owner_opcode = op_own; wmb(); - writel(ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL); + iowrite32be(ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL); } /* Poll CQ here */ diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index ed2a3977c6e7..e8882023576b 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -307,6 +307,11 @@ static ssize_t store_enabled(struct netconsole_target *nt, return err; if (enabled < 0 || enabled > 1) return -EINVAL; + if (enabled == nt->enabled) { + printk(KERN_INFO "netconsole: network logging has already %s\n", + nt->enabled ? "started" : "stopped"); + return -EINVAL; + } if (enabled) { /* 1 */ diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c index eae542a7e987..89f829f5f725 100644 --- a/drivers/net/pptp.c +++ b/drivers/net/pptp.c @@ -285,8 +285,10 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) ip_send_check(iph); ip_local_out(skb); + return 1; tx_error: + kfree_skb(skb); return 1; } @@ -305,11 +307,18 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) } header = (struct pptp_gre_header *)(skb->data); + headersize = sizeof(*header); /* test if acknowledgement present */ if (PPTP_GRE_IS_A(header->ver)) { - __u32 ack = (PPTP_GRE_IS_S(header->flags)) ? - header->ack : header->seq; /* ack in different place if S = 0 */ + __u32 ack; + + if (!pskb_may_pull(skb, headersize)) + goto drop; + header = (struct pptp_gre_header *)(skb->data); + + /* ack in different place if S = 0 */ + ack = PPTP_GRE_IS_S(header->flags) ? header->ack : header->seq; ack = ntohl(ack); @@ -318,21 +327,18 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) /* also handle sequence number wrap-around */ if (WRAPPED(ack, opt->ack_recv)) opt->ack_recv = ack; + } else { + headersize -= sizeof(header->ack); } - /* test if payload present */ if (!PPTP_GRE_IS_S(header->flags)) goto drop; - headersize = sizeof(*header); payload_len = ntohs(header->payload_len); seq = ntohl(header->seq); - /* no ack present? */ - if (!PPTP_GRE_IS_A(header->ver)) - headersize -= sizeof(header->ack); /* check for incomplete packet (length smaller than expected) */ - if (skb->len - headersize < payload_len) + if (!pskb_may_pull(skb, headersize + payload_len)) goto drop; payload = skb->data + headersize; diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index c23667017922..6d657cabb951 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -2859,7 +2859,7 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x1f, 0x0004); rtl_writephy(tp, 0x1f, 0x0007); rtl_writephy(tp, 0x1e, 0x0020); - rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0100); + rtl_w1w0_phy(tp, 0x15, 0x0000, 0x0100); rtl_writephy(tp, 0x1f, 0x0002); rtl_writephy(tp, 0x1f, 0x0000); rtl_writephy(tp, 0x0d, 0x0007); @@ -3316,6 +3316,37 @@ static void __devinit rtl_init_mdio_ops(struct rtl8169_private *tp) } } +static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) +{ + void __iomem *ioaddr = tp->mmio_addr; + + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_29: + case RTL_GIGA_MAC_VER_30: + case RTL_GIGA_MAC_VER_32: + case RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_34: + RTL_W32(RxConfig, RTL_R32(RxConfig) | + AcceptBroadcast | AcceptMulticast | AcceptMyPhys); + break; + default: + break; + } +} + +static bool rtl_wol_pll_power_down(struct rtl8169_private *tp) +{ + if (!(__rtl8169_get_wol(tp) & WAKE_ANY)) + return false; + + rtl_writephy(tp, 0x1f, 0x0000); + rtl_writephy(tp, MII_BMCR, 0x0000); + + rtl_wol_suspend_quirk(tp); + + return true; +} + static void r810x_phy_power_down(struct rtl8169_private *tp) { rtl_writephy(tp, 0x1f, 0x0000); @@ -3330,18 +3361,8 @@ static void r810x_phy_power_up(struct rtl8169_private *tp) static void r810x_pll_power_down(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - if (__rtl8169_get_wol(tp) & WAKE_ANY) { - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, MII_BMCR, 0x0000); - - if (tp->mac_version == RTL_GIGA_MAC_VER_29 || - tp->mac_version == RTL_GIGA_MAC_VER_30) - RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast | - AcceptMulticast | AcceptMyPhys); + if (rtl_wol_pll_power_down(tp)) return; - } r810x_phy_power_down(tp); } @@ -3430,17 +3451,8 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) tp->mac_version == RTL_GIGA_MAC_VER_33) rtl_ephy_write(ioaddr, 0x19, 0xff64); - if (__rtl8169_get_wol(tp) & WAKE_ANY) { - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, MII_BMCR, 0x0000); - - if (tp->mac_version == RTL_GIGA_MAC_VER_32 || - tp->mac_version == RTL_GIGA_MAC_VER_33 || - tp->mac_version == RTL_GIGA_MAC_VER_34) - RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast | - AcceptMulticast | AcceptMyPhys); + if (rtl_wol_pll_power_down(tp)) return; - } r8168_phy_power_down(tp); @@ -5788,11 +5800,30 @@ static const struct dev_pm_ops rtl8169_pm_ops = { #endif /* !CONFIG_PM */ +static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) +{ + void __iomem *ioaddr = tp->mmio_addr; + + /* WoL fails with 8168b when the receiver is disabled. */ + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_11: + case RTL_GIGA_MAC_VER_12: + case RTL_GIGA_MAC_VER_17: + pci_clear_master(tp->pci_dev); + + RTL_W8(ChipCmd, CmdRxEnb); + /* PCI commit */ + RTL_R8(ChipCmd); + break; + default: + break; + } +} + static void rtl_shutdown(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; rtl8169_net_suspend(dev); @@ -5806,16 +5837,9 @@ static void rtl_shutdown(struct pci_dev *pdev) spin_unlock_irq(&tp->lock); if (system_state == SYSTEM_POWER_OFF) { - /* WoL fails with 8168b when the receiver is disabled. */ - if ((tp->mac_version == RTL_GIGA_MAC_VER_11 || - tp->mac_version == RTL_GIGA_MAC_VER_12 || - tp->mac_version == RTL_GIGA_MAC_VER_17) && - (tp->features & RTL_FEATURE_WOL)) { - pci_clear_master(pdev); - - RTL_W8(ChipCmd, CmdRxEnb); - /* PCI commit */ - RTL_R8(ChipCmd); + if (__rtl8169_get_wol(tp) & WAKE_ANY) { + rtl_wol_suspend_quirk(tp); + rtl_wol_shutdown_quirk(tp); } pci_wake_from_d3(pdev, true); diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index b9016a30cdc5..c90ddb61cc56 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -26,6 +26,7 @@ * LAN9215, LAN9216, LAN9217, LAN9218 * LAN9210, LAN9211 * LAN9220, LAN9221 + * LAN89218 * */ @@ -1983,6 +1984,7 @@ static int __devinit smsc911x_init(struct net_device *dev) case 0x01170000: case 0x01160000: case 0x01150000: + case 0x218A0000: /* LAN911[5678] family */ pdata->generation = pdata->idrev & 0x0000FFFF; break; diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 4a1374df6084..c11a2b8327f3 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -15577,7 +15577,7 @@ static void __devexit tg3_remove_one(struct pci_dev *pdev) cancel_work_sync(&tp->reset_task); - if (!tg3_flag(tp, USE_PHYLIB)) { + if (tg3_flag(tp, USE_PHYLIB)) { tg3_phy_fini(tp); tg3_mdio_fini(tp); } diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 6fa215a38615..90832a955991 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -400,9 +400,8 @@ static int pcifront_claim_resource(struct pci_dev *dev, void *data) dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n", pci_name(dev), i); if (pci_claim_resource(dev, i)) { - dev_err(&pdev->xdev->dev, "Could not claim " - "resource %s/%d! Device offline. Try " - "giving less than 4GB to domain.\n", + dev_err(&pdev->xdev->dev, "Could not claim resource %s/%d! " + "Device offline. Try using e820_host=1 in the guest config.\n", pci_name(dev), i); } } diff --git a/drivers/pcmcia/sa1100_simpad.c b/drivers/pcmcia/sa1100_simpad.c index c998f7aaadbc..0fac9658b020 100644 --- a/drivers/pcmcia/sa1100_simpad.c +++ b/drivers/pcmcia/sa1100_simpad.c @@ -15,10 +15,6 @@ #include <mach/simpad.h> #include "sa1100_generic.h" -extern long get_cs3_shadow(void); -extern void set_cs3_bit(int value); -extern void clear_cs3_bit(int value); - static struct pcmcia_irqs irqs[] = { { 1, IRQ_GPIO_CF_CD, "CF_CD" }, }; @@ -26,7 +22,7 @@ static struct pcmcia_irqs irqs[] = { static int simpad_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { - clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); + simpad_clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); skt->socket.pci_irq = IRQ_GPIO_CF_IRQ; @@ -38,8 +34,8 @@ static void simpad_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt) soc_pcmcia_free_irqs(skt, irqs, ARRAY_SIZE(irqs)); /* Disable CF bus: */ - //set_cs3_bit(PCMCIA_BUFF_DIS); - clear_cs3_bit(PCMCIA_RESET); + /*simpad_set_cs3_bit(PCMCIA_BUFF_DIS);*/ + simpad_clear_cs3_bit(PCMCIA_RESET); } static void @@ -47,15 +43,16 @@ simpad_pcmcia_socket_state(struct soc_pcmcia_socket *skt, struct pcmcia_state *state) { unsigned long levels = GPLR; - long cs3reg = get_cs3_shadow(); + long cs3reg = simpad_get_cs3_ro(); state->detect=((levels & GPIO_CF_CD)==0)?1:0; state->ready=(levels & GPIO_CF_IRQ)?1:0; - state->bvd1=1; /* Not available on Simpad. */ - state->bvd2=1; /* Not available on Simpad. */ + state->bvd1 = 1; /* Might be cs3reg & PCMCIA_BVD1 */ + state->bvd2 = 1; /* Might be cs3reg & PCMCIA_BVD2 */ state->wrprot=0; /* Not available on Simpad. */ - - if((cs3reg & 0x0c) == 0x0c) { + + if ((cs3reg & (PCMCIA_VS1|PCMCIA_VS2)) == + (PCMCIA_VS1|PCMCIA_VS2)) { state->vs_3v=0; state->vs_Xv=0; } else { @@ -75,23 +72,23 @@ simpad_pcmcia_configure_socket(struct soc_pcmcia_socket *skt, /* Murphy: see table of MIC2562a-1 */ switch (state->Vcc) { case 0: - clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); + simpad_clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); break; case 33: - clear_cs3_bit(VCC_3V_EN|EN1); - set_cs3_bit(VCC_5V_EN|EN0); + simpad_clear_cs3_bit(VCC_3V_EN|EN1); + simpad_set_cs3_bit(VCC_5V_EN|EN0); break; case 50: - clear_cs3_bit(VCC_5V_EN|EN1); - set_cs3_bit(VCC_3V_EN|EN0); + simpad_clear_cs3_bit(VCC_5V_EN|EN1); + simpad_set_cs3_bit(VCC_3V_EN|EN0); break; default: printk(KERN_ERR "%s(): unrecognized Vcc %u\n", __func__, state->Vcc); - clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); + simpad_clear_cs3_bit(VCC_3V_EN|VCC_5V_EN|EN0|EN1); local_irq_restore(flags); return -1; } @@ -110,7 +107,7 @@ static void simpad_pcmcia_socket_init(struct soc_pcmcia_socket *skt) static void simpad_pcmcia_socket_suspend(struct soc_pcmcia_socket *skt) { soc_pcmcia_disable_irqs(skt, irqs, ARRAY_SIZE(irqs)); - set_cs3_bit(PCMCIA_RESET); + simpad_set_cs3_bit(PCMCIA_RESET); } static struct pcmcia_low_level simpad_pcmcia_ops = { diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index c4ea3a9a555b..39f021b855ef 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -63,6 +63,7 @@ u32 sas_get_pr_transport_id( unsigned char *buf) { unsigned char *ptr; + int ret; /* * Set PROTOCOL IDENTIFIER to 6h for SAS @@ -74,7 +75,9 @@ u32 sas_get_pr_transport_id( */ ptr = &se_nacl->initiatorname[4]; /* Skip over 'naa. prefix */ - hex2bin(&buf[4], ptr, 8); + ret = hex2bin(&buf[4], ptr, 8); + if (ret < 0) + pr_debug("sas transport_id: invalid hex string\n"); /* * The SAS Transport ID is a hardcoded 24-byte length @@ -156,8 +159,9 @@ u32 fc_get_pr_transport_id( unsigned char *buf) { unsigned char *ptr; - int i; + int i, ret; u32 off = 8; + /* * PROTOCOL IDENTIFIER is 0h for FCP-2 * @@ -174,7 +178,9 @@ u32 fc_get_pr_transport_id( i++; continue; } - hex2bin(&buf[off++], &ptr[i], 1); + ret = hex2bin(&buf[off++], &ptr[i], 1); + if (ret < 0) + pr_debug("fc transport_id: invalid hex string\n"); i += 2; } /* diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 5f7ff8e2fc14..8795480c2350 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -137,16 +137,6 @@ config XEN_GRANT_DEV_ALLOC to other domains. This can be used to implement frontend drivers or as part of an inter-domain shared memory channel. -config XEN_PLATFORM_PCI - tristate "xen platform pci device driver" - depends on XEN_PVHVM && PCI - default m - help - Driver for the Xen PCI Platform device: it is responsible for - initializing xenbus and grant_table when running in a Xen HVM - domain. As a consequence this driver is required to run any Xen PV - frontend on Xen HVM. - config SWIOTLB_XEN def_bool y depends on PCI diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 72bbb27d7a68..974fffdf22b2 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_XEN_GNTDEV) += xen-gntdev.o obj-$(CONFIG_XEN_GRANT_DEV_ALLOC) += xen-gntalloc.o obj-$(CONFIG_XENFS) += xenfs/ obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o -obj-$(CONFIG_XEN_PLATFORM_PCI) += xen-platform-pci.o +obj-$(CONFIG_XEN_PVHVM) += platform-pci.o obj-$(CONFIG_XEN_TMEM) += tmem.o obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o obj-$(CONFIG_XEN_DOM0) += pci.o @@ -23,5 +23,3 @@ obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/ xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o - -xen-platform-pci-y := platform-pci.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 5dfd8f8ff07f..5876e1ae6c2d 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -501,20 +501,24 @@ EXPORT_SYMBOL_GPL(balloon_set_new_target); * alloc_xenballooned_pages - get pages that have been ballooned out * @nr_pages: Number of pages to get * @pages: pages returned + * @highmem: highmem or lowmem pages * @return 0 on success, error otherwise */ -int alloc_xenballooned_pages(int nr_pages, struct page** pages) +int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem) { int pgno = 0; struct page* page; mutex_lock(&balloon_mutex); while (pgno < nr_pages) { - page = balloon_retrieve(true); - if (page) { + page = balloon_retrieve(highmem); + if (page && PageHighMem(page) == highmem) { pages[pgno++] = page; } else { enum bp_state st; - st = decrease_reservation(nr_pages - pgno, GFP_HIGHUSER); + if (page) + balloon_append(page); + st = decrease_reservation(nr_pages - pgno, + highmem ? GFP_HIGHUSER : GFP_USER); if (st != BP_DONE) goto out_undo; } @@ -555,17 +559,40 @@ void free_xenballooned_pages(int nr_pages, struct page** pages) } EXPORT_SYMBOL(free_xenballooned_pages); -static int __init balloon_init(void) +static void __init balloon_add_region(unsigned long start_pfn, + unsigned long pages) { unsigned long pfn, extra_pfn_end; struct page *page; + /* + * If the amount of usable memory has been limited (e.g., with + * the 'mem' command line parameter), don't add pages beyond + * this limit. + */ + extra_pfn_end = min(max_pfn, start_pfn + pages); + + for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { + page = pfn_to_page(pfn); + /* totalram_pages and totalhigh_pages do not + include the boot-time balloon extension, so + don't subtract from it. */ + __balloon_append(page); + } +} + +static int __init balloon_init(void) +{ + int i; + if (!xen_domain()) return -ENODEV; pr_info("xen/balloon: Initialising balloon driver.\n"); - balloon_stats.current_pages = xen_pv_domain() ? min(xen_start_info->nr_pages, max_pfn) : max_pfn; + balloon_stats.current_pages = xen_pv_domain() + ? min(xen_start_info->nr_pages - xen_released_pages, max_pfn) + : max_pfn; balloon_stats.target_pages = balloon_stats.current_pages; balloon_stats.balloon_low = 0; balloon_stats.balloon_high = 0; @@ -584,24 +611,13 @@ static int __init balloon_init(void) #endif /* - * Initialise the balloon with excess memory space. We need - * to make sure we don't add memory which doesn't exist or - * logically exist. The E820 map can be trimmed to be smaller - * than the amount of physical memory due to the mem= command - * line parameter. And if this is a 32-bit non-HIGHMEM kernel - * on a system with memory which requires highmem to access, - * don't try to use it. + * Initialize the balloon with pages from the extra memory + * regions (see arch/x86/xen/setup.c). */ - extra_pfn_end = min(min(max_pfn, e820_end_of_ram_pfn()), - (unsigned long)PFN_DOWN(xen_extra_mem_start + xen_extra_mem_size)); - for (pfn = PFN_UP(xen_extra_mem_start); - pfn < extra_pfn_end; - pfn++) { - page = pfn_to_page(pfn); - /* totalram_pages and totalhigh_pages do not include the boot-time - balloon extension, so don't subtract from it. */ - __balloon_append(page); - } + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) + if (xen_extra_mem[i].size) + balloon_add_region(PFN_UP(xen_extra_mem[i].start), + PFN_DOWN(xen_extra_mem[i].size)); return 0; } diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 7523719bf8a4..7a55b292bf39 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -432,7 +432,8 @@ static int __must_check xen_allocate_irq_dynamic(void) irq = irq_alloc_desc_from(first, -1); - xen_irq_init(irq); + if (irq >= 0) + xen_irq_init(irq); return irq; } @@ -713,7 +714,7 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, mutex_lock(&irq_mapping_update_lock); irq = xen_allocate_irq_dynamic(); - if (irq == -1) + if (irq < 0) goto out; irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq, @@ -729,7 +730,7 @@ out: error_irq: mutex_unlock(&irq_mapping_update_lock); xen_free_irq(irq); - return -1; + return ret; } #endif @@ -779,7 +780,7 @@ int xen_irq_from_pirq(unsigned pirq) mutex_lock(&irq_mapping_update_lock); list_for_each_entry(info, &xen_irq_list_head, list) { - if (info == NULL || info->type != IRQT_PIRQ) + if (info->type != IRQT_PIRQ) continue; irq = info->irq; if (info->u.pirq.pirq == pirq) @@ -872,11 +873,32 @@ static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, return err ? : bind_evtchn_to_irq(bind_interdomain.local_port); } +static int find_virq(unsigned int virq, unsigned int cpu) +{ + struct evtchn_status status; + int port, rc = -ENOENT; + + memset(&status, 0, sizeof(status)); + for (port = 0; port <= NR_EVENT_CHANNELS; port++) { + status.dom = DOMID_SELF; + status.port = port; + rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status); + if (rc < 0) + continue; + if (status.status != EVTCHNSTAT_virq) + continue; + if (status.u.virq == virq && status.vcpu == cpu) { + rc = port; + break; + } + } + return rc; +} int bind_virq_to_irq(unsigned int virq, unsigned int cpu) { struct evtchn_bind_virq bind_virq; - int evtchn, irq; + int evtchn, irq, ret; mutex_lock(&irq_mapping_update_lock); @@ -892,10 +914,16 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu) bind_virq.virq = virq; bind_virq.vcpu = cpu; - if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq, - &bind_virq) != 0) - BUG(); - evtchn = bind_virq.port; + ret = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq, + &bind_virq); + if (ret == 0) + evtchn = bind_virq.port; + else { + if (ret == -EEXIST) + ret = find_virq(virq, cpu); + BUG_ON(ret < 0); + evtchn = ret; + } xen_irq_info_virq_init(cpu, irq, evtchn, virq); @@ -1670,6 +1698,7 @@ void __init xen_init_IRQ(void) evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq), GFP_KERNEL); + BUG_ON(!evtchn_to_irq); for (i = 0; i < NR_EVENT_CHANNELS; i++) evtchn_to_irq[i] = -1; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index f914b26cf0c2..880798aae2f2 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -83,6 +83,7 @@ struct grant_map { struct ioctl_gntdev_grant_ref *grants; struct gnttab_map_grant_ref *map_ops; struct gnttab_unmap_grant_ref *unmap_ops; + struct gnttab_map_grant_ref *kmap_ops; struct page **pages; }; @@ -116,19 +117,22 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count) add->grants = kzalloc(sizeof(add->grants[0]) * count, GFP_KERNEL); add->map_ops = kzalloc(sizeof(add->map_ops[0]) * count, GFP_KERNEL); add->unmap_ops = kzalloc(sizeof(add->unmap_ops[0]) * count, GFP_KERNEL); + add->kmap_ops = kzalloc(sizeof(add->kmap_ops[0]) * count, GFP_KERNEL); add->pages = kzalloc(sizeof(add->pages[0]) * count, GFP_KERNEL); if (NULL == add->grants || NULL == add->map_ops || NULL == add->unmap_ops || + NULL == add->kmap_ops || NULL == add->pages) goto err; - if (alloc_xenballooned_pages(count, add->pages)) + if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */)) goto err; for (i = 0; i < count; i++) { add->map_ops[i].handle = -1; add->unmap_ops[i].handle = -1; + add->kmap_ops[i].handle = -1; } add->index = 0; @@ -142,6 +146,7 @@ err: kfree(add->grants); kfree(add->map_ops); kfree(add->unmap_ops); + kfree(add->kmap_ops); kfree(add); return NULL; } @@ -243,10 +248,35 @@ static int map_grant_pages(struct grant_map *map) gnttab_set_unmap_op(&map->unmap_ops[i], addr, map->flags, -1 /* handle */); } + } else { + /* + * Setup the map_ops corresponding to the pte entries pointing + * to the kernel linear addresses of the struct pages. + * These ptes are completely different from the user ptes dealt + * with find_grant_ptes. + */ + for (i = 0; i < map->count; i++) { + unsigned level; + unsigned long address = (unsigned long) + pfn_to_kaddr(page_to_pfn(map->pages[i])); + pte_t *ptep; + u64 pte_maddr = 0; + BUG_ON(PageHighMem(map->pages[i])); + + ptep = lookup_address(address, &level); + pte_maddr = arbitrary_virt_to_machine(ptep).maddr; + gnttab_set_map_op(&map->kmap_ops[i], pte_maddr, + map->flags | + GNTMAP_host_map | + GNTMAP_contains_pte, + map->grants[i].ref, + map->grants[i].domid); + } } pr_debug("map %d+%d\n", map->index, map->count); - err = gnttab_map_refs(map->map_ops, map->pages, map->count); + err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL, + map->pages, map->count); if (err) return err; @@ -462,13 +492,11 @@ static int gntdev_release(struct inode *inode, struct file *flip) pr_debug("priv %p\n", priv); - spin_lock(&priv->lock); while (!list_empty(&priv->maps)) { map = list_entry(priv->maps.next, struct grant_map, next); list_del(&map->next); gntdev_put_map(map); } - spin_unlock(&priv->lock); if (use_ptemod) mmu_notifier_unregister(&priv->mn, priv->mm); @@ -532,10 +560,11 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv, map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count); if (map) { list_del(&map->next); - gntdev_put_map(map); err = 0; } spin_unlock(&priv->lock); + if (map) + gntdev_put_map(map); return err; } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 4f44b347b24a..8c71ab801756 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -448,7 +448,8 @@ unsigned int gnttab_max_grant_frames(void) EXPORT_SYMBOL_GPL(gnttab_max_grant_frames); int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, - struct page **pages, unsigned int count) + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) { int i, ret; pte_t *pte; @@ -488,8 +489,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, */ return -EOPNOTSUPP; } - ret = m2p_add_override(mfn, pages[i], - map_ops[i].flags & GNTMAP_contains_pte); + ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]); if (ret) return ret; } diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index cef4bafc07dc..66057075d6e2 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -18,6 +18,7 @@ */ #include <linux/pci.h> +#include <linux/acpi.h> #include <xen/xen.h> #include <xen/interface/physdev.h> #include <xen/interface/xen.h> @@ -26,26 +27,85 @@ #include <asm/xen/hypercall.h> #include "../pci/pci.h" +static bool __read_mostly pci_seg_supported = true; + static int xen_add_device(struct device *dev) { int r; struct pci_dev *pci_dev = to_pci_dev(dev); +#ifdef CONFIG_PCI_IOV + struct pci_dev *physfn = pci_dev->physfn; +#endif + + if (pci_seg_supported) { + struct physdev_pci_device_add add = { + .seg = pci_domain_nr(pci_dev->bus), + .bus = pci_dev->bus->number, + .devfn = pci_dev->devfn + }; +#ifdef CONFIG_ACPI + acpi_handle handle; +#endif + +#ifdef CONFIG_PCI_IOV + if (pci_dev->is_virtfn) { + add.flags = XEN_PCI_DEV_VIRTFN; + add.physfn.bus = physfn->bus->number; + add.physfn.devfn = physfn->devfn; + } else +#endif + if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) + add.flags = XEN_PCI_DEV_EXTFN; + +#ifdef CONFIG_ACPI + handle = DEVICE_ACPI_HANDLE(&pci_dev->dev); + if (!handle) + handle = DEVICE_ACPI_HANDLE(pci_dev->bus->bridge); +#ifdef CONFIG_PCI_IOV + if (!handle && pci_dev->is_virtfn) + handle = DEVICE_ACPI_HANDLE(physfn->bus->bridge); +#endif + if (handle) { + acpi_status status; + + do { + unsigned long long pxm; + + status = acpi_evaluate_integer(handle, "_PXM", + NULL, &pxm); + if (ACPI_SUCCESS(status)) { + add.optarr[0] = pxm; + add.flags |= XEN_PCI_DEV_PXM; + break; + } + status = acpi_get_parent(handle, &handle); + } while (ACPI_SUCCESS(status)); + } +#endif /* CONFIG_ACPI */ + + r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_add, &add); + if (r != -ENOSYS) + return r; + pci_seg_supported = false; + } + if (pci_domain_nr(pci_dev->bus)) + r = -ENOSYS; #ifdef CONFIG_PCI_IOV - if (pci_dev->is_virtfn) { + else if (pci_dev->is_virtfn) { struct physdev_manage_pci_ext manage_pci_ext = { .bus = pci_dev->bus->number, .devfn = pci_dev->devfn, .is_virtfn = 1, - .physfn.bus = pci_dev->physfn->bus->number, - .physfn.devfn = pci_dev->physfn->devfn, + .physfn.bus = physfn->bus->number, + .physfn.devfn = physfn->devfn, }; r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext, &manage_pci_ext); - } else + } #endif - if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) { + else if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) { struct physdev_manage_pci_ext manage_pci_ext = { .bus = pci_dev->bus->number, .devfn = pci_dev->devfn, @@ -71,13 +131,27 @@ static int xen_remove_device(struct device *dev) { int r; struct pci_dev *pci_dev = to_pci_dev(dev); - struct physdev_manage_pci manage_pci; - manage_pci.bus = pci_dev->bus->number; - manage_pci.devfn = pci_dev->devfn; + if (pci_seg_supported) { + struct physdev_pci_device device = { + .seg = pci_domain_nr(pci_dev->bus), + .bus = pci_dev->bus->number, + .devfn = pci_dev->devfn + }; - r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove, - &manage_pci); + r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_remove, + &device); + } else if (pci_domain_nr(pci_dev->bus)) + r = -ENOSYS; + else { + struct physdev_manage_pci manage_pci = { + .bus = pci_dev->bus->number, + .devfn = pci_dev->devfn + }; + + r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove, + &manage_pci); + } return r; } @@ -96,13 +170,16 @@ static int xen_pci_notifier(struct notifier_block *nb, r = xen_remove_device(dev); break; default: - break; + return NOTIFY_DONE; } - - return r; + if (r) + dev_err(dev, "Failed to %s - passthrough or MSI/MSI-X might fail!\n", + action == BUS_NOTIFY_ADD_DEVICE ? "add" : + (action == BUS_NOTIFY_DEL_DEVICE ? "delete" : "?")); + return NOTIFY_OK; } -struct notifier_block device_nb = { +static struct notifier_block device_nb = { .notifier_call = xen_pci_notifier, }; diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 6e8c15a23201..c984768d98ca 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -38,6 +38,7 @@ #include <xen/swiotlb-xen.h> #include <xen/page.h> #include <xen/xen-ops.h> +#include <xen/hvc-console.h> /* * Used to do a quick range check in swiotlb_tbl_unmap_single and * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this @@ -146,8 +147,10 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs) void __init xen_swiotlb_init(int verbose) { unsigned long bytes; - int rc; + int rc = -ENOMEM; unsigned long nr_tbl; + char *m = NULL; + unsigned int repeat = 3; nr_tbl = swioltb_nr_tbl(); if (nr_tbl) @@ -156,16 +159,17 @@ void __init xen_swiotlb_init(int verbose) xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT); xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE); } - +retry: bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT; /* * Get IO TLB memory from any location. */ xen_io_tlb_start = alloc_bootmem(bytes); - if (!xen_io_tlb_start) - panic("Cannot allocate SWIOTLB buffer"); - + if (!xen_io_tlb_start) { + m = "Cannot allocate Xen-SWIOTLB buffer!\n"; + goto error; + } xen_io_tlb_end = xen_io_tlb_start + bytes; /* * And replace that memory with pages under 4GB. @@ -173,17 +177,28 @@ void __init xen_swiotlb_init(int verbose) rc = xen_swiotlb_fixup(xen_io_tlb_start, bytes, xen_io_tlb_nslabs); - if (rc) + if (rc) { + free_bootmem(__pa(xen_io_tlb_start), bytes); + m = "Failed to get contiguous memory for DMA from Xen!\n"\ + "You either: don't have the permissions, do not have"\ + " enough free memory under 4GB, or the hypervisor memory"\ + "is too fragmented!"; goto error; - + } start_dma_addr = xen_virt_to_bus(xen_io_tlb_start); swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose); return; error: - panic("DMA(%d): Failed to exchange pages allocated for DMA with Xen! "\ - "We either don't have the permission or you do not have enough"\ - "free memory under 4GB!\n", rc); + if (repeat--) { + xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */ + (xen_io_tlb_nslabs >> 1)); + printk(KERN_INFO "Xen-SWIOTLB: Lowering to %luMB\n", + (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20); + goto retry; + } + xen_raw_printk("%s (rc:%d)", m, rc); + panic("%s (rc:%d)", m, rc); } void * @@ -194,6 +209,8 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size, int order = get_order(size); u64 dma_mask = DMA_BIT_MASK(32); unsigned long vstart; + phys_addr_t phys; + dma_addr_t dev_addr; /* * Ignore region specifiers - the kernel's ideas of @@ -209,18 +226,26 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size, vstart = __get_free_pages(flags, order); ret = (void *)vstart; + if (!ret) + return ret; + if (hwdev && hwdev->coherent_dma_mask) - dma_mask = dma_alloc_coherent_mask(hwdev, flags); + dma_mask = hwdev->coherent_dma_mask; - if (ret) { + phys = virt_to_phys(ret); + dev_addr = xen_phys_to_bus(phys); + if (((dev_addr + size - 1 <= dma_mask)) && + !range_straddles_page_boundary(phys, size)) + *dma_handle = dev_addr; + else { if (xen_create_contiguous_region(vstart, order, fls64(dma_mask)) != 0) { free_pages(vstart, order); return NULL; } - memset(ret, 0, size); *dma_handle = virt_to_machine(ret).maddr; } + memset(ret, 0, size); return ret; } EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent); @@ -230,11 +255,21 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dev_addr) { int order = get_order(size); + phys_addr_t phys; + u64 dma_mask = DMA_BIT_MASK(32); if (dma_release_from_coherent(hwdev, order, vaddr)) return; - xen_destroy_contiguous_region((unsigned long)vaddr, order); + if (hwdev && hwdev->coherent_dma_mask) + dma_mask = hwdev->coherent_dma_mask; + + phys = virt_to_phys(vaddr); + + if (((dev_addr + size - 1 > dma_mask)) || + range_straddles_page_boundary(phys, size)) + xen_destroy_contiguous_region((unsigned long)vaddr, order); + free_pages((unsigned long)vaddr, order); } EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent); @@ -278,9 +313,10 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, /* * Ensure that the address returned is DMA'ble */ - if (!dma_capable(dev, dev_addr, size)) - panic("map_single: bounce buffer is not DMA'ble"); - + if (!dma_capable(dev, dev_addr, size)) { + swiotlb_tbl_unmap_single(dev, map, size, dir); + dev_addr = 0; + } return dev_addr; } EXPORT_SYMBOL_GPL(xen_swiotlb_map_page); diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index a8031445d94e..444345afbd5c 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -15,7 +15,6 @@ #include "conf_space.h" #include "conf_space_quirks.h" -#define DRV_NAME "xen-pciback" static int permissive; module_param(permissive, bool, 0644); diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index da3cbdfcb5dc..3daf862d739d 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -15,7 +15,6 @@ struct pci_bar_info { int which; }; -#define DRV_NAME "xen-pciback" #define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO)) #define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER) @@ -25,7 +24,7 @@ static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data) int ret; ret = xen_pcibk_read_config_word(dev, offset, value, data); - if (!atomic_read(&dev->enable_cnt)) + if (!pci_is_enabled(dev)) return ret; for (i = 0; i < PCI_ROM_RESOURCE; i++) { @@ -187,7 +186,7 @@ static inline void read_dev_bar(struct pci_dev *dev, bar_info->val = res[pos].start | (res[pos].flags & PCI_REGION_FLAG_MASK); - bar_info->len_val = res[pos].end - res[pos].start + 1; + bar_info->len_val = resource_size(&res[pos]); } static void *bar_init(struct pci_dev *dev, int offset) diff --git a/drivers/xen/xen-pciback/conf_space_quirks.c b/drivers/xen/xen-pciback/conf_space_quirks.c index 921a889e65eb..7476791cab40 100644 --- a/drivers/xen/xen-pciback/conf_space_quirks.c +++ b/drivers/xen/xen-pciback/conf_space_quirks.c @@ -12,7 +12,6 @@ #include "conf_space_quirks.h" LIST_HEAD(xen_pcibk_quirks); -#define DRV_NAME "xen-pciback" static inline const struct pci_device_id * match_one_device(const struct pci_device_id *id, const struct pci_dev *dev) { @@ -36,7 +35,7 @@ static struct xen_pcibk_config_quirk *xen_pcibk_find_quirk(struct pci_dev *dev) goto out; tmp_quirk = NULL; printk(KERN_DEBUG DRV_NAME - ":quirk didn't match any device xen_pciback knows about\n"); + ": quirk didn't match any device known\n"); out: return tmp_quirk; } diff --git a/drivers/xen/xen-pciback/passthrough.c b/drivers/xen/xen-pciback/passthrough.c index 1d32a9a42c01..828dddc360df 100644 --- a/drivers/xen/xen-pciback/passthrough.c +++ b/drivers/xen/xen-pciback/passthrough.c @@ -7,13 +7,13 @@ #include <linux/list.h> #include <linux/pci.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> #include "pciback.h" struct passthrough_dev_data { /* Access to dev_list must be protected by lock */ struct list_head dev_list; - spinlock_t lock; + struct mutex lock; }; static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, @@ -24,9 +24,8 @@ static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, struct passthrough_dev_data *dev_data = pdev->pci_dev_data; struct pci_dev_entry *dev_entry; struct pci_dev *dev = NULL; - unsigned long flags; - spin_lock_irqsave(&dev_data->lock, flags); + mutex_lock(&dev_data->lock); list_for_each_entry(dev_entry, &dev_data->dev_list, list) { if (domain == (unsigned int)pci_domain_nr(dev_entry->dev->bus) @@ -37,7 +36,7 @@ static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, } } - spin_unlock_irqrestore(&dev_data->lock, flags); + mutex_unlock(&dev_data->lock); return dev; } @@ -48,7 +47,6 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, { struct passthrough_dev_data *dev_data = pdev->pci_dev_data; struct pci_dev_entry *dev_entry; - unsigned long flags; unsigned int domain, bus, devfn; int err; @@ -57,9 +55,9 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, return -ENOMEM; dev_entry->dev = dev; - spin_lock_irqsave(&dev_data->lock, flags); + mutex_lock(&dev_data->lock); list_add_tail(&dev_entry->list, &dev_data->dev_list); - spin_unlock_irqrestore(&dev_data->lock, flags); + mutex_unlock(&dev_data->lock); /* Publish this device. */ domain = (unsigned int)pci_domain_nr(dev->bus); @@ -76,9 +74,8 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, struct passthrough_dev_data *dev_data = pdev->pci_dev_data; struct pci_dev_entry *dev_entry, *t; struct pci_dev *found_dev = NULL; - unsigned long flags; - spin_lock_irqsave(&dev_data->lock, flags); + mutex_lock(&dev_data->lock); list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) { if (dev_entry->dev == dev) { @@ -88,7 +85,7 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, } } - spin_unlock_irqrestore(&dev_data->lock, flags); + mutex_unlock(&dev_data->lock); if (found_dev) pcistub_put_pci_dev(found_dev); @@ -102,7 +99,7 @@ static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev) if (!dev_data) return -ENOMEM; - spin_lock_init(&dev_data->lock); + mutex_init(&dev_data->lock); INIT_LIST_HEAD(&dev_data->dev_list); @@ -116,14 +113,14 @@ static int __xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev, { int err = 0; struct passthrough_dev_data *dev_data = pdev->pci_dev_data; - struct pci_dev_entry *dev_entry, *e, *tmp; + struct pci_dev_entry *dev_entry, *e; struct pci_dev *dev; int found; unsigned int domain, bus; - spin_lock(&dev_data->lock); + mutex_lock(&dev_data->lock); - list_for_each_entry_safe(dev_entry, tmp, &dev_data->dev_list, list) { + list_for_each_entry(dev_entry, &dev_data->dev_list, list) { /* Only publish this device as a root if none of its * parent bridges are exported */ @@ -142,16 +139,13 @@ static int __xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev, bus = (unsigned int)dev_entry->dev->bus->number; if (!found) { - spin_unlock(&dev_data->lock); err = publish_root_cb(pdev, domain, bus); if (err) break; - spin_lock(&dev_data->lock); } } - if (!err) - spin_unlock(&dev_data->lock); + mutex_unlock(&dev_data->lock); return err; } @@ -182,7 +176,7 @@ static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev, return 1; } -struct xen_pcibk_backend xen_pcibk_passthrough_backend = { +const struct xen_pcibk_backend xen_pcibk_passthrough_backend = { .name = "passthrough", .init = __xen_pcibk_init_devices, .free = __xen_pcibk_release_devices, diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index aec214ac0a14..8f06e1ed028c 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -21,8 +21,6 @@ #include "conf_space.h" #include "conf_space_quirks.h" -#define DRV_NAME "xen-pciback" - static char *pci_devs_to_hide; wait_queue_head_t xen_pcibk_aer_wait_queue; /*Add sem for sync AER handling and xen_pcibk remove/reconfigue ops, @@ -222,6 +220,8 @@ void pcistub_put_pci_dev(struct pci_dev *dev) } spin_unlock_irqrestore(&pcistub_devices_lock, flags); + if (WARN_ON(!found_psdev)) + return; /*hold this lock for avoiding breaking link between * pcistub and xen_pcibk when AER is in processing @@ -514,12 +514,9 @@ static void kill_domain_by_device(struct pcistub_device *psdev) int err; char nodename[PCI_NODENAME_MAX]; - if (!psdev) - dev_err(&psdev->dev->dev, - "device is NULL when do AER recovery/kill_domain\n"); + BUG_ON(!psdev); snprintf(nodename, PCI_NODENAME_MAX, "/local/domain/0/backend/pci/%d/0", psdev->pdev->xdev->otherend_id); - nodename[strlen(nodename)] = '\0'; again: err = xenbus_transaction_start(&xbt); @@ -605,7 +602,7 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, if (test_bit(_XEN_PCIF_active, (unsigned long *)&psdev->pdev->sh_info->flags)) { dev_dbg(&psdev->dev->dev, - "schedule pci_conf service in xen_pcibk\n"); + "schedule pci_conf service in " DRV_NAME "\n"); xen_pcibk_test_and_schedule_op(psdev->pdev); } @@ -995,8 +992,7 @@ out: err = count; return err; } - -DRIVER_ATTR(new_slot, S_IWUSR, NULL, pcistub_slot_add); +static DRIVER_ATTR(new_slot, S_IWUSR, NULL, pcistub_slot_add); static ssize_t pcistub_slot_remove(struct device_driver *drv, const char *buf, size_t count) @@ -1015,8 +1011,7 @@ out: err = count; return err; } - -DRIVER_ATTR(remove_slot, S_IWUSR, NULL, pcistub_slot_remove); +static DRIVER_ATTR(remove_slot, S_IWUSR, NULL, pcistub_slot_remove); static ssize_t pcistub_slot_show(struct device_driver *drv, char *buf) { @@ -1039,8 +1034,7 @@ static ssize_t pcistub_slot_show(struct device_driver *drv, char *buf) return count; } - -DRIVER_ATTR(slots, S_IRUSR, pcistub_slot_show, NULL); +static DRIVER_ATTR(slots, S_IRUSR, pcistub_slot_show, NULL); static ssize_t pcistub_irq_handler_show(struct device_driver *drv, char *buf) { @@ -1069,8 +1063,7 @@ static ssize_t pcistub_irq_handler_show(struct device_driver *drv, char *buf) spin_unlock_irqrestore(&pcistub_devices_lock, flags); return count; } - -DRIVER_ATTR(irq_handlers, S_IRUSR, pcistub_irq_handler_show, NULL); +static DRIVER_ATTR(irq_handlers, S_IRUSR, pcistub_irq_handler_show, NULL); static ssize_t pcistub_irq_handler_switch(struct device_driver *drv, const char *buf, @@ -1106,7 +1099,8 @@ out: err = count; return err; } -DRIVER_ATTR(irq_handler_state, S_IWUSR, NULL, pcistub_irq_handler_switch); +static DRIVER_ATTR(irq_handler_state, S_IWUSR, NULL, + pcistub_irq_handler_switch); static ssize_t pcistub_quirk_add(struct device_driver *drv, const char *buf, size_t count) @@ -1170,8 +1164,8 @@ out: return count; } - -DRIVER_ATTR(quirks, S_IRUSR | S_IWUSR, pcistub_quirk_show, pcistub_quirk_add); +static DRIVER_ATTR(quirks, S_IRUSR | S_IWUSR, pcistub_quirk_show, + pcistub_quirk_add); static ssize_t permissive_add(struct device_driver *drv, const char *buf, size_t count) @@ -1236,8 +1230,8 @@ static ssize_t permissive_show(struct device_driver *drv, char *buf) spin_unlock_irqrestore(&pcistub_devices_lock, flags); return count; } - -DRIVER_ATTR(permissive, S_IRUSR | S_IWUSR, permissive_show, permissive_add); +static DRIVER_ATTR(permissive, S_IRUSR | S_IWUSR, permissive_show, + permissive_add); static void pcistub_exit(void) { @@ -1374,3 +1368,4 @@ module_init(xen_pcibk_init); module_exit(xen_pcibk_cleanup); MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("xen-backend:pci"); diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index a0e131a81503..e9b4011c5f9a 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -15,6 +15,8 @@ #include <linux/atomic.h> #include <xen/interface/io/pciif.h> +#define DRV_NAME "xen-pciback" + struct pci_dev_entry { struct list_head list; struct pci_dev *dev; @@ -27,7 +29,7 @@ struct pci_dev_entry { struct xen_pcibk_device { void *pci_dev_data; - spinlock_t dev_lock; + struct mutex dev_lock; struct xenbus_device *xdev; struct xenbus_watch be_watch; u8 be_watching; @@ -89,7 +91,7 @@ typedef int (*publish_pci_root_cb) (struct xen_pcibk_device *pdev, * passthrough - BDFs are exactly like in the host. */ struct xen_pcibk_backend { - char *name; + const char *name; int (*init)(struct xen_pcibk_device *pdev); void (*free)(struct xen_pcibk_device *pdev); int (*find)(struct pci_dev *pcidev, struct xen_pcibk_device *pdev, @@ -104,9 +106,9 @@ struct xen_pcibk_backend { unsigned int devfn); }; -extern struct xen_pcibk_backend xen_pcibk_vpci_backend; -extern struct xen_pcibk_backend xen_pcibk_passthrough_backend; -extern struct xen_pcibk_backend *xen_pcibk_backend; +extern const struct xen_pcibk_backend xen_pcibk_vpci_backend; +extern const struct xen_pcibk_backend xen_pcibk_passthrough_backend; +extern const struct xen_pcibk_backend *xen_pcibk_backend; static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev, @@ -116,13 +118,14 @@ static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, if (xen_pcibk_backend && xen_pcibk_backend->add) return xen_pcibk_backend->add(pdev, dev, devid, publish_cb); return -1; -}; +} + static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev) { if (xen_pcibk_backend && xen_pcibk_backend->free) return xen_pcibk_backend->release(pdev, dev); -}; +} static inline struct pci_dev * xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, unsigned int domain, @@ -131,7 +134,8 @@ xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, unsigned int domain, if (xen_pcibk_backend && xen_pcibk_backend->get) return xen_pcibk_backend->get(pdev, domain, bus, devfn); return NULL; -}; +} + /** * Add for domain0 PCIE-AER handling. Get guest domain/bus/devfn in xen_pcibk * before sending aer request to pcifront, so that guest could identify @@ -148,25 +152,29 @@ static inline int xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev, return xen_pcibk_backend->find(pcidev, pdev, domain, bus, devfn); return -1; -}; +} + static inline int xen_pcibk_init_devices(struct xen_pcibk_device *pdev) { if (xen_pcibk_backend && xen_pcibk_backend->init) return xen_pcibk_backend->init(pdev); return -1; -}; +} + static inline int xen_pcibk_publish_pci_roots(struct xen_pcibk_device *pdev, publish_pci_root_cb cb) { if (xen_pcibk_backend && xen_pcibk_backend->publish) return xen_pcibk_backend->publish(pdev, cb); return -1; -}; +} + static inline void xen_pcibk_release_devices(struct xen_pcibk_device *pdev) { if (xen_pcibk_backend && xen_pcibk_backend->free) return xen_pcibk_backend->free(pdev); -}; +} + /* Handles events from front-end */ irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id); void xen_pcibk_do_op(struct work_struct *data); diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 8c95c3415b75..63616d7453e6 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -10,7 +10,6 @@ #include <linux/sched.h> #include "pciback.h" -#define DRV_NAME "xen-pciback" int verbose_request; module_param(verbose_request, int, 0644); diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c index 4a42cfb0959d..46d140baebd8 100644 --- a/drivers/xen/xen-pciback/vpci.c +++ b/drivers/xen/xen-pciback/vpci.c @@ -8,16 +8,15 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/pci.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> #include "pciback.h" #define PCI_SLOT_MAX 32 -#define DRV_NAME "xen-pciback" struct vpci_dev_data { /* Access to dev_list must be protected by lock */ struct list_head dev_list[PCI_SLOT_MAX]; - spinlock_t lock; + struct mutex lock; }; static inline struct list_head *list_first(struct list_head *head) @@ -33,13 +32,12 @@ static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev_entry *entry; struct pci_dev *dev = NULL; struct vpci_dev_data *vpci_dev = pdev->pci_dev_data; - unsigned long flags; if (domain != 0 || bus != 0) return NULL; if (PCI_SLOT(devfn) < PCI_SLOT_MAX) { - spin_lock_irqsave(&vpci_dev->lock, flags); + mutex_lock(&vpci_dev->lock); list_for_each_entry(entry, &vpci_dev->dev_list[PCI_SLOT(devfn)], @@ -50,7 +48,7 @@ static struct pci_dev *__xen_pcibk_get_pci_dev(struct xen_pcibk_device *pdev, } } - spin_unlock_irqrestore(&vpci_dev->lock, flags); + mutex_unlock(&vpci_dev->lock); } return dev; } @@ -71,7 +69,6 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, int err = 0, slot, func = -1; struct pci_dev_entry *t, *dev_entry; struct vpci_dev_data *vpci_dev = pdev->pci_dev_data; - unsigned long flags; if ((dev->class >> 24) == PCI_BASE_CLASS_BRIDGE) { err = -EFAULT; @@ -90,7 +87,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, dev_entry->dev = dev; - spin_lock_irqsave(&vpci_dev->lock, flags); + mutex_lock(&vpci_dev->lock); /* Keep multi-function devices together on the virtual PCI bus */ for (slot = 0; slot < PCI_SLOT_MAX; slot++) { @@ -129,7 +126,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, "No more space on root virtual PCI bus"); unlock: - spin_unlock_irqrestore(&vpci_dev->lock, flags); + mutex_unlock(&vpci_dev->lock); /* Publish this device. */ if (!err) @@ -145,14 +142,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, int slot; struct vpci_dev_data *vpci_dev = pdev->pci_dev_data; struct pci_dev *found_dev = NULL; - unsigned long flags; - spin_lock_irqsave(&vpci_dev->lock, flags); + mutex_lock(&vpci_dev->lock); for (slot = 0; slot < PCI_SLOT_MAX; slot++) { - struct pci_dev_entry *e, *tmp; - list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot], - list) { + struct pci_dev_entry *e; + + list_for_each_entry(e, &vpci_dev->dev_list[slot], list) { if (e->dev == dev) { list_del(&e->list); found_dev = e->dev; @@ -163,7 +159,7 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, } out: - spin_unlock_irqrestore(&vpci_dev->lock, flags); + mutex_unlock(&vpci_dev->lock); if (found_dev) pcistub_put_pci_dev(found_dev); @@ -178,7 +174,7 @@ static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev) if (!vpci_dev) return -ENOMEM; - spin_lock_init(&vpci_dev->lock); + mutex_init(&vpci_dev->lock); for (slot = 0; slot < PCI_SLOT_MAX; slot++) INIT_LIST_HEAD(&vpci_dev->dev_list[slot]); @@ -222,10 +218,9 @@ static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev, struct pci_dev_entry *entry; struct pci_dev *dev = NULL; struct vpci_dev_data *vpci_dev = pdev->pci_dev_data; - unsigned long flags; int found = 0, slot; - spin_lock_irqsave(&vpci_dev->lock, flags); + mutex_lock(&vpci_dev->lock); for (slot = 0; slot < PCI_SLOT_MAX; slot++) { list_for_each_entry(entry, &vpci_dev->dev_list[slot], @@ -243,11 +238,11 @@ static int __xen_pcibk_get_pcifront_dev(struct pci_dev *pcidev, } } } - spin_unlock_irqrestore(&vpci_dev->lock, flags); + mutex_unlock(&vpci_dev->lock); return found; } -struct xen_pcibk_backend xen_pcibk_vpci_backend = { +const struct xen_pcibk_backend xen_pcibk_vpci_backend = { .name = "vpci", .init = __xen_pcibk_init_devices, .free = __xen_pcibk_release_devices, diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 978d2c6f5dca..474d52ec3374 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -13,7 +13,6 @@ #include <asm/xen/pci.h> #include "pciback.h" -#define DRV_NAME "xen-pciback" #define INVALID_EVTCHN_IRQ (-1) struct workqueue_struct *xen_pcibk_wq; @@ -44,7 +43,7 @@ static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev) pdev->xdev = xdev; dev_set_drvdata(&xdev->dev, pdev); - spin_lock_init(&pdev->dev_lock); + mutex_init(&pdev->dev_lock); pdev->sh_info = NULL; pdev->evtchn_irq = INVALID_EVTCHN_IRQ; @@ -62,14 +61,12 @@ out: static void xen_pcibk_disconnect(struct xen_pcibk_device *pdev) { - spin_lock(&pdev->dev_lock); - + mutex_lock(&pdev->dev_lock); /* Ensure the guest can't trigger our handler before removing devices */ if (pdev->evtchn_irq != INVALID_EVTCHN_IRQ) { unbind_from_irqhandler(pdev->evtchn_irq, pdev); pdev->evtchn_irq = INVALID_EVTCHN_IRQ; } - spin_unlock(&pdev->dev_lock); /* If the driver domain started an op, make sure we complete it * before releasing the shared memory */ @@ -77,13 +74,11 @@ static void xen_pcibk_disconnect(struct xen_pcibk_device *pdev) /* Note, the workqueue does not use spinlocks at all.*/ flush_workqueue(xen_pcibk_wq); - spin_lock(&pdev->dev_lock); if (pdev->sh_info != NULL) { xenbus_unmap_ring_vfree(pdev->xdev, pdev->sh_info); pdev->sh_info = NULL; } - spin_unlock(&pdev->dev_lock); - + mutex_unlock(&pdev->dev_lock); } static void free_pdev(struct xen_pcibk_device *pdev) @@ -120,9 +115,7 @@ static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref, goto out; } - spin_lock(&pdev->dev_lock); pdev->sh_info = vaddr; - spin_unlock(&pdev->dev_lock); err = bind_interdomain_evtchn_to_irqhandler( pdev->xdev->otherend_id, remote_evtchn, xen_pcibk_handle_event, @@ -132,10 +125,7 @@ static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref, "Error binding event channel to IRQ"); goto out; } - - spin_lock(&pdev->dev_lock); pdev->evtchn_irq = err; - spin_unlock(&pdev->dev_lock); err = 0; dev_dbg(&pdev->xdev->dev, "Attached!\n"); @@ -150,6 +140,7 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev) char *magic = NULL; + mutex_lock(&pdev->dev_lock); /* Make sure we only do this setup once */ if (xenbus_read_driver_state(pdev->xdev->nodename) != XenbusStateInitialised) @@ -176,7 +167,7 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev) if (magic == NULL || strcmp(magic, XEN_PCI_MAGIC) != 0) { xenbus_dev_fatal(pdev->xdev, -EFAULT, "version mismatch (%s/%s) with pcifront - " - "halting xen_pcibk", + "halting " DRV_NAME, magic, XEN_PCI_MAGIC); goto out; } @@ -194,6 +185,7 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev) dev_dbg(&pdev->xdev->dev, "Connected? %d\n", err); out: + mutex_unlock(&pdev->dev_lock); kfree(magic); @@ -369,6 +361,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n"); + mutex_lock(&pdev->dev_lock); /* Make sure we only reconfigure once */ if (xenbus_read_driver_state(pdev->xdev->nodename) != XenbusStateReconfiguring) @@ -506,6 +499,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) } out: + mutex_unlock(&pdev->dev_lock); return 0; } @@ -562,6 +556,7 @@ static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev) char dev_str[64]; char state_str[64]; + mutex_lock(&pdev->dev_lock); /* It's possible we could get the call to setup twice, so make sure * we're not already connected. */ @@ -642,10 +637,10 @@ static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev) "Error switching to initialised state!"); out: + mutex_unlock(&pdev->dev_lock); if (!err) /* see if pcifront is already configured (if not, we'll wait) */ xen_pcibk_attach(pdev); - return err; } @@ -724,7 +719,7 @@ static struct xenbus_driver xenbus_xen_pcibk_driver = { .otherend_changed = xen_pcibk_frontend_changed, }; -struct xen_pcibk_backend *xen_pcibk_backend; +const struct xen_pcibk_backend *__read_mostly xen_pcibk_backend; int __init xen_pcibk_xenbus_register(void) { diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 6ea852e25162..d93c70857e03 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -68,6 +68,8 @@ */ #include <linux/kernel.h> +#include <linux/bootmem.h> +#include <linux/swap.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/module.h> @@ -93,6 +95,15 @@ static unsigned int selfballoon_uphysteresis __read_mostly = 1; /* In HZ, controls frequency of worker invocation. */ static unsigned int selfballoon_interval __read_mostly = 5; +/* + * Minimum usable RAM in MB for selfballooning target for balloon. + * If non-zero, it is added to totalreserve_pages and self-ballooning + * will not balloon below the sum. If zero, a piecewise linear function + * is calculated as a minimum and added to totalreserve_pages. Note that + * setting this value indiscriminately may cause OOMs and crashes. + */ +static unsigned int selfballoon_min_usable_mb; + static void selfballoon_process(struct work_struct *work); static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process); @@ -189,20 +200,23 @@ static int __init xen_selfballooning_setup(char *s) __setup("selfballooning", xen_selfballooning_setup); #endif /* CONFIG_FRONTSWAP */ +#define MB2PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) + /* * Use current balloon size, the goal (vm_committed_as), and hysteresis * parameters to set a new target balloon size */ static void selfballoon_process(struct work_struct *work) { - unsigned long cur_pages, goal_pages, tgt_pages; + unsigned long cur_pages, goal_pages, tgt_pages, floor_pages; + unsigned long useful_pages; bool reset_timer = false; if (xen_selfballooning_enabled) { - cur_pages = balloon_stats.current_pages; + cur_pages = totalram_pages; tgt_pages = cur_pages; /* default is no change */ goal_pages = percpu_counter_read_positive(&vm_committed_as) + - balloon_stats.current_pages - totalram_pages; + totalreserve_pages; #ifdef CONFIG_FRONTSWAP /* allow space for frontswap pages to be repatriated */ if (frontswap_selfshrinking && frontswap_enabled) @@ -217,7 +231,26 @@ static void selfballoon_process(struct work_struct *work) ((goal_pages - cur_pages) / selfballoon_uphysteresis); /* else if cur_pages == goal_pages, no change */ - balloon_set_new_target(tgt_pages); + useful_pages = max_pfn - totalreserve_pages; + if (selfballoon_min_usable_mb != 0) + floor_pages = totalreserve_pages + + MB2PAGES(selfballoon_min_usable_mb); + /* piecewise linear function ending in ~3% slope */ + else if (useful_pages < MB2PAGES(16)) + floor_pages = max_pfn; /* not worth ballooning */ + else if (useful_pages < MB2PAGES(64)) + floor_pages = totalreserve_pages + MB2PAGES(16) + + ((useful_pages - MB2PAGES(16)) >> 1); + else if (useful_pages < MB2PAGES(512)) + floor_pages = totalreserve_pages + MB2PAGES(40) + + ((useful_pages - MB2PAGES(40)) >> 3); + else /* useful_pages >= MB2PAGES(512) */ + floor_pages = totalreserve_pages + MB2PAGES(99) + + ((useful_pages - MB2PAGES(99)) >> 5); + if (tgt_pages < floor_pages) + tgt_pages = floor_pages; + balloon_set_new_target(tgt_pages + + balloon_stats.current_pages - totalram_pages); reset_timer = true; } #ifdef CONFIG_FRONTSWAP @@ -340,6 +373,31 @@ static ssize_t store_selfballoon_uphys(struct sys_device *dev, static SYSDEV_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR, show_selfballoon_uphys, store_selfballoon_uphys); +SELFBALLOON_SHOW(selfballoon_min_usable_mb, "%d\n", + selfballoon_min_usable_mb); + +static ssize_t store_selfballoon_min_usable_mb(struct sys_device *dev, + struct sysdev_attribute *attr, + const char *buf, + size_t count) +{ + unsigned long val; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + err = strict_strtoul(buf, 10, &val); + if (err || val == 0) + return -EINVAL; + selfballoon_min_usable_mb = val; + return count; +} + +static SYSDEV_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR, + show_selfballoon_min_usable_mb, + store_selfballoon_min_usable_mb); + + #ifdef CONFIG_FRONTSWAP SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking); @@ -421,6 +479,7 @@ static struct attribute *selfballoon_attrs[] = { &attr_selfballoon_interval.attr, &attr_selfballoon_downhysteresis.attr, &attr_selfballoon_uphysteresis.attr, + &attr_selfballoon_min_usable_mb.attr, #ifdef CONFIG_FRONTSWAP &attr_frontswap_selfshrinking.attr, &attr_frontswap_hysteresis.attr, diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index 090c61ee8fd0..2eff7a6aaa20 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -212,7 +212,9 @@ int xb_init_comms(void) printk(KERN_WARNING "XENBUS response ring is not quiescent " "(%08x:%08x): fixing up\n", intf->rsp_cons, intf->rsp_prod); - intf->rsp_cons = intf->rsp_prod; + /* breaks kdump */ + if (!reset_devices) + intf->rsp_cons = intf->rsp_prod; } if (xenbus_irq) { diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index bd2f90c9ac8b..cef9b0bf63d5 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -684,64 +684,74 @@ static int __init xenbus_probe_initcall(void) device_initcall(xenbus_probe_initcall); -static int __init xenbus_init(void) +/* Set up event channel for xenstored which is run as a local process + * (this is normally used only in dom0) + */ +static int __init xenstored_local_init(void) { int err = 0; unsigned long page = 0; + struct evtchn_alloc_unbound alloc_unbound; - DPRINTK(""); + /* Allocate Xenstore page */ + page = get_zeroed_page(GFP_KERNEL); + if (!page) + goto out_err; - err = -ENODEV; - if (!xen_domain()) - return err; + xen_store_mfn = xen_start_info->store_mfn = + pfn_to_mfn(virt_to_phys((void *)page) >> + PAGE_SHIFT); - /* - * Domain0 doesn't have a store_evtchn or store_mfn yet. - */ - if (xen_initial_domain()) { - struct evtchn_alloc_unbound alloc_unbound; + /* Next allocate a local port which xenstored can bind to */ + alloc_unbound.dom = DOMID_SELF; + alloc_unbound.remote_dom = DOMID_SELF; - /* Allocate Xenstore page */ - page = get_zeroed_page(GFP_KERNEL); - if (!page) - goto out_error; + err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound, + &alloc_unbound); + if (err == -ENOSYS) + goto out_err; - xen_store_mfn = xen_start_info->store_mfn = - pfn_to_mfn(virt_to_phys((void *)page) >> - PAGE_SHIFT); + BUG_ON(err); + xen_store_evtchn = xen_start_info->store_evtchn = + alloc_unbound.port; - /* Next allocate a local port which xenstored can bind to */ - alloc_unbound.dom = DOMID_SELF; - alloc_unbound.remote_dom = 0; + return 0; - err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound, - &alloc_unbound); - if (err == -ENOSYS) - goto out_error; + out_err: + if (page != 0) + free_page(page); + return err; +} - BUG_ON(err); - xen_store_evtchn = xen_start_info->store_evtchn = - alloc_unbound.port; +static int __init xenbus_init(void) +{ + int err = 0; - xen_store_interface = mfn_to_virt(xen_store_mfn); + if (!xen_domain()) + return -ENODEV; + + if (xen_hvm_domain()) { + uint64_t v = 0; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); + if (err) + goto out_error; + xen_store_mfn = (unsigned long)v; + xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE); } else { - if (xen_hvm_domain()) { - uint64_t v = 0; - err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); - if (err) - goto out_error; - xen_store_evtchn = (int)v; - err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); + xen_store_evtchn = xen_start_info->store_evtchn; + xen_store_mfn = xen_start_info->store_mfn; + if (xen_store_evtchn) + xenstored_ready = 1; + else { + err = xenstored_local_init(); if (err) goto out_error; - xen_store_mfn = (unsigned long)v; - xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE); - } else { - xen_store_evtchn = xen_start_info->store_evtchn; - xen_store_mfn = xen_start_info->store_mfn; - xen_store_interface = mfn_to_virt(xen_store_mfn); - xenstored_ready = 1; } + xen_store_interface = mfn_to_virt(xen_store_mfn); } /* Initialize the interface to xenstore. */ @@ -760,12 +770,7 @@ static int __init xenbus_init(void) proc_mkdir("xen", NULL); #endif - return 0; - - out_error: - if (page != 0) - free_page(page); - + out_error: return err; } diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index 60adf919d78d..32417b5064fd 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -104,8 +104,6 @@ static int xenbus_uevent_backend(struct device *dev, xdev = to_xenbus_device(dev); bus = container_of(xdev->dev.bus, struct xen_bus_type, bus); - if (xdev == NULL) - return -ENODEV; if (add_uevent_var(env, "MODALIAS=xen-backend:%s", xdev->devicetype)) return -ENOMEM; diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index ed2ba474a560..540587e18a94 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -248,10 +248,131 @@ int __xenbus_register_frontend(struct xenbus_driver *drv, } EXPORT_SYMBOL_GPL(__xenbus_register_frontend); +static DECLARE_WAIT_QUEUE_HEAD(backend_state_wq); +static int backend_state; + +static void xenbus_reset_backend_state_changed(struct xenbus_watch *w, + const char **v, unsigned int l) +{ + xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &backend_state); + printk(KERN_DEBUG "XENBUS: backend %s %s\n", + v[XS_WATCH_PATH], xenbus_strstate(backend_state)); + wake_up(&backend_state_wq); +} + +static void xenbus_reset_wait_for_backend(char *be, int expected) +{ + long timeout; + timeout = wait_event_interruptible_timeout(backend_state_wq, + backend_state == expected, 5 * HZ); + if (timeout <= 0) + printk(KERN_INFO "XENBUS: backend %s timed out.\n", be); +} + +/* + * Reset frontend if it is in Connected or Closed state. + * Wait for backend to catch up. + * State Connected happens during kdump, Closed after kexec. + */ +static void xenbus_reset_frontend(char *fe, char *be, int be_state) +{ + struct xenbus_watch be_watch; + + printk(KERN_DEBUG "XENBUS: backend %s %s\n", + be, xenbus_strstate(be_state)); + + memset(&be_watch, 0, sizeof(be_watch)); + be_watch.node = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/state", be); + if (!be_watch.node) + return; + + be_watch.callback = xenbus_reset_backend_state_changed; + backend_state = XenbusStateUnknown; + + printk(KERN_INFO "XENBUS: triggering reconnect on %s\n", be); + register_xenbus_watch(&be_watch); + + /* fall through to forward backend to state XenbusStateInitialising */ + switch (be_state) { + case XenbusStateConnected: + xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing); + xenbus_reset_wait_for_backend(be, XenbusStateClosing); + + case XenbusStateClosing: + xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed); + xenbus_reset_wait_for_backend(be, XenbusStateClosed); + + case XenbusStateClosed: + xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising); + xenbus_reset_wait_for_backend(be, XenbusStateInitWait); + } + + unregister_xenbus_watch(&be_watch); + printk(KERN_INFO "XENBUS: reconnect done on %s\n", be); + kfree(be_watch.node); +} + +static void xenbus_check_frontend(char *class, char *dev) +{ + int be_state, fe_state, err; + char *backend, *frontend; + + frontend = kasprintf(GFP_NOIO | __GFP_HIGH, "device/%s/%s", class, dev); + if (!frontend) + return; + + err = xenbus_scanf(XBT_NIL, frontend, "state", "%i", &fe_state); + if (err != 1) + goto out; + + switch (fe_state) { + case XenbusStateConnected: + case XenbusStateClosed: + printk(KERN_DEBUG "XENBUS: frontend %s %s\n", + frontend, xenbus_strstate(fe_state)); + backend = xenbus_read(XBT_NIL, frontend, "backend", NULL); + if (!backend || IS_ERR(backend)) + goto out; + err = xenbus_scanf(XBT_NIL, backend, "state", "%i", &be_state); + if (err == 1) + xenbus_reset_frontend(frontend, backend, be_state); + kfree(backend); + break; + default: + break; + } +out: + kfree(frontend); +} + +static void xenbus_reset_state(void) +{ + char **devclass, **dev; + int devclass_n, dev_n; + int i, j; + + devclass = xenbus_directory(XBT_NIL, "device", "", &devclass_n); + if (IS_ERR(devclass)) + return; + + for (i = 0; i < devclass_n; i++) { + dev = xenbus_directory(XBT_NIL, "device", devclass[i], &dev_n); + if (IS_ERR(dev)) + continue; + for (j = 0; j < dev_n; j++) + xenbus_check_frontend(devclass[i], dev[j]); + kfree(dev); + } + kfree(devclass); +} + static int frontend_probe_and_watch(struct notifier_block *notifier, unsigned long event, void *data) { + /* reset devices in Connected or Closed state */ + if (xen_hvm_domain()) + xenbus_reset_state(); /* Enumerate devices in xenstore and watch for changes. */ xenbus_probe_devices(&xenbus_frontend); register_xenbus_watch(&fe_watch); diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 5534690075af..b3b8f2f3ad10 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -45,6 +45,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <xen/xenbus.h> +#include <xen/xen.h> #include "xenbus_comms.h" struct xs_stored_msg { @@ -620,6 +621,15 @@ static struct xenbus_watch *find_watch(const char *token) return NULL; } +static void xs_reset_watches(void) +{ + int err; + + err = xs_error(xs_single(XBT_NIL, XS_RESET_WATCHES, "", NULL)); + if (err && err != -EEXIST) + printk(KERN_WARNING "xs_reset_watches failed: %d\n", err); +} + /* Register callback to watch this node. */ int register_xenbus_watch(struct xenbus_watch *watch) { @@ -638,8 +648,7 @@ int register_xenbus_watch(struct xenbus_watch *watch) err = xs_watch(watch->node, token); - /* Ignore errors due to multiple registration. */ - if ((err != 0) && (err != -EEXIST)) { + if (err) { spin_lock(&watches_lock); list_del(&watch->list); spin_unlock(&watches_lock); @@ -897,5 +906,9 @@ int xs_init(void) if (IS_ERR(task)) return PTR_ERR(task); + /* shutdown watches for kexec boot */ + if (xen_hvm_domain()) + xs_reset_watches(); + return 0; } diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c index 7ee2b6e71786..229624f867d3 100644 --- a/drivers/zorro/zorro-driver.c +++ b/drivers/zorro/zorro-driver.c @@ -37,6 +37,7 @@ zorro_match_device(const struct zorro_device_id *ids, } return NULL; } +EXPORT_SYMBOL(zorro_match_device); static int zorro_device_probe(struct device *dev) @@ -91,6 +92,7 @@ int zorro_register_driver(struct zorro_driver *drv) /* register with core */ return driver_register(&drv->driver); } +EXPORT_SYMBOL(zorro_register_driver); /** @@ -107,6 +109,7 @@ void zorro_unregister_driver(struct zorro_driver *drv) { driver_unregister(&drv->driver); } +EXPORT_SYMBOL(zorro_unregister_driver); /** @@ -168,6 +171,7 @@ struct bus_type zorro_bus_type = { .probe = zorro_device_probe, .remove = zorro_device_remove, }; +EXPORT_SYMBOL(zorro_bus_type); static int __init zorro_driver_init(void) @@ -177,7 +181,3 @@ static int __init zorro_driver_init(void) postcore_initcall(zorro_driver_init); -EXPORT_SYMBOL(zorro_match_device); -EXPORT_SYMBOL(zorro_register_driver); -EXPORT_SYMBOL(zorro_unregister_driver); -EXPORT_SYMBOL(zorro_bus_type); diff --git a/fs/attr.c b/fs/attr.c index 538e27959d3f..7ee7ba488313 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -13,6 +13,7 @@ #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/security.h> +#include <linux/evm.h> /** * inode_change_ok - check if attribute changes to an inode are allowed @@ -237,8 +238,10 @@ int notify_change(struct dentry * dentry, struct iattr * attr) else error = simple_setattr(dentry, attr); - if (!error) + if (!error) { fsnotify_change(dentry, ia_valid); + evm_inode_post_setattr(dentry, ia_valid); + } return error; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 538f65a79ec5..dae5dfe41ba5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1047,7 +1047,16 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (!max_to_defrag) max_to_defrag = last_index - 1; - while (i <= last_index && defrag_count < max_to_defrag) { + /* + * make writeback starts from i, so the defrag range can be + * written sequentially. + */ + if (i < inode->i_mapping->writeback_index) + inode->i_mapping->writeback_index = i; + + while (i <= last_index && defrag_count < max_to_defrag && + (i < (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT)) { /* * make sure we stop running if someone unmounts * the FS diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 69565e5fc6a0..426aa464f1af 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -383,36 +383,36 @@ int btrfs_removexattr(struct dentry *dentry, const char *name) XATTR_REPLACE); } -int btrfs_xattr_security_init(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *dir, - const struct qstr *qstr) +int btrfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int err; - size_t len; - void *value; - char *suffix; + const struct xattr *xattr; + struct btrfs_trans_handle *trans = fs_info; char *name; + int err = 0; - err = security_inode_init_security(inode, dir, qstr, &suffix, &value, - &len); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; - } - - name = kmalloc(XATTR_SECURITY_PREFIX_LEN + strlen(suffix) + 1, - GFP_NOFS); - if (!name) { - err = -ENOMEM; - } else { + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + name = kmalloc(XATTR_SECURITY_PREFIX_LEN + + strlen(xattr->name) + 1, GFP_NOFS); + if (!name) { + err = -ENOMEM; + break; + } strcpy(name, XATTR_SECURITY_PREFIX); - strcpy(name + XATTR_SECURITY_PREFIX_LEN, suffix); - err = __btrfs_setxattr(trans, inode, name, value, len, 0); + strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); + err = __btrfs_setxattr(trans, inode, name, + xattr->value, xattr->value_len, 0); kfree(name); + if (err < 0) + break; } - - kfree(suffix); - kfree(value); return err; } + +int btrfs_xattr_security_init(struct btrfs_trans_handle *trans, + struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &btrfs_initxattrs, trans); +} diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 2a22fb2989e4..c32308882148 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/posix_acl_xattr.h> #include <linux/slab.h> +#include <linux/xattr.h> #include "cifsfs.h" #include "cifspdu.h" #include "cifsglob.h" @@ -31,16 +32,8 @@ #define MAX_EA_VALUE_SIZE 65535 #define CIFS_XATTR_DOS_ATTRIB "user.DosAttrib" #define CIFS_XATTR_CIFS_ACL "system.cifs_acl" -#define CIFS_XATTR_USER_PREFIX "user." -#define CIFS_XATTR_SYSTEM_PREFIX "system." -#define CIFS_XATTR_OS2_PREFIX "os2." -#define CIFS_XATTR_SECURITY_PREFIX "security." -#define CIFS_XATTR_TRUSTED_PREFIX "trusted." -#define XATTR_TRUSTED_PREFIX_LEN 8 -#define XATTR_SECURITY_PREFIX_LEN 9 -/* BB need to add server (Samba e.g) support for security and trusted prefix */ - +/* BB need to add server (Samba e.g) support for security and trusted prefix */ int cifs_removexattr(struct dentry *direntry, const char *ea_name) { @@ -76,8 +69,8 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name) } if (ea_name == NULL) { cFYI(1, "Null xattr names not supported"); - } else if (strncmp(ea_name, CIFS_XATTR_USER_PREFIX, 5) - && (strncmp(ea_name, CIFS_XATTR_OS2_PREFIX, 4))) { + } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) + && (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN))) { cFYI(1, "illegal xattr request %s (only user namespace supported)", ea_name); @@ -88,7 +81,7 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) goto remove_ea_exit; - ea_name += 5; /* skip past user. prefix */ + ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */ rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, NULL, (__u16)0, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); @@ -149,21 +142,23 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, if (ea_name == NULL) { cFYI(1, "Null xattr names not supported"); - } else if (strncmp(ea_name, CIFS_XATTR_USER_PREFIX, 5) == 0) { + } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) + == 0) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) goto set_ea_exit; if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0) cFYI(1, "attempt to set cifs inode metadata"); - ea_name += 5; /* skip past user. prefix */ + ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */ rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value, (__u16)value_size, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - } else if (strncmp(ea_name, CIFS_XATTR_OS2_PREFIX, 4) == 0) { + } else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) + == 0) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) goto set_ea_exit; - ea_name += 4; /* skip past os2. prefix */ + ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */ rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value, (__u16)value_size, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); @@ -269,7 +264,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, /* return alt name if available as pseudo attr */ if (ea_name == NULL) { cFYI(1, "Null xattr names not supported"); - } else if (strncmp(ea_name, CIFS_XATTR_USER_PREFIX, 5) == 0) { + } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) + == 0) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) goto get_ea_exit; @@ -277,15 +273,15 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, cFYI(1, "attempt to query cifs inode metadata"); /* revalidate/getattr then populate from inode */ } /* BB add else when above is implemented */ - ea_name += 5; /* skip past user. prefix */ + ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */ rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value, buf_size, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - } else if (strncmp(ea_name, CIFS_XATTR_OS2_PREFIX, 4) == 0) { + } else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) goto get_ea_exit; - ea_name += 4; /* skip past os2. prefix */ + ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */ rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value, buf_size, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); @@ -339,10 +335,10 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, cFYI(1, "Query CIFS ACL not supported yet"); #endif /* CONFIG_CIFS_ACL */ } else if (strncmp(ea_name, - CIFS_XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) { + XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) { cFYI(1, "Trusted xattr namespace not supported yet"); } else if (strncmp(ea_name, - CIFS_XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) == 0) { + XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) == 0) { cFYI(1, "Security xattr namespace not supported yet"); } else cFYI(1, diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index 5d979b4347b0..c922adc8ef41 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -46,28 +46,30 @@ ext2_xattr_security_set(struct dentry *dentry, const char *name, value, size, flags); } -int -ext2_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr) +int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int err; - size_t len; - void *value; - char *name; + const struct xattr *xattr; + int err = 0; - err = security_inode_init_security(inode, dir, qstr, &name, &value, &len); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, 0); + if (err < 0) + break; } - err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, - name, value, len, 0); - kfree(name); - kfree(value); return err; } +int +ext2_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &ext2_initxattrs, NULL); +} + const struct xattr_handler ext2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .list = ext2_xattr_security_list, diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c index b8d9f83aa5c5..3c218b8a51d4 100644 --- a/fs/ext3/xattr_security.c +++ b/fs/ext3/xattr_security.c @@ -48,28 +48,32 @@ ext3_xattr_security_set(struct dentry *dentry, const char *name, name, value, size, flags); } -int -ext3_init_security(handle_t *handle, struct inode *inode, struct inode *dir, - const struct qstr *qstr) +int ext3_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int err; - size_t len; - void *value; - char *name; + const struct xattr *xattr; + handle_t *handle = fs_info; + int err = 0; - err = security_inode_init_security(inode, dir, qstr, &name, &value, &len); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = ext3_xattr_set_handle(handle, inode, + EXT3_XATTR_INDEX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, 0); + if (err < 0) + break; } - err = ext3_xattr_set_handle(handle, inode, EXT3_XATTR_INDEX_SECURITY, - name, value, len, 0); - kfree(name); - kfree(value); return err; } +int +ext3_init_security(handle_t *handle, struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &ext3_initxattrs, handle); +} + const struct xattr_handler ext3_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .list = ext3_xattr_security_list, diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 007c3bfbf094..34e4350dd4d9 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -48,28 +48,32 @@ ext4_xattr_security_set(struct dentry *dentry, const char *name, name, value, size, flags); } -int -ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir, - const struct qstr *qstr) +int ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int err; - size_t len; - void *value; - char *name; + const struct xattr *xattr; + handle_t *handle = fs_info; + int err = 0; - err = security_inode_init_security(inode, dir, qstr, &name, &value, &len); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = ext4_xattr_set_handle(handle, inode, + EXT4_XATTR_INDEX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, 0); + if (err < 0) + break; } - err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY, - name, value, len, 0); - kfree(name); - kfree(value); return err; } +int +ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &ext4_initxattrs, handle); +} + const struct xattr_handler ext4_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .list = ext4_xattr_security_list, diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 900cf986aadc..6525b804d5ec 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -624,31 +624,29 @@ fail: return error; } -static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip, - const struct qstr *qstr) +int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int err; - size_t len; - void *value; - char *name; - - err = security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr, - &name, &value, &len); - - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; + const struct xattr *xattr; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = __gfs2_xattr_set(inode, xattr->name, xattr->value, + xattr->value_len, 0, + GFS2_EATYPE_SECURITY); + if (err < 0) + break; } - - err = __gfs2_xattr_set(&ip->i_inode, name, value, len, 0, - GFS2_EATYPE_SECURITY); - kfree(value); - kfree(name); - return err; } +static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip, + const struct qstr *qstr) +{ + return security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr, + &gfs2_initxattrs, NULL); +} + /** * gfs2_create_inode - Create a new inode * @dir: The parent directory diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index cfeb7164b085..0f20208df602 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -22,26 +22,29 @@ #include <linux/security.h> #include "nodelist.h" -/* ---- Initial Security Label Attachment -------------- */ -int jffs2_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr) +/* ---- Initial Security Label(s) Attachment callback --- */ +int jffs2_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int rc; - size_t len; - void *value; - char *name; + const struct xattr *xattr; + int err = 0; - rc = security_inode_init_security(inode, dir, qstr, &name, &value, &len); - if (rc) { - if (rc == -EOPNOTSUPP) - return 0; - return rc; + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = do_jffs2_setxattr(inode, JFFS2_XPREFIX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, 0); + if (err < 0) + break; } - rc = do_jffs2_setxattr(inode, JFFS2_XPREFIX_SECURITY, name, value, len, 0); + return err; +} - kfree(name); - kfree(value); - return rc; +/* ---- Initial Security Label(s) Attachment ----------- */ +int jffs2_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &jffs2_initxattrs, NULL); } /* ---- XATTR Handler for "security.*" ----------------- */ diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index e87fedef23db..26683e15b3ac 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -1089,38 +1089,37 @@ int jfs_removexattr(struct dentry *dentry, const char *name) } #ifdef CONFIG_JFS_SECURITY -int jfs_init_security(tid_t tid, struct inode *inode, struct inode *dir, - const struct qstr *qstr) +int jfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) { - int rc; - size_t len; - void *value; - char *suffix; + const struct xattr *xattr; + tid_t *tid = fs_info; char *name; - - rc = security_inode_init_security(inode, dir, qstr, &suffix, &value, - &len); - if (rc) { - if (rc == -EOPNOTSUPP) - return 0; - return rc; - } - name = kmalloc(XATTR_SECURITY_PREFIX_LEN + 1 + strlen(suffix), - GFP_NOFS); - if (!name) { - rc = -ENOMEM; - goto kmalloc_failed; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + name = kmalloc(XATTR_SECURITY_PREFIX_LEN + + strlen(xattr->name) + 1, GFP_NOFS); + if (!name) { + err = -ENOMEM; + break; + } + strcpy(name, XATTR_SECURITY_PREFIX); + strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); + + err = __jfs_setxattr(*tid, inode, name, + xattr->value, xattr->value_len, 0); + kfree(name); + if (err < 0) + break; } - strcpy(name, XATTR_SECURITY_PREFIX); - strcpy(name + XATTR_SECURITY_PREFIX_LEN, suffix); - - rc = __jfs_setxattr(tid, inode, name, value, len, 0); - - kfree(name); -kmalloc_failed: - kfree(suffix); - kfree(value); + return err; +} - return rc; +int jfs_init_security(tid_t tid, struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &jfs_initxattrs, &tid); } #endif diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 81ecf9c0bf0a..194fb22ef79d 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7185,20 +7185,9 @@ int ocfs2_init_security_and_acl(struct inode *dir, { int ret = 0; struct buffer_head *dir_bh = NULL; - struct ocfs2_security_xattr_info si = { - .enable = 1, - }; - ret = ocfs2_init_security_get(inode, dir, qstr, &si); + ret = ocfs2_init_security_get(inode, dir, qstr, NULL); if (!ret) { - ret = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, - si.name, si.value, si.value_len, - XATTR_CREATE); - if (ret) { - mlog_errno(ret); - goto leave; - } - } else if (ret != -EOPNOTSUPP) { mlog_errno(ret); goto leave; } @@ -7255,6 +7244,22 @@ static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name, name, value, size, flags); } +int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) +{ + const struct xattr *xattr; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, XATTR_CREATE); + if (err) + break; + } + return err; +} + int ocfs2_init_security_get(struct inode *inode, struct inode *dir, const struct qstr *qstr, @@ -7263,8 +7268,13 @@ int ocfs2_init_security_get(struct inode *inode, /* check whether ocfs2 support feature xattr */ if (!ocfs2_supports_xattr(OCFS2_SB(dir->i_sb))) return -EOPNOTSUPP; - return security_inode_init_security(inode, dir, qstr, &si->name, - &si->value, &si->value_len); + if (si) + return security_old_inode_init_security(inode, dir, qstr, + &si->name, &si->value, + &si->value_len); + + return security_inode_init_security(inode, dir, qstr, + &ocfs2_initxattrs, NULL); } int ocfs2_init_security_set(handle_t *handle, diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index ef66c18a9332..534668fa41be 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -66,8 +66,8 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, if (IS_PRIVATE(dir)) return 0; - error = security_inode_init_security(inode, dir, qstr, &sec->name, - &sec->value, &sec->length); + error = security_old_inode_init_security(inode, dir, qstr, &sec->name, + &sec->value, &sec->length); if (error) { if (error == -EOPNOTSUPP) error = 0; diff --git a/fs/xattr.c b/fs/xattr.c index f060663ab70c..67583de8218c 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -14,6 +14,7 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> +#include <linux/evm.h> #include <linux/syscalls.h> #include <linux/module.h> #include <linux/fsnotify.h> @@ -166,6 +167,64 @@ out_noalloc: } EXPORT_SYMBOL_GPL(xattr_getsecurity); +/* + * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr + * + * Allocate memory, if not already allocated, or re-allocate correct size, + * before retrieving the extended attribute. + * + * Returns the result of alloc, if failed, or the getxattr operation. + */ +ssize_t +vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, + size_t xattr_size, gfp_t flags) +{ + struct inode *inode = dentry->d_inode; + char *value = *xattr_value; + int error; + + error = xattr_permission(inode, name, MAY_READ); + if (error) + return error; + + if (!inode->i_op->getxattr) + return -EOPNOTSUPP; + + error = inode->i_op->getxattr(dentry, name, NULL, 0); + if (error < 0) + return error; + + if (!value || (error > xattr_size)) { + value = krealloc(*xattr_value, error + 1, flags); + if (!value) + return -ENOMEM; + memset(value, 0, error + 1); + } + + error = inode->i_op->getxattr(dentry, name, value, error); + *xattr_value = value; + return error; +} + +/* Compare an extended attribute value with the given value */ +int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, + const char *value, size_t size, gfp_t flags) +{ + char *xattr_value = NULL; + int rc; + + rc = vfs_getxattr_alloc(dentry, xattr_name, &xattr_value, 0, flags); + if (rc < 0) + return rc; + + if ((rc != size) || (memcmp(xattr_value, value, rc) != 0)) + rc = -EINVAL; + else + rc = 0; + kfree(xattr_value); + return rc; +} + ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { @@ -243,8 +302,10 @@ vfs_removexattr(struct dentry *dentry, const char *name) error = inode->i_op->removexattr(dentry, name); mutex_unlock(&inode->i_mutex); - if (!error) + if (!error) { fsnotify_xattr(dentry); + evm_inode_post_removexattr(dentry, name); + } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index cac2ecfa6746..ef43fce519a1 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -629,7 +629,7 @@ xfs_buf_item_push( * the xfsbufd to get this buffer written. We have to unlock the buffer * to allow the xfsbufd to write it, too. */ -STATIC void +STATIC bool xfs_buf_item_pushbuf( struct xfs_log_item *lip) { @@ -643,6 +643,7 @@ xfs_buf_item_pushbuf( xfs_buf_delwri_promote(bp); xfs_buf_relse(bp); + return true; } STATIC void diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 9e0e2fa3f2c8..bb3f71d236d2 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -183,13 +183,14 @@ xfs_qm_dqunpin_wait( * search the buffer cache can be a time consuming thing, and AIL lock is a * spinlock. */ -STATIC void +STATIC bool xfs_qm_dquot_logitem_pushbuf( struct xfs_log_item *lip) { struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_buf *bp; + bool ret = true; ASSERT(XFS_DQ_IS_LOCKED(dqp)); @@ -201,17 +202,20 @@ xfs_qm_dquot_logitem_pushbuf( if (completion_done(&dqp->q_flush) || !(lip->li_flags & XFS_LI_IN_AIL)) { xfs_dqunlock(dqp); - return; + return true; } bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno, dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK); xfs_dqunlock(dqp); if (!bp) - return; + return true; if (XFS_BUF_ISDELAYWRITE(bp)) xfs_buf_delwri_promote(bp); + if (xfs_buf_ispinned(bp)) + ret = false; xfs_buf_relse(bp); + return ret; } /* diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 588406dc6a35..836ad80d4f2b 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -708,13 +708,14 @@ xfs_inode_item_committed( * marked delayed write. If that's the case, we'll promote it and that will * allow the caller to write the buffer by triggering the xfsbufd to run. */ -STATIC void +STATIC bool xfs_inode_item_pushbuf( struct xfs_log_item *lip) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; struct xfs_buf *bp; + bool ret = true; ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); @@ -725,7 +726,7 @@ xfs_inode_item_pushbuf( if (completion_done(&ip->i_flush) || !(lip->li_flags & XFS_LI_IN_AIL)) { xfs_iunlock(ip, XFS_ILOCK_SHARED); - return; + return true; } bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno, @@ -733,10 +734,13 @@ xfs_inode_item_pushbuf( xfs_iunlock(ip, XFS_ILOCK_SHARED); if (!bp) - return; + return true; if (XFS_BUF_ISDELAYWRITE(bp)) xfs_buf_delwri_promote(bp); + if (xfs_buf_ispinned(bp)) + ret = false; xfs_buf_relse(bp); + return ret; } /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 673704fab748..28856accb4fa 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -102,37 +102,38 @@ xfs_mark_inode_dirty( } + +int xfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) +{ + const struct xattr *xattr; + struct xfs_inode *ip = XFS_I(inode); + int error = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + error = xfs_attr_set(ip, xattr->name, xattr->value, + xattr->value_len, ATTR_SECURE); + if (error < 0) + break; + } + return error; +} + /* * Hook in SELinux. This is not quite correct yet, what we really need * here (as we do for default ACLs) is a mechanism by which creation of * these attrs can be journalled at inode creation time (along with the * inode, of course, such that log replay can't cause these to be lost). */ + STATIC int xfs_init_security( struct inode *inode, struct inode *dir, const struct qstr *qstr) { - struct xfs_inode *ip = XFS_I(inode); - size_t length; - void *value; - unsigned char *name; - int error; - - error = security_inode_init_security(inode, dir, qstr, (char **)&name, - &value, &length); - if (error) { - if (error == -EOPNOTSUPP) - return 0; - return -error; - } - - error = xfs_attr_set(ip, name, value, length, ATTR_SECURE); - - kfree(name); - kfree(value); - return error; + return security_inode_init_security(inode, dir, qstr, + &xfs_initxattrs, NULL); } static void diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 1e8a45e74c3e..828662f70d64 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -68,6 +68,8 @@ #include <linux/ctype.h> #include <linux/writeback.h> #include <linux/capability.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <linux/list_sort.h> #include <asm/page.h> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 2366c54cc4fa..5cf06b85fd9d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1652,24 +1652,13 @@ xfs_init_workqueues(void) */ xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8); if (!xfs_syncd_wq) - goto out; - - xfs_ail_wq = alloc_workqueue("xfsail", WQ_CPU_INTENSIVE, 8); - if (!xfs_ail_wq) - goto out_destroy_syncd; - + return -ENOMEM; return 0; - -out_destroy_syncd: - destroy_workqueue(xfs_syncd_wq); -out: - return -ENOMEM; } STATIC void xfs_destroy_workqueues(void) { - destroy_workqueue(xfs_ail_wq); destroy_workqueue(xfs_syncd_wq); } diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 06a9759b6352..53597f4db9b5 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -350,7 +350,7 @@ typedef struct xfs_item_ops { void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); void (*iop_push)(xfs_log_item_t *); - void (*iop_pushbuf)(xfs_log_item_t *); + bool (*iop_pushbuf)(xfs_log_item_t *); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); } xfs_item_ops_t; diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index c15aa29fa169..3a1e7ca54c2d 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -28,8 +28,6 @@ #include "xfs_trans_priv.h" #include "xfs_error.h" -struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ - #ifdef DEBUG /* * Check that the list is sorted as it should be. @@ -356,16 +354,10 @@ xfs_ail_delete( xfs_trans_ail_cursor_clear(ailp, lip); } -/* - * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself - * to run at a later time if there is more work to do to complete the push. - */ -STATIC void -xfs_ail_worker( - struct work_struct *work) +static long +xfsaild_push( + struct xfs_ail *ailp) { - struct xfs_ail *ailp = container_of(to_delayed_work(work), - struct xfs_ail, xa_work); xfs_mount_t *mp = ailp->xa_mount; struct xfs_ail_cursor cur; xfs_log_item_t *lip; @@ -427,8 +419,13 @@ xfs_ail_worker( case XFS_ITEM_PUSHBUF: XFS_STATS_INC(xs_push_ail_pushbuf); - IOP_PUSHBUF(lip); - ailp->xa_last_pushed_lsn = lsn; + + if (!IOP_PUSHBUF(lip)) { + stuck++; + flush_log = 1; + } else { + ailp->xa_last_pushed_lsn = lsn; + } push_xfsbufd = 1; break; @@ -440,7 +437,6 @@ xfs_ail_worker( case XFS_ITEM_LOCKED: XFS_STATS_INC(xs_push_ail_locked); - ailp->xa_last_pushed_lsn = lsn; stuck++; break; @@ -501,20 +497,6 @@ out_done: /* We're past our target or empty, so idle */ ailp->xa_last_pushed_lsn = 0; - /* - * We clear the XFS_AIL_PUSHING_BIT first before checking - * whether the target has changed. If the target has changed, - * this pushes the requeue race directly onto the result of the - * atomic test/set bit, so we are guaranteed that either the - * the pusher that changed the target or ourselves will requeue - * the work (but not both). - */ - clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags); - smp_rmb(); - if (XFS_LSN_CMP(ailp->xa_target, target) == 0 || - test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags)) - return; - tout = 50; } else if (XFS_LSN_CMP(lsn, target) >= 0) { /* @@ -537,9 +519,30 @@ out_done: tout = 20; } - /* There is more to do, requeue us. */ - queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, - msecs_to_jiffies(tout)); + return tout; +} + +static int +xfsaild( + void *data) +{ + struct xfs_ail *ailp = data; + long tout = 0; /* milliseconds */ + + while (!kthread_should_stop()) { + if (tout && tout <= 20) + __set_current_state(TASK_KILLABLE); + else + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(tout ? + msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT); + + try_to_freeze(); + + tout = xfsaild_push(ailp); + } + + return 0; } /* @@ -574,8 +577,9 @@ xfs_ail_push( */ smp_wmb(); xfs_trans_ail_copy_lsn(ailp, &ailp->xa_target, &threshold_lsn); - if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags)) - queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0); + smp_wmb(); + + wake_up_process(ailp->xa_task); } /* @@ -813,9 +817,18 @@ xfs_trans_ail_init( INIT_LIST_HEAD(&ailp->xa_ail); INIT_LIST_HEAD(&ailp->xa_cursors); spin_lock_init(&ailp->xa_lock); - INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker); + + ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s", + ailp->xa_mount->m_fsname); + if (IS_ERR(ailp->xa_task)) + goto out_free_ailp; + mp->m_ail = ailp; return 0; + +out_free_ailp: + kmem_free(ailp); + return ENOMEM; } void @@ -824,6 +837,6 @@ xfs_trans_ail_destroy( { struct xfs_ail *ailp = mp->m_ail; - cancel_delayed_work_sync(&ailp->xa_work); + kthread_stop(ailp->xa_task); kmem_free(ailp); } diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 212946b97239..22750b5e4a8f 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -64,23 +64,17 @@ struct xfs_ail_cursor { */ struct xfs_ail { struct xfs_mount *xa_mount; + struct task_struct *xa_task; struct list_head xa_ail; xfs_lsn_t xa_target; struct list_head xa_cursors; spinlock_t xa_lock; - struct delayed_work xa_work; xfs_lsn_t xa_last_pushed_lsn; - unsigned long xa_flags; }; -#define XFS_AIL_PUSHING_BIT 0 - /* * From xfs_trans_ail.c */ - -extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ - void xfs_trans_ail_update_bulk(struct xfs_ail *ailp, struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index db22d136ad08..b5e2e4c6b017 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -222,7 +222,6 @@ VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \ *(__tracepoints_ptrs) /* Tracepoints: pointer array */\ VMLINUX_SYMBOL(__stop___tracepoints_ptrs) = .; \ - *(__markers_strings) /* Markers: strings */ \ *(__tracepoints_strings)/* Tracepoints: strings */ \ } \ \ diff --git a/include/linux/evm.h b/include/linux/evm.h new file mode 100644 index 000000000000..9fc13a760928 --- /dev/null +++ b/include/linux/evm.h @@ -0,0 +1,100 @@ +/* + * evm.h + * + * Copyright (c) 2009 IBM Corporation + * Author: Mimi Zohar <zohar@us.ibm.com> + */ + +#ifndef _LINUX_EVM_H +#define _LINUX_EVM_H + +#include <linux/integrity.h> +#include <linux/xattr.h> + +struct integrity_iint_cache; + +#ifdef CONFIG_EVM +extern enum integrity_status evm_verifyxattr(struct dentry *dentry, + const char *xattr_name, + void *xattr_value, + size_t xattr_value_len, + struct integrity_iint_cache *iint); +extern int evm_inode_setattr(struct dentry *dentry, struct iattr *attr); +extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); +extern int evm_inode_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size); +extern void evm_inode_post_setxattr(struct dentry *dentry, + const char *xattr_name, + const void *xattr_value, + size_t xattr_value_len); +extern int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name); +extern void evm_inode_post_removexattr(struct dentry *dentry, + const char *xattr_name); +extern int evm_inode_init_security(struct inode *inode, + const struct xattr *xattr_array, + struct xattr *evm); +#ifdef CONFIG_FS_POSIX_ACL +extern int posix_xattr_acl(const char *xattrname); +#else +static inline int posix_xattr_acl(const char *xattrname) +{ + return 0; +} +#endif +#else +#ifdef CONFIG_INTEGRITY +static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, + const char *xattr_name, + void *xattr_value, + size_t xattr_value_len, + struct integrity_iint_cache *iint) +{ + return INTEGRITY_UNKNOWN; +} +#endif + +static inline int evm_inode_setattr(struct dentry *dentry, struct iattr *attr) +{ + return 0; +} + +static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) +{ + return; +} + +static inline int evm_inode_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size) +{ + return 0; +} + +static inline void evm_inode_post_setxattr(struct dentry *dentry, + const char *xattr_name, + const void *xattr_value, + size_t xattr_value_len) +{ + return; +} + +static inline int evm_inode_removexattr(struct dentry *dentry, + const char *xattr_name) +{ + return 0; +} + +static inline void evm_inode_post_removexattr(struct dentry *dentry, + const char *xattr_name) +{ + return; +} + +static inline int evm_inode_init_security(struct inode *inode, + const struct xattr *xattr_array, + struct xattr *evm) +{ + return 0; +} + +#endif /* CONFIG_EVM_H */ +#endif /* LINUX_EVM_H */ diff --git a/include/linux/ima.h b/include/linux/ima.h index 09e6e62f9953..6ac8e50c6cf5 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -15,8 +15,6 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); -extern int ima_inode_alloc(struct inode *inode); -extern void ima_inode_free(struct inode *inode); extern int ima_file_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); @@ -27,16 +25,6 @@ static inline int ima_bprm_check(struct linux_binprm *bprm) return 0; } -static inline int ima_inode_alloc(struct inode *inode) -{ - return 0; -} - -static inline void ima_inode_free(struct inode *inode) -{ - return; -} - static inline int ima_file_check(struct file *file, int mask) { return 0; @@ -51,6 +39,5 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) { return 0; } - #endif /* CONFIG_IMA_H */ #endif /* _LINUX_IMA_H */ diff --git a/include/linux/integrity.h b/include/linux/integrity.h new file mode 100644 index 000000000000..a0c41256cb92 --- /dev/null +++ b/include/linux/integrity.h @@ -0,0 +1,39 @@ +/* + * Copyright (C) 2009 IBM Corporation + * Author: Mimi Zohar <zohar@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + */ + +#ifndef _LINUX_INTEGRITY_H +#define _LINUX_INTEGRITY_H + +#include <linux/fs.h> + +enum integrity_status { + INTEGRITY_PASS = 0, + INTEGRITY_FAIL, + INTEGRITY_NOLABEL, + INTEGRITY_NOXATTRS, + INTEGRITY_UNKNOWN, +}; + +/* List of EVM protected security xattrs */ +#ifdef CONFIG_INTEGRITY +extern int integrity_inode_alloc(struct inode *inode); +extern void integrity_inode_free(struct inode *inode); + +#else +static inline int integrity_inode_alloc(struct inode *inode) +{ + return 0; +} + +static inline void integrity_inode_free(struct inode *inode) +{ + return; +} +#endif /* CONFIG_INTEGRITY_H */ +#endif /* _LINUX_INTEGRITY_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 46ac9a50528d..8eefcf7e95eb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -382,7 +382,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) } extern int hex_to_bin(char ch); -extern void hex2bin(u8 *dst, const char *src, size_t count); +extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); /* * General tracing related utility functions - trace_printk(), diff --git a/include/linux/security.h b/include/linux/security.h index ebd2a53a3d07..19d8e04e1688 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -36,6 +36,7 @@ #include <linux/key.h> #include <linux/xfrm.h> #include <linux/slab.h> +#include <linux/xattr.h> #include <net/flow.h> /* Maximum number of letters for an LSM name string */ @@ -147,6 +148,10 @@ extern int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif +/* security_inode_init_security callback function to write xattrs */ +typedef int (*initxattrs) (struct inode *inode, + const struct xattr *xattr_array, void *fs_data); + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -1367,7 +1372,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @inode_getsecctx: * Returns a string containing all relavent security context information * - * @inode we wish to set the security context of. + * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. * This is the main security structure. @@ -1655,6 +1660,8 @@ struct security_operations { extern int security_init(void); extern int security_module_enable(struct security_operations *ops); extern int register_security(struct security_operations *ops); +extern void __init security_fixup_ops(struct security_operations *ops); + /* Security operations */ int security_ptrace_access_check(struct task_struct *child, unsigned int mode); @@ -1704,8 +1711,11 @@ int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); int security_inode_alloc(struct inode *inode); void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, char **name, - void **value, size_t *len); + const struct qstr *qstr, + initxattrs initxattrs, void *fs_data); +int security_old_inode_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, char **name, + void **value, size_t *len); int security_inode_create(struct inode *dir, struct dentry *dentry, int mode); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); @@ -2034,11 +2044,19 @@ static inline void security_inode_free(struct inode *inode) static inline int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, - char **name, - void **value, - size_t *len) + initxattrs initxattrs, + void *fs_data) { - return -EOPNOTSUPP; + return 0; +} + +static inline int security_old_inode_init_security(struct inode *inode, + struct inode *dir, + const struct qstr *qstr, + char **name, void **value, + size_t *len) +{ + return 0; } static inline int security_inode_create(struct inode *dir, diff --git a/include/linux/xattr.h b/include/linux/xattr.h index aed54c50aa66..e5d122031542 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -30,6 +30,9 @@ #define XATTR_USER_PREFIX_LEN (sizeof (XATTR_USER_PREFIX) - 1) /* Security namespace */ +#define XATTR_EVM_SUFFIX "evm" +#define XATTR_NAME_EVM XATTR_SECURITY_PREFIX XATTR_EVM_SUFFIX + #define XATTR_SELINUX_SUFFIX "selinux" #define XATTR_NAME_SELINUX XATTR_SECURITY_PREFIX XATTR_SELINUX_SUFFIX @@ -49,6 +52,11 @@ #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX +#define XATTR_POSIX_ACL_ACCESS "posix_acl_access" +#define XATTR_NAME_POSIX_ACL_ACCESS XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_ACCESS +#define XATTR_POSIX_ACL_DEFAULT "posix_acl_default" +#define XATTR_NAME_POSIX_ACL_DEFAULT XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_DEFAULT + #ifdef __KERNEL__ #include <linux/types.h> @@ -67,6 +75,12 @@ struct xattr_handler { size_t size, int flags, int handler_flags); }; +struct xattr { + char *name; + void *value; + size_t value_len; +}; + ssize_t xattr_getsecurity(struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); @@ -78,7 +92,10 @@ ssize_t generic_getxattr(struct dentry *dentry, const char *name, void *buffer, ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); int generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int generic_removexattr(struct dentry *dentry, const char *name); - +ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, + char **xattr_value, size_t size, gfp_t flags); +int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, + const char *value, size_t size, gfp_t flags); #endif /* __KERNEL__ */ #endif /* _LINUX_XATTR_H */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 1aaf915656f3..8fa4430f99c1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -900,6 +900,7 @@ struct netns_ipvs { volatile int sync_state; volatile int master_syncid; volatile int backup_syncid; + struct mutex sync_mutex; /* multicast interface name */ char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; diff --git a/include/net/udplite.h b/include/net/udplite.h index 673a024c6b2a..5f097ca7d5c5 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -66,40 +66,34 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) return 0; } -static inline int udplite_sender_cscov(struct udp_sock *up, struct udphdr *uh) +/* Slow-path computation of checksum. Socket is locked. */ +static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) { + const struct udp_sock *up = udp_sk(skb->sk); int cscov = up->len; + __wsum csum = 0; - /* - * Sender has set `partial coverage' option on UDP-Lite socket - */ - if (up->pcflag & UDPLITE_SEND_CC) { + if (up->pcflag & UDPLITE_SEND_CC) { + /* + * Sender has set `partial coverage' option on UDP-Lite socket. + * The special case "up->pcslen == 0" signifies full coverage. + */ if (up->pcslen < up->len) { - /* up->pcslen == 0 means that full coverage is required, - * partial coverage only if 0 < up->pcslen < up->len */ - if (0 < up->pcslen) { - cscov = up->pcslen; - } - uh->len = htons(up->pcslen); + if (0 < up->pcslen) + cscov = up->pcslen; + udp_hdr(skb)->len = htons(up->pcslen); } - /* - * NOTE: Causes for the error case `up->pcslen > up->len': - * (i) Application error (will not be penalized). - * (ii) Payload too big for send buffer: data is split - * into several packets, each with its own header. - * In this case (e.g. last segment), coverage may - * exceed packet length. - * Since packets with coverage length > packet length are - * illegal, we fall back to the defaults here. - */ + /* + * NOTE: Causes for the error case `up->pcslen > up->len': + * (i) Application error (will not be penalized). + * (ii) Payload too big for send buffer: data is split + * into several packets, each with its own header. + * In this case (e.g. last segment), coverage may + * exceed packet length. + * Since packets with coverage length > packet length are + * illegal, we fall back to the defaults here. + */ } - return cscov; -} - -static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) -{ - int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); - __wsum csum = 0; skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ @@ -115,16 +109,21 @@ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) return csum; } +/* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { - struct sock *sk = skb->sk; - int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); + const struct udp_sock *up = udp_sk(skb->sk); const int off = skb_transport_offset(skb); - const int len = skb->len - off; + int len = skb->len - off; + if ((up->pcflag & UDPLITE_SEND_CC) && up->pcslen < len) { + if (0 < up->pcslen) + len = up->pcslen; + udp_hdr(skb)->len = htons(up->pcslen); + } skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ - return skb_checksum(skb, off, min(cscov, len), 0); + return skb_checksum(skb, off, len, 0); } extern void udplite4_register(void); diff --git a/include/xen/balloon.h b/include/xen/balloon.h index 76f7538bb339..d29c153705bc 100644 --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -25,8 +25,9 @@ extern struct balloon_stats balloon_stats; void balloon_set_new_target(unsigned long target); -int alloc_xenballooned_pages(int nr_pages, struct page** pages); -void free_xenballooned_pages(int nr_pages, struct page** pages); +int alloc_xenballooned_pages(int nr_pages, struct page **pages, + bool highmem); +void free_xenballooned_pages(int nr_pages, struct page **pages); struct sys_device; #ifdef CONFIG_XEN_SELFBALLOONING diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index b1fab6b5b3ef..6b99bfbd785d 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -156,6 +156,7 @@ unsigned int gnttab_max_grant_frames(void); #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, struct page **pages, unsigned int count); diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index 99fcffb372d1..f0b6890370be 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -26,7 +26,11 @@ enum xsd_sockmsg_type XS_SET_PERMS, XS_WATCH_EVENT, XS_ERROR, - XS_IS_DOMAIN_INTRODUCED + XS_IS_DOMAIN_INTRODUCED, + XS_RESUME, + XS_SET_TARGET, + XS_RESTRICT, + XS_RESET_WATCHES }; #define XS_WRITE_NONE "NONE" diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index 534cac89a77d..c1080d9c705d 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -109,6 +109,7 @@ struct physdev_irq { #define MAP_PIRQ_TYPE_MSI 0x0 #define MAP_PIRQ_TYPE_GSI 0x1 #define MAP_PIRQ_TYPE_UNKNOWN 0x2 +#define MAP_PIRQ_TYPE_MSI_SEG 0x3 #define PHYSDEVOP_map_pirq 13 struct physdev_map_pirq { @@ -119,7 +120,7 @@ struct physdev_map_pirq { int index; /* IN or OUT */ int pirq; - /* IN */ + /* IN - high 16 bits hold segment for MAP_PIRQ_TYPE_MSI_SEG */ int bus; /* IN */ int devfn; @@ -198,6 +199,37 @@ struct physdev_get_free_pirq { uint32_t pirq; }; +#define XEN_PCI_DEV_EXTFN 0x1 +#define XEN_PCI_DEV_VIRTFN 0x2 +#define XEN_PCI_DEV_PXM 0x4 + +#define PHYSDEVOP_pci_device_add 25 +struct physdev_pci_device_add { + /* IN */ + uint16_t seg; + uint8_t bus; + uint8_t devfn; + uint32_t flags; + struct { + uint8_t bus; + uint8_t devfn; + } physfn; +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint32_t optarr[]; +#elif defined(__GNUC__) + uint32_t optarr[0]; +#endif +}; + +#define PHYSDEVOP_pci_device_remove 26 +#define PHYSDEVOP_restore_msi_ext 27 +struct physdev_pci_device { + /* IN */ + uint16_t seg; + uint8_t bus; + uint8_t devfn; +}; + /* * Notify that some PIRQ-bound event channels have been unmasked. * ** This command is obsolete since interface version 0x00030202 and is ** diff --git a/include/xen/page.h b/include/xen/page.h index 0be36b976f4b..12765b6f9517 100644 --- a/include/xen/page.h +++ b/include/xen/page.h @@ -3,6 +3,16 @@ #include <asm/xen/page.h> -extern phys_addr_t xen_extra_mem_start, xen_extra_mem_size; +struct xen_memory_region { + phys_addr_t start; + phys_addr_t size; +}; + +#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820MAX */ + +extern __initdata +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS]; + +extern unsigned long xen_released_pages; #endif /* _XEN_PAGE_H */ diff --git a/kernel/cred.c b/kernel/cred.c index 8ef31f53c44c..bb55d052d858 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -644,6 +644,9 @@ void __init cred_init(void) */ struct cred *prepare_kernel_cred(struct task_struct *daemon) { +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred; +#endif const struct cred *old; struct cred *new; @@ -651,6 +654,14 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (!new) return NULL; +#ifdef CONFIG_KEYS + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) { + kmem_cache_free(cred_jar, new); + return NULL; + } +#endif + kdebug("prepare_kernel_cred() alloc %p", new); if (daemon) @@ -667,8 +678,11 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) get_group_info(new->group_info); #ifdef CONFIG_KEYS - atomic_inc(&init_tgcred.usage); - new->tgcred = &init_tgcred; + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + tgcred->process_keyring = NULL; + tgcred->session_keyring = NULL; + new->tgcred = tgcred; new->request_key_auth = NULL; new->thread_keyring = NULL; new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c8008dd58ef2..640ded8f5c48 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -274,9 +274,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) struct task_cputime sum; unsigned long flags; - spin_lock_irqsave(&cputimer->lock, flags); if (!cputimer->running) { - cputimer->running = 1; /* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have @@ -284,8 +282,11 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) * it. */ thread_group_cputime(tsk, &sum); + spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 1; update_gt_cputime(&cputimer->cputime, &sum); - } + } else + spin_lock_irqsave(&cputimer->lock, flags); *times = cputimer->cputime; spin_unlock_irqrestore(&cputimer->lock, flags); } diff --git a/kernel/sys.c b/kernel/sys.c index 18ee1d2f6474..1dbbe695a5ef 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1172,7 +1172,7 @@ DECLARE_RWSEM(uts_sem); static int override_release(char __user *release, int len) { int ret = 0; - char buf[len]; + char buf[65]; if (current->personality & UNAME26) { char *rest = UTS_RELEASE; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c0cb9c4bc46d..103c171ce605 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1081,7 +1081,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT depends on !X86_64 select STACKTRACE - select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE + select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND help Provide stacktrace filter for fault-injection capabilities @@ -1091,7 +1091,7 @@ config LATENCYTOP depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT depends on PROC_FS - select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE + select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND select KALLSYMS select KALLSYMS_ALL select STACKTRACE diff --git a/lib/hexdump.c b/lib/hexdump.c index f5fe6ba7a3ab..51d5ae210244 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -38,14 +38,21 @@ EXPORT_SYMBOL(hex_to_bin); * @dst: binary result * @src: ascii hexadecimal string * @count: result length + * + * Return 0 on success, -1 in case of bad input. */ -void hex2bin(u8 *dst, const char *src, size_t count) +int hex2bin(u8 *dst, const char *src, size_t count) { while (count--) { - *dst = hex_to_bin(*src++) << 4; - *dst += hex_to_bin(*src++); - dst++; + int hi = hex_to_bin(*src++); + int lo = hex_to_bin(*src++); + + if ((hi < 0) || (lo < 0)) + return -1; + + *dst++ = (hi << 4) | lo; } + return 0; } EXPORT_SYMBOL(hex2bin); diff --git a/mm/migrate.c b/mm/migrate.c index 666e4e677414..14d0a6a632f6 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -120,10 +120,10 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, ptep = pte_offset_map(pmd, addr); - if (!is_swap_pte(*ptep)) { - pte_unmap(ptep); - goto out; - } + /* + * Peek to check is_swap_pte() before taking ptlock? No, we + * can race mremap's move_ptes(), which skips anon_vma lock. + */ ptl = pte_lockptr(mm, pmd); } diff --git a/mm/shmem.c b/mm/shmem.c index 32f6763f16fb..2d3577295298 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1458,7 +1458,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, - &dentry->d_name, NULL, + &dentry->d_name, NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { @@ -1598,7 +1598,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (!inode) return -ENOSPC; - error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, + error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 61f1f623091d..e8292369cdcf 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -26,6 +26,8 @@ /* Bluetooth L2CAP sockets. */ +#include <linux/security.h> + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> @@ -933,6 +935,8 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->force_reliable = pchan->force_reliable; chan->flushable = pchan->flushable; chan->force_active = pchan->force_active; + + security_sk_clone(parent, sk); } else { switch (sk->sk_type) { diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 482722bbc7a0..5417f6127323 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -42,6 +42,7 @@ #include <linux/device.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/security.h> #include <net/sock.h> #include <asm/system.h> @@ -264,6 +265,8 @@ static void rfcomm_sock_init(struct sock *sk, struct sock *parent) pi->sec_level = rfcomm_pi(parent)->sec_level; pi->role_switch = rfcomm_pi(parent)->role_switch; + + security_sk_clone(parent, sk); } else { pi->dlc->defer_setup = 0; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8270f05e3f1f..a324b009e34b 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -41,6 +41,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/list.h> +#include <linux/security.h> #include <net/sock.h> #include <asm/system.h> @@ -403,8 +404,10 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); - if (parent) + if (parent) { sk->sk_type = parent->sk_type; + security_sk_clone(parent, sk); + } } static struct proto sco_proto = { diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index e73815456adf..1d420f64ff27 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -161,9 +161,10 @@ static void del_nbp(struct net_bridge_port *p) call_rcu(&p->rcu, destroy_nbp_rcu); } -/* called with RTNL */ -static void del_br(struct net_bridge *br, struct list_head *head) +/* Delete bridge device */ +void br_dev_delete(struct net_device *dev, struct list_head *head) { + struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p, *n; list_for_each_entry_safe(p, n, &br->port_list, list) { @@ -268,7 +269,7 @@ int br_del_bridge(struct net *net, const char *name) } else - del_br(netdev_priv(dev), NULL); + br_dev_delete(dev, NULL); rtnl_unlock(); return ret; @@ -449,7 +450,7 @@ void __net_exit br_net_exit(struct net *net) rtnl_lock(); for_each_netdev(net, dev) if (dev->priv_flags & IFF_EBRIDGE) - del_br(netdev_priv(dev), &list); + br_dev_delete(dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5b1ed1ba9aa7..e5f9ece3c9a0 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -210,6 +210,7 @@ static struct rtnl_link_ops br_link_ops __read_mostly = { .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .validate = br_validate, + .dellink = br_dev_delete, }; int __init br_netlink_init(void) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 78cc364997d9..857a021deea9 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -294,6 +294,7 @@ static inline int br_is_root_bridge(const struct net_bridge *br) /* br_device.c */ extern void br_dev_setup(struct net_device *dev); +extern void br_dev_delete(struct net_device *dev, struct list_head *list); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev); #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3231b468bb72..27071ee2a4e1 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -475,8 +475,11 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_del_rcu(&rule->list); - if (rule->action == FR_ACT_GOTO) + if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } /* * Check if this rule is a target to any of them. If so, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d2fe4e06b472..0ce3d06dce60 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -328,6 +328,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); + tw->tw_transparent = inet_sk(sk)->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3b5669a2582d..d27c797f9f05 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -875,6 +875,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, skb_reset_transport_header(skb); __skb_push(skb, skb_gro_offset(skb)); + ops = rcu_dereference(inet6_protos[proto]); if (!ops || !ops->gro_receive) goto out_unlock; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ad4ac2601a56..34b2ddeacb67 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1045,8 +1045,10 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + hdr_len; old_headroom = skb_headroom(skb); - if (skb_cow_head(skb, headroom)) + if (skb_cow_head(skb, headroom)) { + dev_kfree_skb(skb); goto abort; + } new_headroom = skb_headroom(skb); skb_orphan(skb); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5290ac353a5e..e3be48bf4dcd 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2283,6 +2283,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) struct ip_vs_service *svc; struct ip_vs_dest_user *udest_compat; struct ip_vs_dest_user_kern udest; + struct netns_ipvs *ipvs = net_ipvs(net); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -2303,6 +2304,24 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* increase the module use count */ ip_vs_use_count_inc(); + /* Handle daemons since they have another lock */ + if (cmd == IP_VS_SO_SET_STARTDAEMON || + cmd == IP_VS_SO_SET_STOPDAEMON) { + struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; + + if (mutex_lock_interruptible(&ipvs->sync_mutex)) { + ret = -ERESTARTSYS; + goto out_dec; + } + if (cmd == IP_VS_SO_SET_STARTDAEMON) + ret = start_sync_thread(net, dm->state, dm->mcast_ifn, + dm->syncid); + else + ret = stop_sync_thread(net, dm->state); + mutex_unlock(&ipvs->sync_mutex); + goto out_dec; + } + if (mutex_lock_interruptible(&__ip_vs_mutex)) { ret = -ERESTARTSYS; goto out_dec; @@ -2316,15 +2335,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg); goto out_unlock; - } else if (cmd == IP_VS_SO_SET_STARTDAEMON) { - struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = start_sync_thread(net, dm->state, dm->mcast_ifn, - dm->syncid); - goto out_unlock; - } else if (cmd == IP_VS_SO_SET_STOPDAEMON) { - struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = stop_sync_thread(net, dm->state); - goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2584,6 +2594,33 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) if (copy_from_user(arg, user, copylen) != 0) return -EFAULT; + /* + * Handle daemons first since it has its own locking + */ + if (cmd == IP_VS_SO_GET_DAEMON) { + struct ip_vs_daemon_user d[2]; + + memset(&d, 0, sizeof(d)); + if (mutex_lock_interruptible(&ipvs->sync_mutex)) + return -ERESTARTSYS; + + if (ipvs->sync_state & IP_VS_STATE_MASTER) { + d[0].state = IP_VS_STATE_MASTER; + strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, + sizeof(d[0].mcast_ifn)); + d[0].syncid = ipvs->master_syncid; + } + if (ipvs->sync_state & IP_VS_STATE_BACKUP) { + d[1].state = IP_VS_STATE_BACKUP; + strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, + sizeof(d[1].mcast_ifn)); + d[1].syncid = ipvs->backup_syncid; + } + if (copy_to_user(user, &d, sizeof(d)) != 0) + ret = -EFAULT; + mutex_unlock(&ipvs->sync_mutex); + return ret; + } if (mutex_lock_interruptible(&__ip_vs_mutex)) return -ERESTARTSYS; @@ -2681,28 +2718,6 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } break; - case IP_VS_SO_GET_DAEMON: - { - struct ip_vs_daemon_user d[2]; - - memset(&d, 0, sizeof(d)); - if (ipvs->sync_state & IP_VS_STATE_MASTER) { - d[0].state = IP_VS_STATE_MASTER; - strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, - sizeof(d[0].mcast_ifn)); - d[0].syncid = ipvs->master_syncid; - } - if (ipvs->sync_state & IP_VS_STATE_BACKUP) { - d[1].state = IP_VS_STATE_BACKUP; - strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, - sizeof(d[1].mcast_ifn)); - d[1].syncid = ipvs->backup_syncid; - } - if (copy_to_user(user, &d, sizeof(d)) != 0) - ret = -EFAULT; - } - break; - default: ret = -EINVAL; } @@ -3205,7 +3220,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct net *net = skb_sknet(skb); struct netns_ipvs *ipvs = net_ipvs(net); - mutex_lock(&__ip_vs_mutex); + mutex_lock(&ipvs->sync_mutex); if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, ipvs->master_mcast_ifn, @@ -3225,7 +3240,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, } nla_put_failure: - mutex_unlock(&__ip_vs_mutex); + mutex_unlock(&ipvs->sync_mutex); return skb->len; } @@ -3271,13 +3286,9 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) return ip_vs_set_timeout(net, &t); } -static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { - struct ip_vs_service *svc = NULL; - struct ip_vs_service_user_kern usvc; - struct ip_vs_dest_user_kern udest; int ret = 0, cmd; - int need_full_svc = 0, need_full_dest = 0; struct net *net; struct netns_ipvs *ipvs; @@ -3285,19 +3296,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; - mutex_lock(&__ip_vs_mutex); - - if (cmd == IPVS_CMD_FLUSH) { - ret = ip_vs_flush(net); - goto out; - } else if (cmd == IPVS_CMD_SET_CONFIG) { - ret = ip_vs_genl_set_config(net, info->attrs); - goto out; - } else if (cmd == IPVS_CMD_NEW_DAEMON || - cmd == IPVS_CMD_DEL_DAEMON) { - + if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1]; + mutex_lock(&ipvs->sync_mutex); if (!info->attrs[IPVS_CMD_ATTR_DAEMON] || nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX, info->attrs[IPVS_CMD_ATTR_DAEMON], @@ -3310,6 +3312,33 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ret = ip_vs_genl_new_daemon(net, daemon_attrs); else ret = ip_vs_genl_del_daemon(net, daemon_attrs); +out: + mutex_unlock(&ipvs->sync_mutex); + } + return ret; +} + +static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct ip_vs_service *svc = NULL; + struct ip_vs_service_user_kern usvc; + struct ip_vs_dest_user_kern udest; + int ret = 0, cmd; + int need_full_svc = 0, need_full_dest = 0; + struct net *net; + struct netns_ipvs *ipvs; + + net = skb_sknet(skb); + ipvs = net_ipvs(net); + cmd = info->genlhdr->cmd; + + mutex_lock(&__ip_vs_mutex); + + if (cmd == IPVS_CMD_FLUSH) { + ret = ip_vs_flush(net); + goto out; + } else if (cmd == IPVS_CMD_SET_CONFIG) { + ret = ip_vs_genl_set_config(net, info->attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { @@ -3536,13 +3565,13 @@ static struct genl_ops ip_vs_genl_ops[] __read_mostly = { .cmd = IPVS_CMD_NEW_DAEMON, .flags = GENL_ADMIN_PERM, .policy = ip_vs_cmd_policy, - .doit = ip_vs_genl_set_cmd, + .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_DEL_DAEMON, .flags = GENL_ADMIN_PERM, .policy = ip_vs_cmd_policy, - .doit = ip_vs_genl_set_cmd, + .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_GET_DAEMON, diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 7ee7215b8ba0..3cdd479f9b5d 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -61,6 +61,7 @@ #define SYNC_PROTO_VER 1 /* Protocol version in header */ +static struct lock_class_key __ipvs_sync_key; /* * IPVS sync connection entry * Version 0, i.e. original version. @@ -1545,6 +1546,7 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + if (state == IP_VS_STATE_MASTER) { if (ipvs->master_thread) return -EEXIST; @@ -1667,6 +1669,7 @@ int __net_init ip_vs_sync_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); INIT_LIST_HEAD(&ipvs->sync_queue); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); @@ -1680,7 +1683,9 @@ int __net_init ip_vs_sync_net_init(struct net *net) void ip_vs_sync_net_cleanup(struct net *net) { int retc; + struct netns_ipvs *ipvs = net_ipvs(net); + mutex_lock(&ipvs->sync_mutex); retc = stop_sync_thread(net, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); @@ -1688,4 +1693,5 @@ void ip_vs_sync_net_cleanup(struct net *net) retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); + mutex_unlock(&ipvs->sync_mutex); } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index cf616e55ca41..d69facdd9a7a 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -241,8 +241,8 @@ static int gre_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.stream_timeout); /* Also, more likely to be important, and not a probe. */ - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); + if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.timeout); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d30615419b4d..5f03e4ea65bf 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -91,7 +91,7 @@ int x25_parse_address_block(struct sk_buff *skb, int needed; int rc; - if (skb->len < 1) { + if (!pskb_may_pull(skb, 1)) { /* packet has no address block */ rc = 0; goto empty; @@ -100,7 +100,7 @@ int x25_parse_address_block(struct sk_buff *skb, len = *skb->data; needed = 1 + (len >> 4) + (len & 0x0f); - if (skb->len < needed) { + if (!pskb_may_pull(skb, needed)) { /* packet is too short to hold the addresses it claims to hold */ rc = -1; @@ -295,7 +295,8 @@ static struct sock *x25_find_listener(struct x25_address *addr, * Found a listening socket, now check the incoming * call user data vs this sockets call user data */ - if(skb->len > 0 && x25_sk(s)->cudmatchlength > 0) { + if (x25_sk(s)->cudmatchlength > 0 && + skb->len >= x25_sk(s)->cudmatchlength) { if((memcmp(x25_sk(s)->calluserdata.cuddata, skb->data, x25_sk(s)->cudmatchlength)) == 0) { @@ -951,14 +952,27 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, * * Facilities length is mandatory in call request packets */ - if (skb->len < 1) + if (!pskb_may_pull(skb, 1)) goto out_clear_request; len = skb->data[0] + 1; - if (skb->len < len) + if (!pskb_may_pull(skb, len)) goto out_clear_request; skb_pull(skb,len); /* + * Ensure that the amount of call user data is valid. + */ + if (skb->len > X25_MAX_CUD_LEN) + goto out_clear_request; + + /* + * Get all the call user data so it can be used in + * x25_find_listener and skb_copy_from_linear_data up ahead. + */ + if (!pskb_may_pull(skb, skb->len)) + goto out_clear_request; + + /* * Find a listener for the particular address/cud pair. */ sk = x25_find_listener(&source_addr,skb); @@ -1166,6 +1180,9 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, * byte of the user data is the logical value of the Q Bit. */ if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { + if (!pskb_may_pull(skb, 1)) + goto out_kfree_skb; + qbit = skb->data[0]; skb_pull(skb, 1); } @@ -1244,7 +1261,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, struct x25_sock *x25 = x25_sk(sk); struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)msg->msg_name; size_t copied; - int qbit; + int qbit, header_len = x25->neighbour->extended ? + X25_EXT_MIN_LEN : X25_STD_MIN_LEN; + struct sk_buff *skb; unsigned char *asmptr; int rc = -ENOTCONN; @@ -1265,6 +1284,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, skb = skb_dequeue(&x25->interrupt_in_queue); + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + goto out_free_dgram; + skb_pull(skb, X25_STD_MIN_LEN); /* @@ -1285,10 +1307,12 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) goto out; + if (!pskb_may_pull(skb, header_len)) + goto out_free_dgram; + qbit = (skb->data[0] & X25_Q_BIT) == X25_Q_BIT; - skb_pull(skb, x25->neighbour->extended ? - X25_EXT_MIN_LEN : X25_STD_MIN_LEN); + skb_pull(skb, header_len); if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { asmptr = skb_push(skb, 1); diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index e547ca1578c3..fa2b41888bd9 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -32,6 +32,9 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) unsigned short frametype; unsigned int lci; + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + return 0; + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); @@ -115,6 +118,9 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, goto drop; } + if (!pskb_may_pull(skb, 1)) + return 0; + switch (skb->data[0]) { case X25_IFACE_DATA: diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index f77e4e75f914..36384a1fa9f2 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -44,7 +44,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask) { - unsigned char *p = skb->data; + unsigned char *p; unsigned int len; *vc_fac_mask = 0; @@ -60,14 +60,16 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, memset(dte_facs->called_ae, '\0', sizeof(dte_facs->called_ae)); memset(dte_facs->calling_ae, '\0', sizeof(dte_facs->calling_ae)); - if (skb->len < 1) + if (!pskb_may_pull(skb, 1)) return 0; - len = *p++; + len = skb->data[0]; - if (len >= skb->len) + if (!pskb_may_pull(skb, 1 + len)) return -1; + p = skb->data + 1; + while (len > 0) { switch (*p & X25_FAC_CLASS_MASK) { case X25_FAC_CLASS_A: diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 0b073b51b183..a49cd4ec551a 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -107,6 +107,8 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp /* * Parse the data in the frame. */ + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + goto out_clear; skb_pull(skb, X25_STD_MIN_LEN); len = x25_parse_address_block(skb, &source_addr, @@ -127,9 +129,11 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp * Copy any Call User Data. */ if (skb->len > 0) { - skb_copy_from_linear_data(skb, - x25->calluserdata.cuddata, - skb->len); + if (skb->len > X25_MAX_CUD_LEN) + goto out_clear; + + skb_copy_bits(skb, 0, x25->calluserdata.cuddata, + skb->len); x25->calluserdata.cudlength = skb->len; } if (!sock_flag(sk, SOCK_DEAD)) @@ -137,6 +141,9 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; } case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]); break; @@ -164,6 +171,9 @@ static int x25_state2_machine(struct sock *sk, struct sk_buff *skb, int frametyp switch (frametype) { case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -177,6 +187,11 @@ static int x25_state2_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_start_t23timer(sk); + return 0; } /* @@ -206,6 +221,9 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -304,6 +322,12 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return queued; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* @@ -313,13 +337,13 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp */ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametype) { + struct x25_sock *x25 = x25_sk(sk); + switch (frametype) { case X25_RESET_REQUEST: x25_write_internal(sk, X25_RESET_CONFIRMATION); case X25_RESET_CONFIRMATION: { - struct x25_sock *x25 = x25_sk(sk); - x25_stop_timer(sk); x25->condition = 0x00; x25->va = 0; @@ -331,6 +355,9 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; } case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -340,6 +367,12 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* Higher level upcall for a LAPB frame */ diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 037958ff8eed..4acacf3c6617 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -90,6 +90,9 @@ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb, break; case X25_DIAGNOSTIC: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 4)) + break; + printk(KERN_WARNING "x25: diagnostic #%d - %02X %02X %02X\n", skb->data[3], skb->data[4], skb->data[5], skb->data[6]); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 24a342ebc7f5..5170d52bfd96 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -269,7 +269,11 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, int *d, int *m) { struct x25_sock *x25 = x25_sk(sk); - unsigned char *frame = skb->data; + unsigned char *frame; + + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; *ns = *nr = *q = *d = *m = 0; @@ -294,6 +298,10 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, if (frame[2] == X25_RR || frame[2] == X25_RNR || frame[2] == X25_REJ) { + if (!pskb_may_pull(skb, X25_EXT_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; + *nr = (frame[3] >> 1) & 0x7F; return frame[2]; } @@ -308,6 +316,10 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, if (x25->neighbour->extended) { if ((frame[2] & 0x01) == X25_DATA) { + if (!pskb_may_pull(skb, X25_EXT_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; + *q = (frame[0] & X25_Q_BIT) == X25_Q_BIT; *d = (frame[0] & X25_D_BIT) == X25_D_BIT; *m = (frame[3] & X25_EXT_M_BIT) == X25_EXT_M_BIT; diff --git a/security/Kconfig b/security/Kconfig index e0f08b52e4ab..51bd5a0b69ae 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -38,7 +38,9 @@ config TRUSTED_KEYS config ENCRYPTED_KEYS tristate "ENCRYPTED KEYS" - depends on KEYS && TRUSTED_KEYS + depends on KEYS + select CRYPTO + select CRYPTO_HMAC select CRYPTO_AES select CRYPTO_CBC select CRYPTO_SHA256 @@ -186,7 +188,7 @@ source security/smack/Kconfig source security/tomoyo/Kconfig source security/apparmor/Kconfig -source security/integrity/ima/Kconfig +source security/integrity/Kconfig choice prompt "Default security module" diff --git a/security/Makefile b/security/Makefile index 8bb0fe9e1ca9..a5e502f8a05b 100644 --- a/security/Makefile +++ b/security/Makefile @@ -24,5 +24,5 @@ obj-$(CONFIG_SECURITY_APPARMOR) += apparmor/built-in.o obj-$(CONFIG_CGROUP_DEVICE) += device_cgroup.o # Object integrity file lists -subdir-$(CONFIG_IMA) += integrity/ima -obj-$(CONFIG_IMA) += integrity/ima/built-in.o +subdir-$(CONFIG_INTEGRITY) += integrity +obj-$(CONFIG_INTEGRITY) += integrity/built-in.o diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 0848292982a2..69ddb47787b2 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -200,7 +200,7 @@ void __init aa_destroy_aafs(void) * * Returns: error on failure */ -int __init aa_create_aafs(void) +static int __init aa_create_aafs(void) { int error; diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c index 649fad88869b..7ee05c6f3c64 100644 --- a/security/apparmor/ipc.c +++ b/security/apparmor/ipc.c @@ -19,6 +19,7 @@ #include "include/capability.h" #include "include/context.h" #include "include/policy.h" +#include "include/ipc.h" /* call back to audit ptrace fields */ static void audit_cb(struct audit_buffer *ab, void *va) diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index b82e383beb77..9516948041ad 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -18,6 +18,7 @@ #include <linux/vmalloc.h> #include "include/audit.h" +#include "include/apparmor.h" /** diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index d6d9a57b5652..741dd13e089b 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -381,11 +381,11 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile) profile->file.trans.size = size; for (i = 0; i < size; i++) { char *str; - int c, j, size = unpack_strdup(e, &str, NULL); + int c, j, size2 = unpack_strdup(e, &str, NULL); /* unpack_strdup verifies that the last character is * null termination byte. */ - if (!size) + if (!size2) goto fail; profile->file.trans.table[i] = str; /* verify that name doesn't start with space */ @@ -393,7 +393,7 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile) goto fail; /* count internal # of internal \0 */ - for (c = j = 0; j < size - 2; j++) { + for (c = j = 0; j < size2 - 2; j++) { if (!str[j]) c++; } @@ -440,11 +440,11 @@ static bool unpack_rlimits(struct aa_ext *e, struct aa_profile *profile) if (size > RLIM_NLIMITS) goto fail; for (i = 0; i < size; i++) { - u64 tmp = 0; + u64 tmp2 = 0; int a = aa_map_resource(i); - if (!unpack_u64(e, &tmp, NULL)) + if (!unpack_u64(e, &tmp2, NULL)) goto fail; - profile->rlimits.limits[a].rlim_max = tmp; + profile->rlimits.limits[a].rlim_max = tmp2; } if (!unpack_nameX(e, AA_ARRAYEND, NULL)) goto fail; diff --git a/security/apparmor/procattr.c b/security/apparmor/procattr.c index 04a2cf8d1b65..1b41c542d376 100644 --- a/security/apparmor/procattr.c +++ b/security/apparmor/procattr.c @@ -16,6 +16,7 @@ #include "include/context.h" #include "include/policy.h" #include "include/domain.h" +#include "include/procattr.h" /** diff --git a/security/commoncap.c b/security/commoncap.c index a93b3b733079..ee4f8486e5f5 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -332,7 +332,8 @@ int cap_inode_killpriv(struct dentry *dentry) */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, - bool *effective) + bool *effective, + bool *has_cap) { struct cred *new = bprm->cred; unsigned i; @@ -341,6 +342,9 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; + if (caps->magic_etc & VFS_CAP_REVISION_MASK) + *has_cap = true; + CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; @@ -424,7 +428,7 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ -static int get_file_caps(struct linux_binprm *bprm, bool *effective) +static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_cap) { struct dentry *dentry; int rc = 0; @@ -450,7 +454,7 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective) goto out; } - rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective); + rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_cap); if (rc == -EINVAL) printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n", __func__, rc, bprm->filename); @@ -475,11 +479,11 @@ int cap_bprm_set_creds(struct linux_binprm *bprm) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; - bool effective; + bool effective, has_cap = false; int ret; effective = false; - ret = get_file_caps(bprm, &effective); + ret = get_file_caps(bprm, &effective, &has_cap); if (ret < 0) return ret; @@ -489,7 +493,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm) * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ - if (effective && new->uid != 0 && new->euid == 0) { + if (has_cap && new->uid != 0 && new->euid == 0) { warn_setuid_and_fcaps_mixed(bprm->filename); goto skip; } diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig new file mode 100644 index 000000000000..4bf00acf7937 --- /dev/null +++ b/security/integrity/Kconfig @@ -0,0 +1,7 @@ +# +config INTEGRITY + def_bool y + depends on IMA || EVM + +source security/integrity/ima/Kconfig +source security/integrity/evm/Kconfig diff --git a/security/integrity/Makefile b/security/integrity/Makefile new file mode 100644 index 000000000000..0ae44aea6516 --- /dev/null +++ b/security/integrity/Makefile @@ -0,0 +1,12 @@ +# +# Makefile for caching inode integrity data (iint) +# + +obj-$(CONFIG_INTEGRITY) += integrity.o + +integrity-y := iint.o + +subdir-$(CONFIG_IMA) += ima +obj-$(CONFIG_IMA) += ima/built-in.o +subdir-$(CONFIG_EVM) += evm +obj-$(CONFIG_EVM) += evm/built-in.o diff --git a/security/integrity/evm/Kconfig b/security/integrity/evm/Kconfig new file mode 100644 index 000000000000..afbb59dd262d --- /dev/null +++ b/security/integrity/evm/Kconfig @@ -0,0 +1,13 @@ +config EVM + boolean "EVM support" + depends on SECURITY && KEYS && (TRUSTED_KEYS=y || TRUSTED_KEYS=n) + select CRYPTO_HMAC + select CRYPTO_MD5 + select CRYPTO_SHA1 + select ENCRYPTED_KEYS + default n + help + EVM protects a file's security extended attributes against + integrity attacks. + + If you are unsure how to answer this question, answer N. diff --git a/security/integrity/evm/Makefile b/security/integrity/evm/Makefile new file mode 100644 index 000000000000..7393c415a066 --- /dev/null +++ b/security/integrity/evm/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for building the Extended Verification Module(EVM) +# +obj-$(CONFIG_EVM) += evm.o + +evm-y := evm_main.o evm_crypto.o evm_secfs.o +evm-$(CONFIG_FS_POSIX_ACL) += evm_posix_acl.o diff --git a/security/integrity/evm/evm.h b/security/integrity/evm/evm.h new file mode 100644 index 000000000000..d320f5197437 --- /dev/null +++ b/security/integrity/evm/evm.h @@ -0,0 +1,38 @@ +/* + * Copyright (C) 2005-2010 IBM Corporation + * + * Authors: + * Mimi Zohar <zohar@us.ibm.com> + * Kylene Hall <kjhall@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + * + * File: evm.h + * + */ +#include <linux/xattr.h> +#include <linux/security.h> +#include "../integrity.h" + +extern int evm_initialized; +extern char *evm_hmac; + +extern struct crypto_shash *hmac_tfm; + +/* List of EVM protected security xattrs */ +extern char *evm_config_xattrnames[]; + +extern int evm_init_key(void); +extern int evm_update_evmxattr(struct dentry *dentry, + const char *req_xattr_name, + const char *req_xattr_value, + size_t req_xattr_value_len); +extern int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name, + const char *req_xattr_value, + size_t req_xattr_value_len, char *digest); +extern int evm_init_hmac(struct inode *inode, const struct xattr *xattr, + char *hmac_val); +extern int evm_init_secfs(void); +extern void evm_cleanup_secfs(void); diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c new file mode 100644 index 000000000000..5dd5b140242c --- /dev/null +++ b/security/integrity/evm/evm_crypto.c @@ -0,0 +1,216 @@ +/* + * Copyright (C) 2005-2010 IBM Corporation + * + * Authors: + * Mimi Zohar <zohar@us.ibm.com> + * Kylene Hall <kjhall@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + * + * File: evm_crypto.c + * Using root's kernel master key (kmk), calculate the HMAC + */ + +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/xattr.h> +#include <keys/encrypted-type.h> +#include <crypto/hash.h> +#include "evm.h" + +#define EVMKEY "evm-key" +#define MAX_KEY_SIZE 128 +static unsigned char evmkey[MAX_KEY_SIZE]; +static int evmkey_len = MAX_KEY_SIZE; + +struct crypto_shash *hmac_tfm; + +static struct shash_desc *init_desc(void) +{ + int rc; + struct shash_desc *desc; + + if (hmac_tfm == NULL) { + hmac_tfm = crypto_alloc_shash(evm_hmac, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(hmac_tfm)) { + pr_err("Can not allocate %s (reason: %ld)\n", + evm_hmac, PTR_ERR(hmac_tfm)); + rc = PTR_ERR(hmac_tfm); + hmac_tfm = NULL; + return ERR_PTR(rc); + } + } + + desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac_tfm), + GFP_KERNEL); + if (!desc) + return ERR_PTR(-ENOMEM); + + desc->tfm = hmac_tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + rc = crypto_shash_setkey(hmac_tfm, evmkey, evmkey_len); + if (rc) + goto out; + rc = crypto_shash_init(desc); +out: + if (rc) { + kfree(desc); + return ERR_PTR(rc); + } + return desc; +} + +/* Protect against 'cutting & pasting' security.evm xattr, include inode + * specific info. + * + * (Additional directory/file metadata needs to be added for more complete + * protection.) + */ +static void hmac_add_misc(struct shash_desc *desc, struct inode *inode, + char *digest) +{ + struct h_misc { + unsigned long ino; + __u32 generation; + uid_t uid; + gid_t gid; + umode_t mode; + } hmac_misc; + + memset(&hmac_misc, 0, sizeof hmac_misc); + hmac_misc.ino = inode->i_ino; + hmac_misc.generation = inode->i_generation; + hmac_misc.uid = inode->i_uid; + hmac_misc.gid = inode->i_gid; + hmac_misc.mode = inode->i_mode; + crypto_shash_update(desc, (const u8 *)&hmac_misc, sizeof hmac_misc); + crypto_shash_final(desc, digest); +} + +/* + * Calculate the HMAC value across the set of protected security xattrs. + * + * Instead of retrieving the requested xattr, for performance, calculate + * the hmac using the requested xattr value. Don't alloc/free memory for + * each xattr, but attempt to re-use the previously allocated memory. + */ +int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name, + const char *req_xattr_value, size_t req_xattr_value_len, + char *digest) +{ + struct inode *inode = dentry->d_inode; + struct shash_desc *desc; + char **xattrname; + size_t xattr_size = 0; + char *xattr_value = NULL; + int error; + int size; + + if (!inode->i_op || !inode->i_op->getxattr) + return -EOPNOTSUPP; + desc = init_desc(); + if (IS_ERR(desc)) + return PTR_ERR(desc); + + error = -ENODATA; + for (xattrname = evm_config_xattrnames; *xattrname != NULL; xattrname++) { + if ((req_xattr_name && req_xattr_value) + && !strcmp(*xattrname, req_xattr_name)) { + error = 0; + crypto_shash_update(desc, (const u8 *)req_xattr_value, + req_xattr_value_len); + continue; + } + size = vfs_getxattr_alloc(dentry, *xattrname, + &xattr_value, xattr_size, GFP_NOFS); + if (size == -ENOMEM) { + error = -ENOMEM; + goto out; + } + if (size < 0) + continue; + + error = 0; + xattr_size = size; + crypto_shash_update(desc, (const u8 *)xattr_value, xattr_size); + } + hmac_add_misc(desc, inode, digest); + +out: + kfree(xattr_value); + kfree(desc); + return error; +} + +/* + * Calculate the hmac and update security.evm xattr + * + * Expects to be called with i_mutex locked. + */ +int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name, + const char *xattr_value, size_t xattr_value_len) +{ + struct inode *inode = dentry->d_inode; + struct evm_ima_xattr_data xattr_data; + int rc = 0; + + rc = evm_calc_hmac(dentry, xattr_name, xattr_value, + xattr_value_len, xattr_data.digest); + if (rc == 0) { + xattr_data.type = EVM_XATTR_HMAC; + rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_EVM, + &xattr_data, + sizeof(xattr_data), 0); + } + else if (rc == -ENODATA) + rc = inode->i_op->removexattr(dentry, XATTR_NAME_EVM); + return rc; +} + +int evm_init_hmac(struct inode *inode, const struct xattr *lsm_xattr, + char *hmac_val) +{ + struct shash_desc *desc; + + desc = init_desc(); + if (IS_ERR(desc)) { + printk(KERN_INFO "init_desc failed\n"); + return PTR_ERR(desc); + } + + crypto_shash_update(desc, lsm_xattr->value, lsm_xattr->value_len); + hmac_add_misc(desc, inode, hmac_val); + kfree(desc); + return 0; +} + +/* + * Get the key from the TPM for the SHA1-HMAC + */ +int evm_init_key(void) +{ + struct key *evm_key; + struct encrypted_key_payload *ekp; + int rc = 0; + + evm_key = request_key(&key_type_encrypted, EVMKEY, NULL); + if (IS_ERR(evm_key)) + return -ENOENT; + + down_read(&evm_key->sem); + ekp = evm_key->payload.data; + if (ekp->decrypted_datalen > MAX_KEY_SIZE) { + rc = -EINVAL; + goto out; + } + memcpy(evmkey, ekp->decrypted_data, ekp->decrypted_datalen); +out: + /* burn the original key contents */ + memset(ekp->decrypted_data, 0, ekp->decrypted_datalen); + up_read(&evm_key->sem); + key_put(evm_key); + return rc; +} diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c new file mode 100644 index 000000000000..92d3d99a9f7b --- /dev/null +++ b/security/integrity/evm/evm_main.c @@ -0,0 +1,384 @@ +/* + * Copyright (C) 2005-2010 IBM Corporation + * + * Author: + * Mimi Zohar <zohar@us.ibm.com> + * Kylene Hall <kjhall@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + * + * File: evm_main.c + * implements evm_inode_setxattr, evm_inode_post_setxattr, + * evm_inode_removexattr, and evm_verifyxattr + */ + +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/xattr.h> +#include <linux/integrity.h> +#include <linux/evm.h> +#include <crypto/hash.h> +#include "evm.h" + +int evm_initialized; + +char *evm_hmac = "hmac(sha1)"; + +char *evm_config_xattrnames[] = { +#ifdef CONFIG_SECURITY_SELINUX + XATTR_NAME_SELINUX, +#endif +#ifdef CONFIG_SECURITY_SMACK + XATTR_NAME_SMACK, +#endif + XATTR_NAME_CAPS, + NULL +}; + +static int evm_fixmode; +static int __init evm_set_fixmode(char *str) +{ + if (strncmp(str, "fix", 3) == 0) + evm_fixmode = 1; + return 0; +} +__setup("evm=", evm_set_fixmode); + +/* + * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr + * + * Compute the HMAC on the dentry's protected set of extended attributes + * and compare it against the stored security.evm xattr. + * + * For performance: + * - use the previoulsy retrieved xattr value and length to calculate the + * HMAC.) + * - cache the verification result in the iint, when available. + * + * Returns integrity status + */ +static enum integrity_status evm_verify_hmac(struct dentry *dentry, + const char *xattr_name, + char *xattr_value, + size_t xattr_value_len, + struct integrity_iint_cache *iint) +{ + struct evm_ima_xattr_data xattr_data; + enum integrity_status evm_status = INTEGRITY_PASS; + int rc; + + if (iint && iint->evm_status == INTEGRITY_PASS) + return iint->evm_status; + + /* if status is not PASS, try to check again - against -ENOMEM */ + + rc = evm_calc_hmac(dentry, xattr_name, xattr_value, + xattr_value_len, xattr_data.digest); + if (rc < 0) { + evm_status = (rc == -ENODATA) + ? INTEGRITY_NOXATTRS : INTEGRITY_FAIL; + goto out; + } + + xattr_data.type = EVM_XATTR_HMAC; + rc = vfs_xattr_cmp(dentry, XATTR_NAME_EVM, (u8 *)&xattr_data, + sizeof xattr_data, GFP_NOFS); + if (rc < 0) + evm_status = (rc == -ENODATA) + ? INTEGRITY_NOLABEL : INTEGRITY_FAIL; +out: + if (iint) + iint->evm_status = evm_status; + return evm_status; +} + +static int evm_protected_xattr(const char *req_xattr_name) +{ + char **xattrname; + int namelen; + int found = 0; + + namelen = strlen(req_xattr_name); + for (xattrname = evm_config_xattrnames; *xattrname != NULL; xattrname++) { + if ((strlen(*xattrname) == namelen) + && (strncmp(req_xattr_name, *xattrname, namelen) == 0)) { + found = 1; + break; + } + if (strncmp(req_xattr_name, + *xattrname + XATTR_SECURITY_PREFIX_LEN, + strlen(req_xattr_name)) == 0) { + found = 1; + break; + } + } + return found; +} + +/** + * evm_verifyxattr - verify the integrity of the requested xattr + * @dentry: object of the verify xattr + * @xattr_name: requested xattr + * @xattr_value: requested xattr value + * @xattr_value_len: requested xattr value length + * + * Calculate the HMAC for the given dentry and verify it against the stored + * security.evm xattr. For performance, use the xattr value and length + * previously retrieved to calculate the HMAC. + * + * Returns the xattr integrity status. + * + * This function requires the caller to lock the inode's i_mutex before it + * is executed. + */ +enum integrity_status evm_verifyxattr(struct dentry *dentry, + const char *xattr_name, + void *xattr_value, size_t xattr_value_len, + struct integrity_iint_cache *iint) +{ + if (!evm_initialized || !evm_protected_xattr(xattr_name)) + return INTEGRITY_UNKNOWN; + + if (!iint) { + iint = integrity_iint_find(dentry->d_inode); + if (!iint) + return INTEGRITY_UNKNOWN; + } + return evm_verify_hmac(dentry, xattr_name, xattr_value, + xattr_value_len, iint); +} +EXPORT_SYMBOL_GPL(evm_verifyxattr); + +/* + * evm_verify_current_integrity - verify the dentry's metadata integrity + * @dentry: pointer to the affected dentry + * + * Verify and return the dentry's metadata integrity. The exceptions are + * before EVM is initialized or in 'fix' mode. + */ +static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + + if (!evm_initialized || !S_ISREG(inode->i_mode) || evm_fixmode) + return 0; + return evm_verify_hmac(dentry, NULL, NULL, 0, NULL); +} + +/* + * evm_protect_xattr - protect the EVM extended attribute + * + * Prevent security.evm from being modified or removed without the + * necessary permissions or when the existing value is invalid. + * + * The posix xattr acls are 'system' prefixed, which normally would not + * affect security.evm. An interesting side affect of writing posix xattr + * acls is their modifying of the i_mode, which is included in security.evm. + * For posix xattr acls only, permit security.evm, even if it currently + * doesn't exist, to be updated. + */ +static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name, + const void *xattr_value, size_t xattr_value_len) +{ + enum integrity_status evm_status; + + if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + } else if (!evm_protected_xattr(xattr_name)) { + if (!posix_xattr_acl(xattr_name)) + return 0; + evm_status = evm_verify_current_integrity(dentry); + if ((evm_status == INTEGRITY_PASS) || + (evm_status == INTEGRITY_NOXATTRS)) + return 0; + return -EPERM; + } + evm_status = evm_verify_current_integrity(dentry); + return evm_status == INTEGRITY_PASS ? 0 : -EPERM; +} + +/** + * evm_inode_setxattr - protect the EVM extended attribute + * @dentry: pointer to the affected dentry + * @xattr_name: pointer to the affected extended attribute name + * @xattr_value: pointer to the new extended attribute value + * @xattr_value_len: pointer to the new extended attribute value length + * + * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that + * the current value is valid. + */ +int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name, + const void *xattr_value, size_t xattr_value_len) +{ + return evm_protect_xattr(dentry, xattr_name, xattr_value, + xattr_value_len); +} + +/** + * evm_inode_removexattr - protect the EVM extended attribute + * @dentry: pointer to the affected dentry + * @xattr_name: pointer to the affected extended attribute name + * + * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that + * the current value is valid. + */ +int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name) +{ + return evm_protect_xattr(dentry, xattr_name, NULL, 0); +} + +/** + * evm_inode_post_setxattr - update 'security.evm' to reflect the changes + * @dentry: pointer to the affected dentry + * @xattr_name: pointer to the affected extended attribute name + * @xattr_value: pointer to the new extended attribute value + * @xattr_value_len: pointer to the new extended attribute value length + * + * Update the HMAC stored in 'security.evm' to reflect the change. + * + * No need to take the i_mutex lock here, as this function is called from + * __vfs_setxattr_noperm(). The caller of which has taken the inode's + * i_mutex lock. + */ +void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, + const void *xattr_value, size_t xattr_value_len) +{ + if (!evm_initialized || (!evm_protected_xattr(xattr_name) + && !posix_xattr_acl(xattr_name))) + return; + + evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); + return; +} + +/** + * evm_inode_post_removexattr - update 'security.evm' after removing the xattr + * @dentry: pointer to the affected dentry + * @xattr_name: pointer to the affected extended attribute name + * + * Update the HMAC stored in 'security.evm' to reflect removal of the xattr. + */ +void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) +{ + struct inode *inode = dentry->d_inode; + + if (!evm_initialized || !evm_protected_xattr(xattr_name)) + return; + + mutex_lock(&inode->i_mutex); + evm_update_evmxattr(dentry, xattr_name, NULL, 0); + mutex_unlock(&inode->i_mutex); + return; +} + +/** + * evm_inode_setattr - prevent updating an invalid EVM extended attribute + * @dentry: pointer to the affected dentry + */ +int evm_inode_setattr(struct dentry *dentry, struct iattr *attr) +{ + unsigned int ia_valid = attr->ia_valid; + enum integrity_status evm_status; + + if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) + return 0; + evm_status = evm_verify_current_integrity(dentry); + if ((evm_status == INTEGRITY_PASS) || + (evm_status == INTEGRITY_NOXATTRS)) + return 0; + return -EPERM; +} + +/** + * evm_inode_post_setattr - update 'security.evm' after modifying metadata + * @dentry: pointer to the affected dentry + * @ia_valid: for the UID and GID status + * + * For now, update the HMAC stored in 'security.evm' to reflect UID/GID + * changes. + * + * This function is called from notify_change(), which expects the caller + * to lock the inode's i_mutex. + */ +void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) +{ + if (!evm_initialized) + return; + + if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) + evm_update_evmxattr(dentry, NULL, NULL, 0); + return; +} + +/* + * evm_inode_init_security - initializes security.evm + */ +int evm_inode_init_security(struct inode *inode, + const struct xattr *lsm_xattr, + struct xattr *evm_xattr) +{ + struct evm_ima_xattr_data *xattr_data; + int rc; + + if (!evm_initialized || !evm_protected_xattr(lsm_xattr->name)) + return 0; + + xattr_data = kzalloc(sizeof(*xattr_data), GFP_NOFS); + if (!xattr_data) + return -ENOMEM; + + xattr_data->type = EVM_XATTR_HMAC; + rc = evm_init_hmac(inode, lsm_xattr, xattr_data->digest); + if (rc < 0) + goto out; + + evm_xattr->value = xattr_data; + evm_xattr->value_len = sizeof(*xattr_data); + evm_xattr->name = kstrdup(XATTR_EVM_SUFFIX, GFP_NOFS); + return 0; +out: + kfree(xattr_data); + return rc; +} +EXPORT_SYMBOL_GPL(evm_inode_init_security); + +static int __init init_evm(void) +{ + int error; + + error = evm_init_secfs(); + if (error < 0) { + printk(KERN_INFO "EVM: Error registering secfs\n"); + goto err; + } +err: + return error; +} + +static void __exit cleanup_evm(void) +{ + evm_cleanup_secfs(); + if (hmac_tfm) + crypto_free_shash(hmac_tfm); +} + +/* + * evm_display_config - list the EVM protected security extended attributes + */ +static int __init evm_display_config(void) +{ + char **xattrname; + + for (xattrname = evm_config_xattrnames; *xattrname != NULL; xattrname++) + printk(KERN_INFO "EVM: %s\n", *xattrname); + return 0; +} + +pure_initcall(evm_display_config); +late_initcall(init_evm); + +MODULE_DESCRIPTION("Extended Verification Module"); +MODULE_LICENSE("GPL"); diff --git a/security/integrity/evm/evm_posix_acl.c b/security/integrity/evm/evm_posix_acl.c new file mode 100644 index 000000000000..b1753e98bf9a --- /dev/null +++ b/security/integrity/evm/evm_posix_acl.c @@ -0,0 +1,26 @@ +/* + * Copyright (C) 2011 IBM Corporation + * + * Author: + * Mimi Zohar <zohar@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + */ + +#include <linux/module.h> +#include <linux/xattr.h> + +int posix_xattr_acl(char *xattr) +{ + int xattr_len = strlen(xattr); + + if ((strlen(XATTR_NAME_POSIX_ACL_ACCESS) == xattr_len) + && (strncmp(XATTR_NAME_POSIX_ACL_ACCESS, xattr, xattr_len) == 0)) + return 1; + if ((strlen(XATTR_NAME_POSIX_ACL_DEFAULT) == xattr_len) + && (strncmp(XATTR_NAME_POSIX_ACL_DEFAULT, xattr, xattr_len) == 0)) + return 1; + return 0; +} diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c new file mode 100644 index 000000000000..ac7629950578 --- /dev/null +++ b/security/integrity/evm/evm_secfs.c @@ -0,0 +1,108 @@ +/* + * Copyright (C) 2010 IBM Corporation + * + * Authors: + * Mimi Zohar <zohar@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + * + * File: evm_secfs.c + * - Used to signal when key is on keyring + * - Get the key and enable EVM + */ + +#include <linux/uaccess.h> +#include <linux/module.h> +#include "evm.h" + +static struct dentry *evm_init_tpm; + +/** + * evm_read_key - read() for <securityfs>/evm + * + * @filp: file pointer, not actually used + * @buf: where to put the result + * @count: maximum to send along + * @ppos: where to start + * + * Returns number of bytes read or error code, as appropriate + */ +static ssize_t evm_read_key(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + char temp[80]; + ssize_t rc; + + if (*ppos != 0) + return 0; + + sprintf(temp, "%d", evm_initialized); + rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp)); + + return rc; +} + +/** + * evm_write_key - write() for <securityfs>/evm + * @file: file pointer, not actually used + * @buf: where to get the data from + * @count: bytes sent + * @ppos: where to start + * + * Used to signal that key is on the kernel key ring. + * - get the integrity hmac key from the kernel key ring + * - create list of hmac protected extended attributes + * Returns number of bytes written or error code, as appropriate + */ +static ssize_t evm_write_key(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + char temp[80]; + int i, error; + + if (!capable(CAP_SYS_ADMIN) || evm_initialized) + return -EPERM; + + if (count >= sizeof(temp) || count == 0) + return -EINVAL; + + if (copy_from_user(temp, buf, count) != 0) + return -EFAULT; + + temp[count] = '\0'; + + if ((sscanf(temp, "%d", &i) != 1) || (i != 1)) + return -EINVAL; + + error = evm_init_key(); + if (!error) { + evm_initialized = 1; + pr_info("EVM: initialized\n"); + } else + pr_err("EVM: initialization failed\n"); + return count; +} + +static const struct file_operations evm_key_ops = { + .read = evm_read_key, + .write = evm_write_key, +}; + +int __init evm_init_secfs(void) +{ + int error = 0; + + evm_init_tpm = securityfs_create_file("evm", S_IRUSR | S_IRGRP, + NULL, NULL, &evm_key_ops); + if (!evm_init_tpm || IS_ERR(evm_init_tpm)) + error = -EFAULT; + return error; +} + +void __exit evm_cleanup_secfs(void) +{ + if (evm_init_tpm) + securityfs_remove(evm_init_tpm); +} diff --git a/security/integrity/iint.c b/security/integrity/iint.c new file mode 100644 index 000000000000..399641c3e846 --- /dev/null +++ b/security/integrity/iint.c @@ -0,0 +1,172 @@ +/* + * Copyright (C) 2008 IBM Corporation + * + * Authors: + * Mimi Zohar <zohar@us.ibm.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + * + * File: integrity_iint.c + * - implements the integrity hooks: integrity_inode_alloc, + * integrity_inode_free + * - cache integrity information associated with an inode + * using a rbtree tree. + */ +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/rbtree.h> +#include "integrity.h" + +static struct rb_root integrity_iint_tree = RB_ROOT; +static DEFINE_SPINLOCK(integrity_iint_lock); +static struct kmem_cache *iint_cache __read_mostly; + +int iint_initialized; + +/* + * __integrity_iint_find - return the iint associated with an inode + */ +static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode) +{ + struct integrity_iint_cache *iint; + struct rb_node *n = integrity_iint_tree.rb_node; + + assert_spin_locked(&integrity_iint_lock); + + while (n) { + iint = rb_entry(n, struct integrity_iint_cache, rb_node); + + if (inode < iint->inode) + n = n->rb_left; + else if (inode > iint->inode) + n = n->rb_right; + else + break; + } + if (!n) + return NULL; + + return iint; +} + +/* + * integrity_iint_find - return the iint associated with an inode + */ +struct integrity_iint_cache *integrity_iint_find(struct inode *inode) +{ + struct integrity_iint_cache *iint; + + if (!IS_IMA(inode)) + return NULL; + + spin_lock(&integrity_iint_lock); + iint = __integrity_iint_find(inode); + spin_unlock(&integrity_iint_lock); + + return iint; +} + +static void iint_free(struct integrity_iint_cache *iint) +{ + iint->version = 0; + iint->flags = 0UL; + iint->evm_status = INTEGRITY_UNKNOWN; + kmem_cache_free(iint_cache, iint); +} + +/** + * integrity_inode_alloc - allocate an iint associated with an inode + * @inode: pointer to the inode + */ +int integrity_inode_alloc(struct inode *inode) +{ + struct rb_node **p; + struct rb_node *new_node, *parent = NULL; + struct integrity_iint_cache *new_iint, *test_iint; + int rc; + + new_iint = kmem_cache_alloc(iint_cache, GFP_NOFS); + if (!new_iint) + return -ENOMEM; + + new_iint->inode = inode; + new_node = &new_iint->rb_node; + + mutex_lock(&inode->i_mutex); /* i_flags */ + spin_lock(&integrity_iint_lock); + + p = &integrity_iint_tree.rb_node; + while (*p) { + parent = *p; + test_iint = rb_entry(parent, struct integrity_iint_cache, + rb_node); + rc = -EEXIST; + if (inode < test_iint->inode) + p = &(*p)->rb_left; + else if (inode > test_iint->inode) + p = &(*p)->rb_right; + else + goto out_err; + } + + inode->i_flags |= S_IMA; + rb_link_node(new_node, parent, p); + rb_insert_color(new_node, &integrity_iint_tree); + + spin_unlock(&integrity_iint_lock); + mutex_unlock(&inode->i_mutex); /* i_flags */ + + return 0; +out_err: + spin_unlock(&integrity_iint_lock); + mutex_unlock(&inode->i_mutex); /* i_flags */ + iint_free(new_iint); + + return rc; +} + +/** + * integrity_inode_free - called on security_inode_free + * @inode: pointer to the inode + * + * Free the integrity information(iint) associated with an inode. + */ +void integrity_inode_free(struct inode *inode) +{ + struct integrity_iint_cache *iint; + + if (!IS_IMA(inode)) + return; + + spin_lock(&integrity_iint_lock); + iint = __integrity_iint_find(inode); + rb_erase(&iint->rb_node, &integrity_iint_tree); + spin_unlock(&integrity_iint_lock); + + iint_free(iint); +} + +static void init_once(void *foo) +{ + struct integrity_iint_cache *iint = foo; + + memset(iint, 0, sizeof *iint); + iint->version = 0; + iint->flags = 0UL; + mutex_init(&iint->mutex); + iint->evm_status = INTEGRITY_UNKNOWN; +} + +static int __init integrity_iintcache_init(void) +{ + iint_cache = + kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache), + 0, SLAB_PANIC, init_once); + iint_initialized = 1; + return 0; +} +security_initcall(integrity_iintcache_init); diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index b6ecfd4d8d78..19c053b82303 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -3,6 +3,7 @@ config IMA bool "Integrity Measurement Architecture(IMA)" depends on SECURITY + select INTEGRITY select SECURITYFS select CRYPTO select CRYPTO_HMAC diff --git a/security/integrity/ima/Makefile b/security/integrity/ima/Makefile index 787c4cb916cd..5690c021de8f 100644 --- a/security/integrity/ima/Makefile +++ b/security/integrity/ima/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_IMA) += ima.o ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \ - ima_policy.o ima_iint.o ima_audit.o + ima_policy.o ima_audit.o diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 08408bd71462..3ccf7acac6df 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -24,18 +24,19 @@ #include <linux/tpm.h> #include <linux/audit.h> +#include "../integrity.h" + enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_ASCII }; enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 }; /* digest size for IMA, fits SHA1 or MD5 */ -#define IMA_DIGEST_SIZE 20 +#define IMA_DIGEST_SIZE SHA1_DIGEST_SIZE #define IMA_EVENT_NAME_LEN_MAX 255 #define IMA_HASH_BITS 9 #define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS) /* set during initialization */ -extern int iint_initialized; extern int ima_initialized; extern int ima_used_chip; extern char *ima_hash; @@ -96,34 +97,21 @@ static inline unsigned long ima_hash_key(u8 *digest) return hash_long(*digest, IMA_HASH_BITS); } -/* iint cache flags */ -#define IMA_MEASURED 0x01 - -/* integrity data associated with an inode */ -struct ima_iint_cache { - struct rb_node rb_node; /* rooted in ima_iint_tree */ - struct inode *inode; /* back pointer to inode in question */ - u64 version; /* track inode changes */ - unsigned char flags; - u8 digest[IMA_DIGEST_SIZE]; - struct mutex mutex; /* protects: version, flags, digest */ -}; - /* LIM API function definitions */ int ima_must_measure(struct inode *inode, int mask, int function); -int ima_collect_measurement(struct ima_iint_cache *iint, struct file *file); -void ima_store_measurement(struct ima_iint_cache *iint, struct file *file, +int ima_collect_measurement(struct integrity_iint_cache *iint, + struct file *file); +void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file, const unsigned char *filename); int ima_store_template(struct ima_template_entry *entry, int violation, struct inode *inode); -void ima_template_show(struct seq_file *m, void *e, - enum ima_show_type show); +void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show); /* rbtree tree calls to lookup, insert, delete * integrity data associated with an inode. */ -struct ima_iint_cache *ima_iint_insert(struct inode *inode); -struct ima_iint_cache *ima_iint_find(struct inode *inode); +struct integrity_iint_cache *integrity_iint_insert(struct inode *inode); +struct integrity_iint_cache *integrity_iint_find(struct inode *inode); /* IMA policy related functions */ enum ima_hooks { FILE_CHECK = 1, FILE_MMAP, BPRM_CHECK }; diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index da36d2c085a4..0d50df04ccc4 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -126,7 +126,8 @@ int ima_must_measure(struct inode *inode, int mask, int function) * * Return 0 on success, error code otherwise */ -int ima_collect_measurement(struct ima_iint_cache *iint, struct file *file) +int ima_collect_measurement(struct integrity_iint_cache *iint, + struct file *file) { int result = -EEXIST; @@ -156,8 +157,8 @@ int ima_collect_measurement(struct ima_iint_cache *iint, struct file *file) * * Must be called with iint->mutex held. */ -void ima_store_measurement(struct ima_iint_cache *iint, struct file *file, - const unsigned char *filename) +void ima_store_measurement(struct integrity_iint_cache *iint, + struct file *file, const unsigned char *filename) { const char *op = "add_template_measure"; const char *audit_cause = "ENOMEM"; diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index ef21b96a0b42..e1aa2b482dd2 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -287,7 +287,7 @@ static atomic_t policy_opencount = ATOMIC_INIT(1); /* * ima_open_policy: sequentialize access to the policy file */ -int ima_open_policy(struct inode * inode, struct file * filp) +static int ima_open_policy(struct inode * inode, struct file * filp) { /* No point in being allowed to open it if you aren't going to write */ if (!(filp->f_flags & O_WRONLY)) diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c deleted file mode 100644 index 4ae73040ab7b..000000000000 --- a/security/integrity/ima/ima_iint.c +++ /dev/null @@ -1,169 +0,0 @@ -/* - * Copyright (C) 2008 IBM Corporation - * - * Authors: - * Mimi Zohar <zohar@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation, version 2 of the - * License. - * - * File: ima_iint.c - * - implements the IMA hooks: ima_inode_alloc, ima_inode_free - * - cache integrity information associated with an inode - * using a rbtree tree. - */ -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/rbtree.h> -#include "ima.h" - -static struct rb_root ima_iint_tree = RB_ROOT; -static DEFINE_SPINLOCK(ima_iint_lock); -static struct kmem_cache *iint_cache __read_mostly; - -int iint_initialized = 0; - -/* - * __ima_iint_find - return the iint associated with an inode - */ -static struct ima_iint_cache *__ima_iint_find(struct inode *inode) -{ - struct ima_iint_cache *iint; - struct rb_node *n = ima_iint_tree.rb_node; - - assert_spin_locked(&ima_iint_lock); - - while (n) { - iint = rb_entry(n, struct ima_iint_cache, rb_node); - - if (inode < iint->inode) - n = n->rb_left; - else if (inode > iint->inode) - n = n->rb_right; - else - break; - } - if (!n) - return NULL; - - return iint; -} - -/* - * ima_iint_find - return the iint associated with an inode - */ -struct ima_iint_cache *ima_iint_find(struct inode *inode) -{ - struct ima_iint_cache *iint; - - if (!IS_IMA(inode)) - return NULL; - - spin_lock(&ima_iint_lock); - iint = __ima_iint_find(inode); - spin_unlock(&ima_iint_lock); - - return iint; -} - -static void iint_free(struct ima_iint_cache *iint) -{ - iint->version = 0; - iint->flags = 0UL; - kmem_cache_free(iint_cache, iint); -} - -/** - * ima_inode_alloc - allocate an iint associated with an inode - * @inode: pointer to the inode - */ -int ima_inode_alloc(struct inode *inode) -{ - struct rb_node **p; - struct rb_node *new_node, *parent = NULL; - struct ima_iint_cache *new_iint, *test_iint; - int rc; - - new_iint = kmem_cache_alloc(iint_cache, GFP_NOFS); - if (!new_iint) - return -ENOMEM; - - new_iint->inode = inode; - new_node = &new_iint->rb_node; - - mutex_lock(&inode->i_mutex); /* i_flags */ - spin_lock(&ima_iint_lock); - - p = &ima_iint_tree.rb_node; - while (*p) { - parent = *p; - test_iint = rb_entry(parent, struct ima_iint_cache, rb_node); - - rc = -EEXIST; - if (inode < test_iint->inode) - p = &(*p)->rb_left; - else if (inode > test_iint->inode) - p = &(*p)->rb_right; - else - goto out_err; - } - - inode->i_flags |= S_IMA; - rb_link_node(new_node, parent, p); - rb_insert_color(new_node, &ima_iint_tree); - - spin_unlock(&ima_iint_lock); - mutex_unlock(&inode->i_mutex); /* i_flags */ - - return 0; -out_err: - spin_unlock(&ima_iint_lock); - mutex_unlock(&inode->i_mutex); /* i_flags */ - iint_free(new_iint); - - return rc; -} - -/** - * ima_inode_free - called on security_inode_free - * @inode: pointer to the inode - * - * Free the integrity information(iint) associated with an inode. - */ -void ima_inode_free(struct inode *inode) -{ - struct ima_iint_cache *iint; - - if (!IS_IMA(inode)) - return; - - spin_lock(&ima_iint_lock); - iint = __ima_iint_find(inode); - rb_erase(&iint->rb_node, &ima_iint_tree); - spin_unlock(&ima_iint_lock); - - iint_free(iint); -} - -static void init_once(void *foo) -{ - struct ima_iint_cache *iint = foo; - - memset(iint, 0, sizeof *iint); - iint->version = 0; - iint->flags = 0UL; - mutex_init(&iint->mutex); -} - -static int __init ima_iintcache_init(void) -{ - iint_cache = - kmem_cache_create("iint_cache", sizeof(struct ima_iint_cache), 0, - SLAB_PANIC, init_once); - iint_initialized = 1; - return 0; -} -security_initcall(ima_iintcache_init); diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 26b46ff74663..1eff5cb001e5 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -22,6 +22,7 @@ #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> +#include <linux/ima.h> #include "ima.h" @@ -82,7 +83,7 @@ out: "open_writers"); } -static void ima_check_last_writer(struct ima_iint_cache *iint, +static void ima_check_last_writer(struct integrity_iint_cache *iint, struct inode *inode, struct file *file) { @@ -105,12 +106,12 @@ static void ima_check_last_writer(struct ima_iint_cache *iint, void ima_file_free(struct file *file) { struct inode *inode = file->f_dentry->d_inode; - struct ima_iint_cache *iint; + struct integrity_iint_cache *iint; if (!iint_initialized || !S_ISREG(inode->i_mode)) return; - iint = ima_iint_find(inode); + iint = integrity_iint_find(inode); if (!iint) return; @@ -121,7 +122,7 @@ static int process_measurement(struct file *file, const unsigned char *filename, int mask, int function) { struct inode *inode = file->f_dentry->d_inode; - struct ima_iint_cache *iint; + struct integrity_iint_cache *iint; int rc = 0; if (!ima_initialized || !S_ISREG(inode->i_mode)) @@ -131,9 +132,9 @@ static int process_measurement(struct file *file, const unsigned char *filename, if (rc != 0) return rc; retry: - iint = ima_iint_find(inode); + iint = integrity_iint_find(inode); if (!iint) { - rc = ima_inode_alloc(inode); + rc = integrity_inode_alloc(inode); if (!rc || rc == -EEXIST) goto retry; return rc; diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h new file mode 100644 index 000000000000..3143a3c39868 --- /dev/null +++ b/security/integrity/integrity.h @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2009-2010 IBM Corporation + * + * Authors: + * Mimi Zohar <zohar@us.ibm.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + * + */ + +#include <linux/types.h> +#include <linux/integrity.h> +#include <crypto/sha.h> + +/* iint cache flags */ +#define IMA_MEASURED 0x01 + +enum evm_ima_xattr_type { + IMA_XATTR_DIGEST = 0x01, + EVM_XATTR_HMAC, + EVM_IMA_XATTR_DIGSIG, +}; + +struct evm_ima_xattr_data { + u8 type; + u8 digest[SHA1_DIGEST_SIZE]; +} __attribute__((packed)); + +/* integrity data associated with an inode */ +struct integrity_iint_cache { + struct rb_node rb_node; /* rooted in integrity_iint_tree */ + struct inode *inode; /* back pointer to inode in question */ + u64 version; /* track inode changes */ + unsigned char flags; + u8 digest[SHA1_DIGEST_SIZE]; + struct mutex mutex; /* protects: version, flags, digest */ + enum integrity_status evm_status; +}; + +/* rbtree tree calls to lookup, insert, delete + * integrity data associated with an inode. + */ +struct integrity_iint_cache *integrity_iint_insert(struct inode *inode); +struct integrity_iint_cache *integrity_iint_find(struct inode *inode); + +/* set during initialization */ +extern int iint_initialized; diff --git a/security/keys/Makefile b/security/keys/Makefile index b34cc6ee6900..a56f1ffdc64d 100644 --- a/security/keys/Makefile +++ b/security/keys/Makefile @@ -14,7 +14,7 @@ obj-y := \ user_defined.o obj-$(CONFIG_TRUSTED_KEYS) += trusted.o -obj-$(CONFIG_ENCRYPTED_KEYS) += ecryptfs_format.o encrypted.o +obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/ obj-$(CONFIG_KEYS_COMPAT) += compat.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSCTL) += sysctl.o diff --git a/security/keys/encrypted-keys/Makefile b/security/keys/encrypted-keys/Makefile new file mode 100644 index 000000000000..6bc7a86d1027 --- /dev/null +++ b/security/keys/encrypted-keys/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for encrypted keys +# + +obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted.o ecryptfs_format.o +obj-$(CONFIG_TRUSTED_KEYS) += masterkey_trusted.o diff --git a/security/keys/ecryptfs_format.c b/security/keys/encrypted-keys/ecryptfs_format.c index 6daa3b6ff9ed..6daa3b6ff9ed 100644 --- a/security/keys/ecryptfs_format.c +++ b/security/keys/encrypted-keys/ecryptfs_format.c diff --git a/security/keys/ecryptfs_format.h b/security/keys/encrypted-keys/ecryptfs_format.h index 40294de238bb..40294de238bb 100644 --- a/security/keys/ecryptfs_format.h +++ b/security/keys/encrypted-keys/ecryptfs_format.h diff --git a/security/keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index e7eca9ec4c65..f33804c1b4c8 100644 --- a/security/keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -299,31 +299,6 @@ out: } /* - * request_trusted_key - request the trusted key - * - * Trusted keys are sealed to PCRs and other metadata. Although userspace - * manages both trusted/encrypted key-types, like the encrypted key type - * data, trusted key type data is not visible decrypted from userspace. - */ -static struct key *request_trusted_key(const char *trusted_desc, - u8 **master_key, size_t *master_keylen) -{ - struct trusted_key_payload *tpayload; - struct key *tkey; - - tkey = request_key(&key_type_trusted, trusted_desc, NULL); - if (IS_ERR(tkey)) - goto error; - - down_read(&tkey->sem); - tpayload = rcu_dereference(tkey->payload.data); - *master_key = tpayload->key; - *master_keylen = tpayload->key_len; -error: - return tkey; -} - -/* * request_user_key - request the user key * * Use a user provided key to encrypt/decrypt an encrypted-key. @@ -469,8 +444,14 @@ static struct key *request_master_key(struct encrypted_key_payload *epayload, goto out; if (IS_ERR(mkey)) { - pr_info("encrypted_key: key %s not found", - epayload->master_desc); + int ret = PTR_ERR(epayload); + + if (ret == -ENOTSUPP) + pr_info("encrypted_key: key %s not supported", + epayload->master_desc); + else + pr_info("encrypted_key: key %s not found", + epayload->master_desc); goto out; } @@ -686,11 +667,19 @@ static int encrypted_key_decrypt(struct encrypted_key_payload *epayload, return -EINVAL; hex_encoded_data = hex_encoded_iv + (2 * ivsize) + 2; - hex2bin(epayload->iv, hex_encoded_iv, ivsize); - hex2bin(epayload->encrypted_data, hex_encoded_data, encrypted_datalen); + ret = hex2bin(epayload->iv, hex_encoded_iv, ivsize); + if (ret < 0) + return -EINVAL; + ret = hex2bin(epayload->encrypted_data, hex_encoded_data, + encrypted_datalen); + if (ret < 0) + return -EINVAL; hmac = epayload->format + epayload->datablob_len; - hex2bin(hmac, hex_encoded_data + (encrypted_datalen * 2), HASH_SIZE); + ret = hex2bin(hmac, hex_encoded_data + (encrypted_datalen * 2), + HASH_SIZE); + if (ret < 0) + return -EINVAL; mkey = request_master_key(epayload, &master_key, &master_keylen); if (IS_ERR(mkey)) diff --git a/security/keys/encrypted.h b/security/keys/encrypted-keys/encrypted.h index cef5e2f2b7d1..b6ade8945250 100644 --- a/security/keys/encrypted.h +++ b/security/keys/encrypted-keys/encrypted.h @@ -2,6 +2,17 @@ #define __ENCRYPTED_KEY_H #define ENCRYPTED_DEBUG 0 +#ifdef CONFIG_TRUSTED_KEYS +extern struct key *request_trusted_key(const char *trusted_desc, + u8 **master_key, size_t *master_keylen); +#else +static inline struct key *request_trusted_key(const char *trusted_desc, + u8 **master_key, + size_t *master_keylen) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif #if ENCRYPTED_DEBUG static inline void dump_master_key(const u8 *master_key, size_t master_keylen) diff --git a/security/keys/encrypted-keys/masterkey_trusted.c b/security/keys/encrypted-keys/masterkey_trusted.c new file mode 100644 index 000000000000..df87272e3f51 --- /dev/null +++ b/security/keys/encrypted-keys/masterkey_trusted.c @@ -0,0 +1,45 @@ +/* + * Copyright (C) 2010 IBM Corporation + * Copyright (C) 2010 Politecnico di Torino, Italy + * TORSEC group -- http://security.polito.it + * + * Authors: + * Mimi Zohar <zohar@us.ibm.com> + * Roberto Sassu <roberto.sassu@polito.it> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + * + * See Documentation/security/keys-trusted-encrypted.txt + */ + +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/err.h> +#include <keys/trusted-type.h> + +/* + * request_trusted_key - request the trusted key + * + * Trusted keys are sealed to PCRs and other metadata. Although userspace + * manages both trusted/encrypted key-types, like the encrypted key type + * data, trusted key type data is not visible decrypted from userspace. + */ +struct key *request_trusted_key(const char *trusted_desc, + u8 **master_key, size_t *master_keylen) +{ + struct trusted_key_payload *tpayload; + struct key *tkey; + + tkey = request_key(&key_type_trusted, trusted_desc, NULL); + if (IS_ERR(tkey)) + goto error; + + down_read(&tkey->sem); + tpayload = rcu_dereference(tkey->payload.data); + *master_key = tpayload->key; + *master_keylen = tpayload->key_len; +error: + return tkey; +} diff --git a/security/keys/gc.c b/security/keys/gc.c index 89df6b5f203c..bf4d8da5a795 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -1,6 +1,6 @@ /* Key garbage collector * - * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2009-2011 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or @@ -10,6 +10,8 @@ */ #include <linux/module.h> +#include <linux/slab.h> +#include <linux/security.h> #include <keys/keyring-type.h> #include "internal.h" @@ -19,17 +21,33 @@ unsigned key_gc_delay = 5 * 60; /* - * Reaper + * Reaper for unused keys. + */ +static void key_garbage_collector(struct work_struct *work); +DECLARE_WORK(key_gc_work, key_garbage_collector); + +/* + * Reaper for links from keyrings to dead keys. */ static void key_gc_timer_func(unsigned long); -static void key_garbage_collector(struct work_struct *); static DEFINE_TIMER(key_gc_timer, key_gc_timer_func, 0, 0); -static DECLARE_WORK(key_gc_work, key_garbage_collector); -static key_serial_t key_gc_cursor; /* the last key the gc considered */ -static bool key_gc_again; -static unsigned long key_gc_executing; + static time_t key_gc_next_run = LONG_MAX; -static time_t key_gc_new_timer; +static struct key_type *key_gc_dead_keytype; + +static unsigned long key_gc_flags; +#define KEY_GC_KEY_EXPIRED 0 /* A key expired and needs unlinking */ +#define KEY_GC_REAP_KEYTYPE 1 /* A keytype is being unregistered */ +#define KEY_GC_REAPING_KEYTYPE 2 /* Cleared when keytype reaped */ + + +/* + * Any key whose type gets unregistered will be re-typed to this if it can't be + * immediately unlinked. + */ +struct key_type key_type_dead = { + .name = "dead", +}; /* * Schedule a garbage collection run. @@ -42,31 +60,75 @@ void key_schedule_gc(time_t gc_at) kenter("%ld", gc_at - now); - if (gc_at <= now) { - schedule_work(&key_gc_work); + if (gc_at <= now || test_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) { + kdebug("IMMEDIATE"); + queue_work(system_nrt_wq, &key_gc_work); } else if (gc_at < key_gc_next_run) { + kdebug("DEFERRED"); + key_gc_next_run = gc_at; expires = jiffies + (gc_at - now) * HZ; mod_timer(&key_gc_timer, expires); } } /* - * The garbage collector timer kicked off + * Some key's cleanup time was met after it expired, so we need to get the + * reaper to go through a cycle finding expired keys. */ static void key_gc_timer_func(unsigned long data) { kenter(""); key_gc_next_run = LONG_MAX; - schedule_work(&key_gc_work); + set_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags); + queue_work(system_nrt_wq, &key_gc_work); +} + +/* + * wait_on_bit() sleep function for uninterruptible waiting + */ +static int key_gc_wait_bit(void *flags) +{ + schedule(); + return 0; +} + +/* + * Reap keys of dead type. + * + * We use three flags to make sure we see three complete cycles of the garbage + * collector: the first to mark keys of that type as being dead, the second to + * collect dead links and the third to clean up the dead keys. We have to be + * careful as there may already be a cycle in progress. + * + * The caller must be holding key_types_sem. + */ +void key_gc_keytype(struct key_type *ktype) +{ + kenter("%s", ktype->name); + + key_gc_dead_keytype = ktype; + set_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags); + smp_mb(); + set_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags); + + kdebug("schedule"); + queue_work(system_nrt_wq, &key_gc_work); + + kdebug("sleep"); + wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE, key_gc_wait_bit, + TASK_UNINTERRUPTIBLE); + + key_gc_dead_keytype = NULL; + kleave(""); } /* * Garbage collect pointers from a keyring. * - * Return true if we altered the keyring. + * Not called with any locks held. The keyring's key struct will not be + * deallocated under us as only our caller may deallocate it. */ -static bool key_gc_keyring(struct key *keyring, time_t limit) - __releases(key_serial_lock) +static void key_gc_keyring(struct key *keyring, time_t limit) { struct keyring_list *klist; struct key *key; @@ -93,130 +155,234 @@ static bool key_gc_keyring(struct key *keyring, time_t limit) unlock_dont_gc: rcu_read_unlock(); dont_gc: - kleave(" = false"); - return false; + kleave(" [no gc]"); + return; do_gc: rcu_read_unlock(); - key_gc_cursor = keyring->serial; - key_get(keyring); - spin_unlock(&key_serial_lock); + keyring_gc(keyring, limit); - key_put(keyring); - kleave(" = true"); - return true; + kleave(" [gc]"); } /* - * Garbage collector for keys. This involves scanning the keyrings for dead, - * expired and revoked keys that have overstayed their welcome + * Garbage collect an unreferenced, detached key */ -static void key_garbage_collector(struct work_struct *work) +static noinline void key_gc_unused_key(struct key *key) { - struct rb_node *rb; - key_serial_t cursor; - struct key *key, *xkey; - time_t new_timer = LONG_MAX, limit, now; - - now = current_kernel_time().tv_sec; - kenter("[%x,%ld]", key_gc_cursor, key_gc_new_timer - now); - - if (test_and_set_bit(0, &key_gc_executing)) { - key_schedule_gc(current_kernel_time().tv_sec + 1); - kleave(" [busy; deferring]"); - return; + key_check(key); + + security_key_free(key); + + /* deal with the user's key tracking and quota */ + if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { + spin_lock(&key->user->lock); + key->user->qnkeys--; + key->user->qnbytes -= key->quotalen; + spin_unlock(&key->user->lock); } - limit = now; + atomic_dec(&key->user->nkeys); + if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) + atomic_dec(&key->user->nikeys); + + key_user_put(key->user); + + /* now throw away the key memory */ + if (key->type->destroy) + key->type->destroy(key); + + kfree(key->description); + +#ifdef KEY_DEBUGGING + key->magic = KEY_DEBUG_MAGIC_X; +#endif + kmem_cache_free(key_jar, key); +} + +/* + * Garbage collector for unused keys. + * + * This is done in process context so that we don't have to disable interrupts + * all over the place. key_put() schedules this rather than trying to do the + * cleanup itself, which means key_put() doesn't have to sleep. + */ +static void key_garbage_collector(struct work_struct *work) +{ + static u8 gc_state; /* Internal persistent state */ +#define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */ +#define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */ +#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */ +#define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */ +#define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */ +#define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */ +#define KEY_GC_FOUND_DEAD_KEY 0x80 /* - We found at least one dead key */ + + struct rb_node *cursor; + struct key *key; + time_t new_timer, limit; + + kenter("[%lx,%x]", key_gc_flags, gc_state); + + limit = current_kernel_time().tv_sec; if (limit > key_gc_delay) limit -= key_gc_delay; else limit = key_gc_delay; + /* Work out what we're going to be doing in this pass */ + gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2; + gc_state <<= 1; + if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags)) + gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER; + + if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) + gc_state |= KEY_GC_REAPING_DEAD_1; + kdebug("new pass %x", gc_state); + + new_timer = LONG_MAX; + + /* As only this function is permitted to remove things from the key + * serial tree, if cursor is non-NULL then it will always point to a + * valid node in the tree - even if lock got dropped. + */ spin_lock(&key_serial_lock); + cursor = rb_first(&key_serial_tree); - if (unlikely(RB_EMPTY_ROOT(&key_serial_tree))) { - spin_unlock(&key_serial_lock); - clear_bit(0, &key_gc_executing); - return; - } +continue_scanning: + while (cursor) { + key = rb_entry(cursor, struct key, serial_node); + cursor = rb_next(cursor); - cursor = key_gc_cursor; - if (cursor < 0) - cursor = 0; - if (cursor > 0) - new_timer = key_gc_new_timer; - else - key_gc_again = false; - - /* find the first key above the cursor */ - key = NULL; - rb = key_serial_tree.rb_node; - while (rb) { - xkey = rb_entry(rb, struct key, serial_node); - if (cursor < xkey->serial) { - key = xkey; - rb = rb->rb_left; - } else if (cursor > xkey->serial) { - rb = rb->rb_right; - } else { - rb = rb_next(rb); - if (!rb) - goto reached_the_end; - key = rb_entry(rb, struct key, serial_node); - break; + if (atomic_read(&key->usage) == 0) + goto found_unreferenced_key; + + if (unlikely(gc_state & KEY_GC_REAPING_DEAD_1)) { + if (key->type == key_gc_dead_keytype) { + gc_state |= KEY_GC_FOUND_DEAD_KEY; + set_bit(KEY_FLAG_DEAD, &key->flags); + key->perm = 0; + goto skip_dead_key; + } + } + + if (gc_state & KEY_GC_SET_TIMER) { + if (key->expiry > limit && key->expiry < new_timer) { + kdebug("will expire %x in %ld", + key_serial(key), key->expiry - limit); + new_timer = key->expiry; + } } - } - if (!key) - goto reached_the_end; + if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) + if (key->type == key_gc_dead_keytype) + gc_state |= KEY_GC_FOUND_DEAD_KEY; - /* trawl through the keys looking for keyrings */ - for (;;) { - if (key->expiry > limit && key->expiry < new_timer) { - kdebug("will expire %x in %ld", - key_serial(key), key->expiry - limit); - new_timer = key->expiry; + if ((gc_state & KEY_GC_REAPING_LINKS) || + unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) { + if (key->type == &key_type_keyring) + goto found_keyring; } - if (key->type == &key_type_keyring && - key_gc_keyring(key, limit)) - /* the gc had to release our lock so that the keyring - * could be modified, so we have to get it again */ - goto gc_released_our_lock; + if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) + if (key->type == key_gc_dead_keytype) + goto destroy_dead_key; - rb = rb_next(&key->serial_node); - if (!rb) - goto reached_the_end; - key = rb_entry(rb, struct key, serial_node); + skip_dead_key: + if (spin_is_contended(&key_serial_lock) || need_resched()) + goto contended; } -gc_released_our_lock: - kdebug("gc_released_our_lock"); - key_gc_new_timer = new_timer; - key_gc_again = true; - clear_bit(0, &key_gc_executing); - schedule_work(&key_gc_work); - kleave(" [continue]"); - return; - - /* when we reach the end of the run, we set the timer for the next one */ -reached_the_end: - kdebug("reached_the_end"); +contended: spin_unlock(&key_serial_lock); - key_gc_new_timer = new_timer; - key_gc_cursor = 0; - clear_bit(0, &key_gc_executing); - - if (key_gc_again) { - /* there may have been a key that expired whilst we were - * scanning, so if we discarded any links we should do another - * scan */ - new_timer = now + 1; - key_schedule_gc(new_timer); - } else if (new_timer < LONG_MAX) { + +maybe_resched: + if (cursor) { + cond_resched(); + spin_lock(&key_serial_lock); + goto continue_scanning; + } + + /* We've completed the pass. Set the timer if we need to and queue a + * new cycle if necessary. We keep executing cycles until we find one + * where we didn't reap any keys. + */ + kdebug("pass complete"); + + if (gc_state & KEY_GC_SET_TIMER && new_timer != (time_t)LONG_MAX) { new_timer += key_gc_delay; key_schedule_gc(new_timer); } - kleave(" [end]"); + + if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) { + /* Make sure everyone revalidates their keys if we marked a + * bunch as being dead and make sure all keyring ex-payloads + * are destroyed. + */ + kdebug("dead sync"); + synchronize_rcu(); + } + + if (unlikely(gc_state & (KEY_GC_REAPING_DEAD_1 | + KEY_GC_REAPING_DEAD_2))) { + if (!(gc_state & KEY_GC_FOUND_DEAD_KEY)) { + /* No remaining dead keys: short circuit the remaining + * keytype reap cycles. + */ + kdebug("dead short"); + gc_state &= ~(KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2); + gc_state |= KEY_GC_REAPING_DEAD_3; + } else { + gc_state |= KEY_GC_REAP_AGAIN; + } + } + + if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) { + kdebug("dead wake"); + smp_mb(); + clear_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags); + wake_up_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE); + } + + if (gc_state & KEY_GC_REAP_AGAIN) + queue_work(system_nrt_wq, &key_gc_work); + kleave(" [end %x]", gc_state); + return; + + /* We found an unreferenced key - once we've removed it from the tree, + * we can safely drop the lock. + */ +found_unreferenced_key: + kdebug("unrefd key %d", key->serial); + rb_erase(&key->serial_node, &key_serial_tree); + spin_unlock(&key_serial_lock); + + key_gc_unused_key(key); + gc_state |= KEY_GC_REAP_AGAIN; + goto maybe_resched; + + /* We found a keyring and we need to check the payload for links to + * dead or expired keys. We don't flag another reap immediately as we + * have to wait for the old payload to be destroyed by RCU before we + * can reap the keys to which it refers. + */ +found_keyring: + spin_unlock(&key_serial_lock); + kdebug("scan keyring %d", key->serial); + key_gc_keyring(key, limit); + goto maybe_resched; + + /* We found a dead key that is still referenced. Reset its type and + * destroy its payload with its semaphore held. + */ +destroy_dead_key: + spin_unlock(&key_serial_lock); + kdebug("destroy key %d", key->serial); + down_write(&key->sem); + key->type = &key_type_dead; + if (key_gc_dead_keytype->destroy) + key_gc_dead_keytype->destroy(key); + memset(&key->payload, KEY_DESTROY, sizeof(key->payload)); + up_write(&key->sem); + goto maybe_resched; } diff --git a/security/keys/internal.h b/security/keys/internal.h index f375152a2500..c7a7caec4830 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -31,6 +31,7 @@ no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__) #endif +extern struct key_type key_type_dead; extern struct key_type key_type_user; /*****************************************************************************/ @@ -75,6 +76,7 @@ extern unsigned key_quota_maxbytes; #define KEYQUOTA_LINK_BYTES 4 /* a link in a keyring is worth 4 bytes */ +extern struct kmem_cache *key_jar; extern struct rb_root key_serial_tree; extern spinlock_t key_serial_lock; extern struct mutex key_construction_mutex; @@ -146,9 +148,11 @@ extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, extern long join_session_keyring(const char *name); +extern struct work_struct key_gc_work; extern unsigned key_gc_delay; extern void keyring_gc(struct key *keyring, time_t limit); extern void key_schedule_gc(time_t expiry_at); +extern void key_gc_keytype(struct key_type *ktype); extern int key_task_permission(const key_ref_t key_ref, const struct cred *cred, diff --git a/security/keys/key.c b/security/keys/key.c index f7f9d93f08d9..4414abddcb5b 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -21,7 +21,7 @@ #include <linux/user_namespace.h> #include "internal.h" -static struct kmem_cache *key_jar; +struct kmem_cache *key_jar; struct rb_root key_serial_tree; /* tree of keys indexed by serial */ DEFINE_SPINLOCK(key_serial_lock); @@ -36,17 +36,9 @@ unsigned int key_quota_maxbytes = 20000; /* general key space quota */ static LIST_HEAD(key_types_list); static DECLARE_RWSEM(key_types_sem); -static void key_cleanup(struct work_struct *work); -static DECLARE_WORK(key_cleanup_task, key_cleanup); - /* We serialise key instantiation and link */ DEFINE_MUTEX(key_construction_mutex); -/* Any key who's type gets unegistered will be re-typed to this */ -static struct key_type key_type_dead = { - .name = "dead", -}; - #ifdef KEY_DEBUGGING void __key_check(const struct key *key) { @@ -591,71 +583,6 @@ int key_reject_and_link(struct key *key, } EXPORT_SYMBOL(key_reject_and_link); -/* - * Garbage collect keys in process context so that we don't have to disable - * interrupts all over the place. - * - * key_put() schedules this rather than trying to do the cleanup itself, which - * means key_put() doesn't have to sleep. - */ -static void key_cleanup(struct work_struct *work) -{ - struct rb_node *_n; - struct key *key; - -go_again: - /* look for a dead key in the tree */ - spin_lock(&key_serial_lock); - - for (_n = rb_first(&key_serial_tree); _n; _n = rb_next(_n)) { - key = rb_entry(_n, struct key, serial_node); - - if (atomic_read(&key->usage) == 0) - goto found_dead_key; - } - - spin_unlock(&key_serial_lock); - return; - -found_dead_key: - /* we found a dead key - once we've removed it from the tree, we can - * drop the lock */ - rb_erase(&key->serial_node, &key_serial_tree); - spin_unlock(&key_serial_lock); - - key_check(key); - - security_key_free(key); - - /* deal with the user's key tracking and quota */ - if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { - spin_lock(&key->user->lock); - key->user->qnkeys--; - key->user->qnbytes -= key->quotalen; - spin_unlock(&key->user->lock); - } - - atomic_dec(&key->user->nkeys); - if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) - atomic_dec(&key->user->nikeys); - - key_user_put(key->user); - - /* now throw away the key memory */ - if (key->type->destroy) - key->type->destroy(key); - - kfree(key->description); - -#ifdef KEY_DEBUGGING - key->magic = KEY_DEBUG_MAGIC_X; -#endif - kmem_cache_free(key_jar, key); - - /* there may, of course, be more than one key to destroy */ - goto go_again; -} - /** * key_put - Discard a reference to a key. * @key: The key to discard a reference from. @@ -670,7 +597,7 @@ void key_put(struct key *key) key_check(key); if (atomic_dec_and_test(&key->usage)) - schedule_work(&key_cleanup_task); + queue_work(system_nrt_wq, &key_gc_work); } } EXPORT_SYMBOL(key_put); @@ -1048,49 +975,11 @@ EXPORT_SYMBOL(register_key_type); */ void unregister_key_type(struct key_type *ktype) { - struct rb_node *_n; - struct key *key; - down_write(&key_types_sem); - - /* withdraw the key type */ list_del_init(&ktype->link); - - /* mark all the keys of this type dead */ - spin_lock(&key_serial_lock); - - for (_n = rb_first(&key_serial_tree); _n; _n = rb_next(_n)) { - key = rb_entry(_n, struct key, serial_node); - - if (key->type == ktype) { - key->type = &key_type_dead; - set_bit(KEY_FLAG_DEAD, &key->flags); - } - } - - spin_unlock(&key_serial_lock); - - /* make sure everyone revalidates their keys */ - synchronize_rcu(); - - /* we should now be able to destroy the payloads of all the keys of - * this type with impunity */ - spin_lock(&key_serial_lock); - - for (_n = rb_first(&key_serial_tree); _n; _n = rb_next(_n)) { - key = rb_entry(_n, struct key, serial_node); - - if (key->type == ktype) { - if (ktype->destroy) - ktype->destroy(key); - memset(&key->payload, KEY_DESTROY, sizeof(key->payload)); - } - } - - spin_unlock(&key_serial_lock); - up_write(&key_types_sem); - - key_schedule_gc(0); + downgrade_write(&key_types_sem); + key_gc_keytype(ktype); + up_read(&key_types_sem); } EXPORT_SYMBOL(unregister_key_type); diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 30e242f7bd0e..37a7f3b28852 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -860,8 +860,7 @@ void __key_link(struct key *keyring, struct key *key, kenter("%d,%d,%p", keyring->serial, key->serial, nklist); - klist = rcu_dereference_protected(keyring->payload.subscriptions, - rwsem_is_locked(&keyring->sem)); + klist = rcu_dereference_locked_keyring(keyring); atomic_inc(&key->usage); diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index a3063eb3dc23..1068cb1939b3 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -270,7 +270,7 @@ static int install_session_keyring(struct key *keyring) if (!new) return -ENOMEM; - ret = install_session_keyring_to_cred(new, NULL); + ret = install_session_keyring_to_cred(new, keyring); if (ret < 0) { abort_creds(new); return ret; @@ -589,12 +589,22 @@ try_again: ret = install_user_keyrings(); if (ret < 0) goto error; - ret = install_session_keyring( - cred->user->session_keyring); + if (lflags & KEY_LOOKUP_CREATE) + ret = join_session_keyring(NULL); + else + ret = install_session_keyring( + cred->user->session_keyring); if (ret < 0) goto error; goto reget_creds; + } else if (cred->tgcred->session_keyring == + cred->user->session_keyring && + lflags & KEY_LOOKUP_CREATE) { + ret = join_session_keyring(NULL); + if (ret < 0) + goto error; + goto reget_creds; } rcu_read_lock(); diff --git a/security/keys/trusted.c b/security/keys/trusted.c index 0c33e2ea1f3c..0964fc236946 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -779,7 +779,10 @@ static int getoptions(char *c, struct trusted_key_payload *pay, opt->pcrinfo_len = strlen(args[0].from) / 2; if (opt->pcrinfo_len > MAX_PCRINFO_SIZE) return -EINVAL; - hex2bin(opt->pcrinfo, args[0].from, opt->pcrinfo_len); + res = hex2bin(opt->pcrinfo, args[0].from, + opt->pcrinfo_len); + if (res < 0) + return -EINVAL; break; case Opt_keyhandle: res = strict_strtoul(args[0].from, 16, &handle); @@ -791,12 +794,18 @@ static int getoptions(char *c, struct trusted_key_payload *pay, case Opt_keyauth: if (strlen(args[0].from) != 2 * SHA1_DIGEST_SIZE) return -EINVAL; - hex2bin(opt->keyauth, args[0].from, SHA1_DIGEST_SIZE); + res = hex2bin(opt->keyauth, args[0].from, + SHA1_DIGEST_SIZE); + if (res < 0) + return -EINVAL; break; case Opt_blobauth: if (strlen(args[0].from) != 2 * SHA1_DIGEST_SIZE) return -EINVAL; - hex2bin(opt->blobauth, args[0].from, SHA1_DIGEST_SIZE); + res = hex2bin(opt->blobauth, args[0].from, + SHA1_DIGEST_SIZE); + if (res < 0) + return -EINVAL; break; case Opt_migratable: if (*args[0].from == '0') @@ -860,7 +869,9 @@ static int datablob_parse(char *datablob, struct trusted_key_payload *p, p->blob_len = strlen(c) / 2; if (p->blob_len > MAX_BLOB_SIZE) return -EINVAL; - hex2bin(p->blob, c, p->blob_len); + ret = hex2bin(p->blob, c, p->blob_len); + if (ret < 0) + return -EINVAL; ret = getoptions(datablob, p, o); if (ret < 0) return ret; diff --git a/security/security.c b/security/security.c index 0e4fccfef12c..0c6cc69c8f86 100644 --- a/security/security.c +++ b/security/security.c @@ -16,15 +16,16 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/security.h> +#include <linux/integrity.h> #include <linux/ima.h> +#include <linux/evm.h> + +#define MAX_LSM_EVM_XATTR 2 /* Boot-time LSM user choice */ static __initdata char chosen_lsm[SECURITY_NAME_MAX + 1] = CONFIG_DEFAULT_SECURITY; -/* things that live in capability.c */ -extern void __init security_fixup_ops(struct security_operations *ops); - static struct security_operations *security_ops; static struct security_operations default_security_ops = { .name = "default", @@ -334,20 +335,57 @@ int security_inode_alloc(struct inode *inode) void security_inode_free(struct inode *inode) { - ima_inode_free(inode); + integrity_inode_free(inode); security_ops->inode_free_security(inode); } int security_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, char **name, - void **value, size_t *len) + const struct qstr *qstr, + const initxattrs initxattrs, void *fs_data) { + struct xattr new_xattrs[MAX_LSM_EVM_XATTR + 1]; + struct xattr *lsm_xattr, *evm_xattr, *xattr; + int ret; + if (unlikely(IS_PRIVATE(inode))) - return -EOPNOTSUPP; + return 0; + + memset(new_xattrs, 0, sizeof new_xattrs); + if (!initxattrs) + return security_ops->inode_init_security(inode, dir, qstr, + NULL, NULL, NULL); + lsm_xattr = new_xattrs; + ret = security_ops->inode_init_security(inode, dir, qstr, + &lsm_xattr->name, + &lsm_xattr->value, + &lsm_xattr->value_len); + if (ret) + goto out; + + evm_xattr = lsm_xattr + 1; + ret = evm_inode_init_security(inode, lsm_xattr, evm_xattr); + if (ret) + goto out; + ret = initxattrs(inode, new_xattrs, fs_data); +out: + for (xattr = new_xattrs; xattr->name != NULL; xattr++) { + kfree(xattr->name); + kfree(xattr->value); + } + return (ret == -EOPNOTSUPP) ? 0 : ret; +} +EXPORT_SYMBOL(security_inode_init_security); + +int security_old_inode_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, char **name, + void **value, size_t *len) +{ + if (unlikely(IS_PRIVATE(inode))) + return 0; return security_ops->inode_init_security(inode, dir, qstr, name, value, len); } -EXPORT_SYMBOL(security_inode_init_security); +EXPORT_SYMBOL(security_old_inode_init_security); #ifdef CONFIG_SECURITY_PATH int security_path_mknod(struct path *dir, struct dentry *dentry, int mode, @@ -523,9 +561,14 @@ int security_inode_permission(struct inode *inode, int mask) int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { + int ret; + if (unlikely(IS_PRIVATE(dentry->d_inode))) return 0; - return security_ops->inode_setattr(dentry, attr); + ret = security_ops->inode_setattr(dentry, attr); + if (ret) + return ret; + return evm_inode_setattr(dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); @@ -539,9 +582,14 @@ int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) int security_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { + int ret; + if (unlikely(IS_PRIVATE(dentry->d_inode))) return 0; - return security_ops->inode_setxattr(dentry, name, value, size, flags); + ret = security_ops->inode_setxattr(dentry, name, value, size, flags); + if (ret) + return ret; + return evm_inode_setxattr(dentry, name, value, size); } void security_inode_post_setxattr(struct dentry *dentry, const char *name, @@ -550,6 +598,7 @@ void security_inode_post_setxattr(struct dentry *dentry, const char *name, if (unlikely(IS_PRIVATE(dentry->d_inode))) return; security_ops->inode_post_setxattr(dentry, name, value, size, flags); + evm_inode_post_setxattr(dentry, name, value, size); } int security_inode_getxattr(struct dentry *dentry, const char *name) @@ -568,9 +617,14 @@ int security_inode_listxattr(struct dentry *dentry) int security_inode_removexattr(struct dentry *dentry, const char *name) { + int ret; + if (unlikely(IS_PRIVATE(dentry->d_inode))) return 0; - return security_ops->inode_removexattr(dentry, name); + ret = security_ops->inode_removexattr(dentry, name); + if (ret) + return ret; + return evm_inode_removexattr(dentry, name); } int security_inode_need_killpriv(struct dentry *dentry) @@ -1097,6 +1151,7 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk) { security_ops->sk_clone_security(sk, newsk); } +EXPORT_SYMBOL(security_sk_clone); void security_sk_classify_flow(struct sock *sk, struct flowi *fl) { diff --git a/security/selinux/exports.c b/security/selinux/exports.c index 90664385dead..e75dd94e2d2b 100644 --- a/security/selinux/exports.c +++ b/security/selinux/exports.c @@ -12,6 +12,7 @@ * as published by the Free Software Foundation. */ #include <linux/module.h> +#include <linux/selinux.h> #include "security.h" diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 266a2292451d..e545b9f67072 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -89,14 +89,14 @@ #include "xfrm.h" #include "netlabel.h" #include "audit.h" +#include "avc_ss.h" #define NUM_SEL_MNT_OPTS 5 -extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm); extern struct security_operations *security_ops; /* SECMARK reference count */ -atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); +static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP int selinux_enforcing; @@ -279,10 +279,6 @@ static void superblock_free_security(struct super_block *sb) kfree(sbsec); } -/* The security server must be initialized before - any labeling or access decisions can be provided. */ -extern int ss_initialized; - /* The file system's label must be initialized prior to use. */ static const char *labeling_behaviors[6] = { @@ -2097,9 +2093,6 @@ static int selinux_bprm_secureexec(struct linux_binprm *bprm) return (atsecure || cap_bprm_secureexec(bprm)); } -extern struct vfsmount *selinuxfs_mount; -extern struct dentry *selinux_null; - /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) @@ -5803,8 +5796,6 @@ static int selinux_disabled; int selinux_disable(void) { - extern void exit_sel_fs(void); - if (ss_initialized) { /* Not permitted after initial policy load. */ return -EINVAL; diff --git a/security/selinux/include/avc_ss.h b/security/selinux/include/avc_ss.h index 4677aa519b04..d5c328452df0 100644 --- a/security/selinux/include/avc_ss.h +++ b/security/selinux/include/avc_ss.h @@ -18,5 +18,11 @@ struct security_class_mapping { extern struct security_class_mapping secclass_map[]; +/* + * The security server must be initialized before + * any labeling or access decisions can be provided. + */ +extern int ss_initialized; + #endif /* _SELINUX_AVC_SS_H_ */ diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index 3ba4feba048a..d871e8ad2103 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -216,6 +216,14 @@ struct selinux_kernel_status { extern void selinux_status_update_setenforce(int enforcing); extern void selinux_status_update_policyload(int seqno); +extern void selinux_complete_init(void); +extern int selinux_disable(void); +extern void exit_sel_fs(void); +extern struct dentry *selinux_null; +extern struct vfsmount *selinuxfs_mount; +extern void selnl_notify_setenforce(int val); +extern void selnl_notify_policyload(u32 seqno); +extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm); #endif /* _SELINUX_SECURITY_H_ */ diff --git a/security/selinux/netlink.c b/security/selinux/netlink.c index 36ac257cec9a..ce3f481558d8 100644 --- a/security/selinux/netlink.c +++ b/security/selinux/netlink.c @@ -19,6 +19,8 @@ #include <linux/selinux_netlink.h> #include <net/net_namespace.h> +#include "security.h" + static struct sock *selnl; static int selnl_msglen(int msgtype) diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 8b02b2137da2..0920ea3bf599 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -21,6 +21,7 @@ #include "flask.h" #include "av_permissions.h" +#include "security.h" struct nlmsg_perm { u16 nlmsg_type; diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 55d92cbb177a..f46658722c78 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -75,8 +75,6 @@ static char policy_opened; /* global data for policy capabilities */ static struct dentry *policycap_dir; -extern void selnl_notify_setenforce(int val); - /* Check whether a task is allowed to use a security operation. */ static int task_has_security(struct task_struct *tsk, u32 perms) @@ -278,7 +276,6 @@ static ssize_t sel_write_disable(struct file *file, const char __user *buf, char *page = NULL; ssize_t length; int new_value; - extern int selinux_disable(void); length = -ENOMEM; if (count >= PAGE_SIZE) @@ -478,7 +475,7 @@ static struct vm_operations_struct sel_mmap_policy_ops = { .page_mkwrite = sel_mmap_policy_fault, }; -int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma) +static int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHARED) { /* do not allow mprotect to make mapping writable */ diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index a53373207fb4..2ec904177fe0 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -555,7 +555,7 @@ static int cond_write_av_list(struct policydb *p, return 0; } -int cond_write_node(struct policydb *p, struct cond_node *node, +static int cond_write_node(struct policydb *p, struct cond_node *node, struct policy_file *fp) { struct cond_expr *cur_expr; diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h index 3f209c635295..4d1f87466508 100644 --- a/security/selinux/ss/conditional.h +++ b/security/selinux/ss/conditional.h @@ -13,6 +13,7 @@ #include "avtab.h" #include "symtab.h" #include "policydb.h" +#include "../include/conditional.h" #define COND_EXPR_MAXDEPTH 10 diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 2381d0ded228..a7f61d52f05c 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -1743,8 +1743,6 @@ static int policydb_bounds_sanity_check(struct policydb *p) return 0; } -extern int ss_initialized; - u16 string_to_security_class(struct policydb *p, const char *name) { struct class_datum *cladatum; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index f6917bc0aa05..185f849a26f6 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -70,8 +70,6 @@ #include "ebitmap.h" #include "audit.h" -extern void selnl_notify_policyload(u32 seqno); - int selinux_policycap_netpeer; int selinux_policycap_openperm; @@ -1790,7 +1788,6 @@ static void security_load_policycaps(void) POLICYDB_CAPABILITY_OPENPERM); } -extern void selinux_complete_init(void); static int security_preserve_bools(struct policydb *p); /** diff --git a/security/smack/smack.h b/security/smack/smack.h index 2b6c6a516123..2ad00657b801 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -41,9 +41,9 @@ struct superblock_smack { }; struct socket_smack { - char *smk_out; /* outbound label */ - char *smk_in; /* inbound label */ - char smk_packet[SMK_LABELLEN]; /* TCP peer label */ + char *smk_out; /* outbound label */ + char *smk_in; /* inbound label */ + char *smk_packet; /* TCP peer label */ }; /* @@ -116,13 +116,19 @@ struct smk_netlbladdr { * If there is a cipso value associated with the label it * gets stored here, too. This will most likely be rare as * the cipso direct mapping in used internally. + * + * Keep the access rules for this subject label here so that + * the entire set of rules does not need to be examined every + * time. */ struct smack_known { struct list_head list; char smk_known[SMK_LABELLEN]; u32 smk_secid; struct smack_cipso *smk_cipso; - spinlock_t smk_cipsolock; /* for changing cipso map */ + spinlock_t smk_cipsolock; /* for changing cipso map */ + struct list_head smk_rules; /* access rules */ + struct mutex smk_rules_lock; /* lock for the rules */ }; /* @@ -150,7 +156,6 @@ struct smack_known { /* * smackfs magic number - * smackfs macic number */ #define SMACK_MAGIC 0x43415d53 /* "SMAC" */ @@ -176,9 +181,9 @@ struct smack_known { #define MAY_NOT 0 /* - * Number of access types used by Smack (rwxa) + * Number of access types used by Smack (rwxat) */ -#define SMK_NUM_ACCESS_TYPE 4 +#define SMK_NUM_ACCESS_TYPE 5 /* * Smack audit data; is empty if CONFIG_AUDIT not set @@ -201,10 +206,12 @@ int smk_access_entry(char *, char *, struct list_head *); int smk_access(char *, char *, int, struct smk_audit_info *); int smk_curacc(char *, u32, struct smk_audit_info *); int smack_to_cipso(const char *, struct smack_cipso *); -void smack_from_cipso(u32, char *, char *); +char *smack_from_cipso(u32, char *); char *smack_from_secid(const u32); +void smk_parse_smack(const char *string, int len, char *smack); char *smk_import(const char *, int); struct smack_known *smk_import_entry(const char *, int); +struct smack_known *smk_find_entry(const char *); u32 smack_to_secid(const char *); /* @@ -223,7 +230,6 @@ extern struct smack_known smack_known_star; extern struct smack_known smack_known_web; extern struct list_head smack_known_list; -extern struct list_head smack_rule_list; extern struct list_head smk_netlbladdr_list; extern struct security_operations smack_ops; diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 9637e107f7ea..cc7cb6edba08 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -77,14 +77,19 @@ int log_policy = SMACK_AUDIT_DENIED; * entry is found returns -ENOENT. * * NOTE: - * Even though Smack labels are usually shared on smack_list - * labels that come in off the network can't be imported - * and added to the list for locking reasons. * - * Therefore, it is necessary to check the contents of the labels, - * not just the pointer values. Of course, in most cases the labels - * will be on the list, so checking the pointers may be a worthwhile - * optimization. + * Earlier versions of this function allowed for labels that + * were not on the label list. This was done to allow for + * labels to come over the network that had never been seen + * before on this host. Unless the receiving socket has the + * star label this will always result in a failure check. The + * star labeled socket case is now handled in the networking + * hooks so there is no case where the label is not on the + * label list. Checking to see if the address of two labels + * is the same is now a reliable test. + * + * Do the object check first because that is more + * likely to differ. */ int smk_access_entry(char *subject_label, char *object_label, struct list_head *rule_list) @@ -93,13 +98,10 @@ int smk_access_entry(char *subject_label, char *object_label, struct smack_rule *srp; list_for_each_entry_rcu(srp, rule_list, list) { - if (srp->smk_subject == subject_label || - strcmp(srp->smk_subject, subject_label) == 0) { - if (srp->smk_object == object_label || - strcmp(srp->smk_object, object_label) == 0) { - may = srp->smk_access; - break; - } + if (srp->smk_object == object_label && + srp->smk_subject == subject_label) { + may = srp->smk_access; + break; } } @@ -117,18 +119,12 @@ int smk_access_entry(char *subject_label, char *object_label, * access rule list and returns 0 if the access is permitted, * non zero otherwise. * - * Even though Smack labels are usually shared on smack_list - * labels that come in off the network can't be imported - * and added to the list for locking reasons. - * - * Therefore, it is necessary to check the contents of the labels, - * not just the pointer values. Of course, in most cases the labels - * will be on the list, so checking the pointers may be a worthwhile - * optimization. + * Smack labels are shared on smack_list */ int smk_access(char *subject_label, char *object_label, int request, struct smk_audit_info *a) { + struct smack_known *skp; int may = MAY_NOT; int rc = 0; @@ -137,8 +133,7 @@ int smk_access(char *subject_label, char *object_label, int request, * * A star subject can't access any object. */ - if (subject_label == smack_known_star.smk_known || - strcmp(subject_label, smack_known_star.smk_known) == 0) { + if (subject_label == smack_known_star.smk_known) { rc = -EACCES; goto out_audit; } @@ -148,33 +143,27 @@ int smk_access(char *subject_label, char *object_label, int request, * An internet subject can access any object. */ if (object_label == smack_known_web.smk_known || - subject_label == smack_known_web.smk_known || - strcmp(object_label, smack_known_web.smk_known) == 0 || - strcmp(subject_label, smack_known_web.smk_known) == 0) + subject_label == smack_known_web.smk_known) goto out_audit; /* * A star object can be accessed by any subject. */ - if (object_label == smack_known_star.smk_known || - strcmp(object_label, smack_known_star.smk_known) == 0) + if (object_label == smack_known_star.smk_known) goto out_audit; /* * An object can be accessed in any way by a subject * with the same label. */ - if (subject_label == object_label || - strcmp(subject_label, object_label) == 0) + if (subject_label == object_label) goto out_audit; /* * A hat subject can read any object. * A floor object can be read by any subject. */ if ((request & MAY_ANYREAD) == request) { - if (object_label == smack_known_floor.smk_known || - strcmp(object_label, smack_known_floor.smk_known) == 0) + if (object_label == smack_known_floor.smk_known) goto out_audit; - if (subject_label == smack_known_hat.smk_known || - strcmp(subject_label, smack_known_hat.smk_known) == 0) + if (subject_label == smack_known_hat.smk_known) goto out_audit; } /* @@ -184,8 +173,9 @@ int smk_access(char *subject_label, char *object_label, int request, * good. A negative response from smk_access_entry() * indicates there is no entry for this pair. */ + skp = smk_find_entry(subject_label); rcu_read_lock(); - may = smk_access_entry(subject_label, object_label, &smack_rule_list); + may = smk_access_entry(subject_label, object_label, &skp->smk_rules); rcu_read_unlock(); if (may > 0 && (request & may) == request) @@ -344,17 +334,32 @@ void smack_log(char *subject_label, char *object_label, int request, static DEFINE_MUTEX(smack_known_lock); /** - * smk_import_entry - import a label, return the list entry + * smk_find_entry - find a label on the list, return the list entry * @string: a text string that might be a Smack label - * @len: the maximum size, or zero if it is NULL terminated. * * Returns a pointer to the entry in the label list that - * matches the passed string, adding it if necessary. + * matches the passed string. */ -struct smack_known *smk_import_entry(const char *string, int len) +struct smack_known *smk_find_entry(const char *string) { struct smack_known *skp; - char smack[SMK_LABELLEN]; + + list_for_each_entry_rcu(skp, &smack_known_list, list) { + if (strncmp(skp->smk_known, string, SMK_MAXLEN) == 0) + return skp; + } + + return NULL; +} + +/** + * smk_parse_smack - parse smack label from a text string + * @string: a text string that might contain a Smack label + * @len: the maximum size, or zero if it is NULL terminated. + * @smack: parsed smack label, or NULL if parse error + */ +void smk_parse_smack(const char *string, int len, char *smack) +{ int found; int i; @@ -372,27 +377,38 @@ struct smack_known *smk_import_entry(const char *string, int len) } else smack[i] = string[i]; } +} + +/** + * smk_import_entry - import a label, return the list entry + * @string: a text string that might be a Smack label + * @len: the maximum size, or zero if it is NULL terminated. + * + * Returns a pointer to the entry in the label list that + * matches the passed string, adding it if necessary. + */ +struct smack_known *smk_import_entry(const char *string, int len) +{ + struct smack_known *skp; + char smack[SMK_LABELLEN]; + smk_parse_smack(string, len, smack); if (smack[0] == '\0') return NULL; mutex_lock(&smack_known_lock); - found = 0; - list_for_each_entry_rcu(skp, &smack_known_list, list) { - if (strncmp(skp->smk_known, smack, SMK_MAXLEN) == 0) { - found = 1; - break; - } - } + skp = smk_find_entry(smack); - if (found == 0) { + if (skp == NULL) { skp = kzalloc(sizeof(struct smack_known), GFP_KERNEL); if (skp != NULL) { strncpy(skp->smk_known, smack, SMK_MAXLEN); skp->smk_secid = smack_next_secid++; skp->smk_cipso = NULL; + INIT_LIST_HEAD(&skp->smk_rules); spin_lock_init(&skp->smk_cipsolock); + mutex_init(&skp->smk_rules_lock); /* * Make sure that the entry is actually * filled before putting it on the list. @@ -480,19 +496,12 @@ u32 smack_to_secid(const char *smack) * smack_from_cipso - find the Smack label associated with a CIPSO option * @level: Bell & LaPadula level from the network * @cp: Bell & LaPadula categories from the network - * @result: where to put the Smack value * * This is a simple lookup in the label table. * - * This is an odd duck as far as smack handling goes in that - * it sends back a copy of the smack label rather than a pointer - * to the master list. This is done because it is possible for - * a foreign host to send a smack label that is new to this - * machine and hence not on the list. That would not be an - * issue except that adding an entry to the master list can't - * be done at that point. + * Return the matching label from the label list or NULL. */ -void smack_from_cipso(u32 level, char *cp, char *result) +char *smack_from_cipso(u32 level, char *cp) { struct smack_known *kp; char *final = NULL; @@ -509,12 +518,13 @@ void smack_from_cipso(u32 level, char *cp, char *result) final = kp->smk_known; spin_unlock_bh(&kp->smk_cipsolock); + + if (final != NULL) + break; } rcu_read_unlock(); - if (final == NULL) - final = smack_known_huh.smk_known; - strncpy(result, final, SMK_MAXLEN); - return; + + return final; } /** diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index b9c5e149903b..7db62b48eb42 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -5,12 +5,13 @@ * * Authors: * Casey Schaufler <casey@schaufler-ca.com> - * Jarkko Sakkinen <ext-jarkko.2.sakkinen@nokia.com> + * Jarkko Sakkinen <jarkko.sakkinen@intel.com> * * Copyright (C) 2007 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2010 Nokia Corporation + * Copyright (C) 2011 Intel Corporation. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, @@ -34,6 +35,7 @@ #include <linux/audit.h> #include <linux/magic.h> #include <linux/dcache.h> +#include <linux/personality.h> #include "smack.h" #define task_security(task) (task_cred_xxx((task), security)) @@ -441,11 +443,17 @@ static int smack_sb_umount(struct vfsmount *mnt, int flags) * BPRM hooks */ +/** + * smack_bprm_set_creds - set creds for exec + * @bprm: the exec information + * + * Returns 0 if it gets a blob, -ENOMEM otherwise + */ static int smack_bprm_set_creds(struct linux_binprm *bprm) { - struct task_smack *tsp = bprm->cred->security; + struct inode *inode = bprm->file->f_path.dentry->d_inode; + struct task_smack *bsp = bprm->cred->security; struct inode_smack *isp; - struct dentry *dp; int rc; rc = cap_bprm_set_creds(bprm); @@ -455,20 +463,48 @@ static int smack_bprm_set_creds(struct linux_binprm *bprm) if (bprm->cred_prepared) return 0; - if (bprm->file == NULL || bprm->file->f_dentry == NULL) + isp = inode->i_security; + if (isp->smk_task == NULL || isp->smk_task == bsp->smk_task) return 0; - dp = bprm->file->f_dentry; + if (bprm->unsafe) + return -EPERM; - if (dp->d_inode == NULL) - return 0; + bsp->smk_task = isp->smk_task; + bprm->per_clear |= PER_CLEAR_ON_SETID; - isp = dp->d_inode->i_security; + return 0; +} - if (isp->smk_task != NULL) - tsp->smk_task = isp->smk_task; +/** + * smack_bprm_committing_creds - Prepare to install the new credentials + * from bprm. + * + * @bprm: binprm for exec + */ +static void smack_bprm_committing_creds(struct linux_binprm *bprm) +{ + struct task_smack *bsp = bprm->cred->security; - return 0; + if (bsp->smk_task != bsp->smk_forked) + current->pdeath_signal = 0; +} + +/** + * smack_bprm_secureexec - Return the decision to use secureexec. + * @bprm: binprm for exec + * + * Returns 0 on success. + */ +static int smack_bprm_secureexec(struct linux_binprm *bprm) +{ + struct task_smack *tsp = current_security(); + int ret = cap_bprm_secureexec(bprm); + + if (!ret && (tsp->smk_task != tsp->smk_forked)) + ret = 1; + + return ret; } /* @@ -516,6 +552,8 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, char **name, void **value, size_t *len) { + struct smack_known *skp; + char *csp = smk_of_current(); char *isp = smk_of_inode(inode); char *dsp = smk_of_inode(dir); int may; @@ -527,8 +565,9 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir, } if (value) { + skp = smk_find_entry(csp); rcu_read_lock(); - may = smk_access_entry(smk_of_current(), dsp, &smack_rule_list); + may = smk_access_entry(csp, dsp, &skp->smk_rules); rcu_read_unlock(); /* @@ -841,7 +880,7 @@ static void smack_inode_post_setxattr(struct dentry *dentry, const char *name, return; } -/* +/** * smack_inode_getxattr - Smack check on getxattr * @dentry: the object * @name: unused @@ -858,7 +897,7 @@ static int smack_inode_getxattr(struct dentry *dentry, const char *name) return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad); } -/* +/** * smack_inode_removexattr - Smack check on removexattr * @dentry: the object * @name: name of the attribute @@ -1088,36 +1127,31 @@ static int smack_file_lock(struct file *file, unsigned int cmd) * @cmd: what action to check * @arg: unused * + * Generally these operations are harmless. + * File locking operations present an obvious mechanism + * for passing information, so they require write access. + * * Returns 0 if current has access, error code otherwise */ static int smack_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { struct smk_audit_info ad; - int rc; + int rc = 0; - smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH); - smk_ad_setfield_u_fs_path(&ad, file->f_path); switch (cmd) { - case F_DUPFD: - case F_GETFD: - case F_GETFL: case F_GETLK: - case F_GETOWN: - case F_GETSIG: - rc = smk_curacc(file->f_security, MAY_READ, &ad); - break; - case F_SETFD: - case F_SETFL: case F_SETLK: case F_SETLKW: case F_SETOWN: case F_SETSIG: + smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH); + smk_ad_setfield_u_fs_path(&ad, file->f_path); rc = smk_curacc(file->f_security, MAY_WRITE, &ad); break; default: - rc = smk_curacc(file->f_security, MAY_READWRITE, &ad); + break; } return rc; @@ -1138,6 +1172,7 @@ static int smack_file_mmap(struct file *file, unsigned long flags, unsigned long addr, unsigned long addr_only) { + struct smack_known *skp; struct smack_rule *srp; struct task_smack *tsp; char *sp; @@ -1170,6 +1205,7 @@ static int smack_file_mmap(struct file *file, tsp = current_security(); sp = smk_of_current(); + skp = smk_find_entry(sp); rc = 0; rcu_read_lock(); @@ -1177,15 +1213,8 @@ static int smack_file_mmap(struct file *file, * For each Smack rule associated with the subject * label verify that the SMACK64MMAP also has access * to that rule's object label. - * - * Because neither of the labels comes - * from the networking code it is sufficient - * to compare pointers. */ - list_for_each_entry_rcu(srp, &smack_rule_list, list) { - if (srp->smk_subject != sp) - continue; - + list_for_each_entry_rcu(srp, &skp->smk_rules, list) { osmack = srp->smk_object; /* * Matching labels always allows access. @@ -1214,7 +1243,8 @@ static int smack_file_mmap(struct file *file, * If there isn't one a SMACK64MMAP subject * can't have as much access as current. */ - mmay = smk_access_entry(msmack, osmack, &smack_rule_list); + skp = smk_find_entry(msmack); + mmay = smk_access_entry(msmack, osmack, &skp->smk_rules); if (mmay == -ENOENT) { rc = -EACCES; break; @@ -1315,6 +1345,24 @@ static int smack_file_receive(struct file *file) return smk_curacc(file->f_security, may, &ad); } +/** + * smack_dentry_open - Smack dentry open processing + * @file: the object + * @cred: unused + * + * Set the security blob in the file structure. + * + * Returns 0 + */ +static int smack_dentry_open(struct file *file, const struct cred *cred) +{ + struct inode_smack *isp = file->f_path.dentry->d_inode->i_security; + + file->f_security = isp->smk_inode; + + return 0; +} + /* * Task hooks */ @@ -1455,15 +1503,17 @@ static int smack_kernel_create_files_as(struct cred *new, /** * smk_curacc_on_task - helper to log task related access * @p: the task object - * @access : the access requested + * @access: the access requested + * @caller: name of the calling function for audit * * Return 0 if access is permitted */ -static int smk_curacc_on_task(struct task_struct *p, int access) +static int smk_curacc_on_task(struct task_struct *p, int access, + const char *caller) { struct smk_audit_info ad; - smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK); + smk_ad_init(&ad, caller, LSM_AUDIT_DATA_TASK); smk_ad_setfield_u_tsk(&ad, p); return smk_curacc(smk_of_task(task_security(p)), access, &ad); } @@ -1477,7 +1527,7 @@ static int smk_curacc_on_task(struct task_struct *p, int access) */ static int smack_task_setpgid(struct task_struct *p, pid_t pgid) { - return smk_curacc_on_task(p, MAY_WRITE); + return smk_curacc_on_task(p, MAY_WRITE, __func__); } /** @@ -1488,7 +1538,7 @@ static int smack_task_setpgid(struct task_struct *p, pid_t pgid) */ static int smack_task_getpgid(struct task_struct *p) { - return smk_curacc_on_task(p, MAY_READ); + return smk_curacc_on_task(p, MAY_READ, __func__); } /** @@ -1499,7 +1549,7 @@ static int smack_task_getpgid(struct task_struct *p) */ static int smack_task_getsid(struct task_struct *p) { - return smk_curacc_on_task(p, MAY_READ); + return smk_curacc_on_task(p, MAY_READ, __func__); } /** @@ -1527,7 +1577,7 @@ static int smack_task_setnice(struct task_struct *p, int nice) rc = cap_task_setnice(p, nice); if (rc == 0) - rc = smk_curacc_on_task(p, MAY_WRITE); + rc = smk_curacc_on_task(p, MAY_WRITE, __func__); return rc; } @@ -1544,7 +1594,7 @@ static int smack_task_setioprio(struct task_struct *p, int ioprio) rc = cap_task_setioprio(p, ioprio); if (rc == 0) - rc = smk_curacc_on_task(p, MAY_WRITE); + rc = smk_curacc_on_task(p, MAY_WRITE, __func__); return rc; } @@ -1556,7 +1606,7 @@ static int smack_task_setioprio(struct task_struct *p, int ioprio) */ static int smack_task_getioprio(struct task_struct *p) { - return smk_curacc_on_task(p, MAY_READ); + return smk_curacc_on_task(p, MAY_READ, __func__); } /** @@ -1573,7 +1623,7 @@ static int smack_task_setscheduler(struct task_struct *p) rc = cap_task_setscheduler(p); if (rc == 0) - rc = smk_curacc_on_task(p, MAY_WRITE); + rc = smk_curacc_on_task(p, MAY_WRITE, __func__); return rc; } @@ -1585,7 +1635,7 @@ static int smack_task_setscheduler(struct task_struct *p) */ static int smack_task_getscheduler(struct task_struct *p) { - return smk_curacc_on_task(p, MAY_READ); + return smk_curacc_on_task(p, MAY_READ, __func__); } /** @@ -1596,7 +1646,7 @@ static int smack_task_getscheduler(struct task_struct *p) */ static int smack_task_movememory(struct task_struct *p) { - return smk_curacc_on_task(p, MAY_WRITE); + return smk_curacc_on_task(p, MAY_WRITE, __func__); } /** @@ -1711,7 +1761,7 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) ssp->smk_in = csp; ssp->smk_out = csp; - ssp->smk_packet[0] = '\0'; + ssp->smk_packet = NULL; sk->sk_security = ssp; @@ -2753,6 +2803,7 @@ static int smack_unix_stream_connect(struct sock *sock, { struct socket_smack *ssp = sock->sk_security; struct socket_smack *osp = other->sk_security; + struct socket_smack *nsp = newsk->sk_security; struct smk_audit_info ad; int rc = 0; @@ -2762,6 +2813,14 @@ static int smack_unix_stream_connect(struct sock *sock, if (!capable(CAP_MAC_OVERRIDE)) rc = smk_access(ssp->smk_out, osp->smk_in, MAY_WRITE, &ad); + /* + * Cross reference the peer labels for SO_PEERSEC. + */ + if (rc == 0) { + nsp->smk_packet = ssp->smk_out; + ssp->smk_packet = osp->smk_out; + } + return rc; } @@ -2813,16 +2872,17 @@ static int smack_socket_sendmsg(struct socket *sock, struct msghdr *msg, return smack_netlabel_send(sock->sk, sip); } - /** * smack_from_secattr - Convert a netlabel attr.mls.lvl/attr.mls.cat pair to smack * @sap: netlabel secattr - * @sip: where to put the result + * @ssp: socket security information * - * Copies a smack label into sip + * Returns a pointer to a Smack label found on the label list. */ -static void smack_from_secattr(struct netlbl_lsm_secattr *sap, char *sip) +static char *smack_from_secattr(struct netlbl_lsm_secattr *sap, + struct socket_smack *ssp) { + struct smack_known *skp; char smack[SMK_LABELLEN]; char *sp; int pcat; @@ -2852,15 +2912,43 @@ static void smack_from_secattr(struct netlbl_lsm_secattr *sap, char *sip) * we are already done. WeeHee. */ if (sap->attr.mls.lvl == smack_cipso_direct) { - memcpy(sip, smack, SMK_MAXLEN); - return; + /* + * The label sent is usually on the label list. + * + * If it is not we may still want to allow the + * delivery. + * + * If the recipient is accepting all packets + * because it is using the star ("*") label + * for SMACK64IPIN provide the web ("@") label + * so that a directed response will succeed. + * This is not very correct from a MAC point + * of view, but gets around the problem that + * locking prevents adding the newly discovered + * label to the list. + * The case where the recipient is not using + * the star label should obviously fail. + * The easy way to do this is to provide the + * star label as the subject label. + */ + skp = smk_find_entry(smack); + if (skp != NULL) + return skp->smk_known; + if (ssp != NULL && + ssp->smk_in == smack_known_star.smk_known) + return smack_known_web.smk_known; + return smack_known_star.smk_known; } /* * Look it up in the supplied table if it is not * a direct mapping. */ - smack_from_cipso(sap->attr.mls.lvl, smack, sip); - return; + sp = smack_from_cipso(sap->attr.mls.lvl, smack); + if (sp != NULL) + return sp; + if (ssp != NULL && ssp->smk_in == smack_known_star.smk_known) + return smack_known_web.smk_known; + return smack_known_star.smk_known; } if ((sap->flags & NETLBL_SECATTR_SECID) != 0) { /* @@ -2875,16 +2963,14 @@ static void smack_from_secattr(struct netlbl_lsm_secattr *sap, char *sip) * secid is from a fallback. */ BUG_ON(sp == NULL); - strncpy(sip, sp, SMK_MAXLEN); - return; + return sp; } /* * Without guidance regarding the smack value * for the packet fall back on the network * ambient value. */ - strncpy(sip, smack_net_ambient, SMK_MAXLEN); - return; + return smack_net_ambient; } /** @@ -2898,7 +2984,6 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct netlbl_lsm_secattr secattr; struct socket_smack *ssp = sk->sk_security; - char smack[SMK_LABELLEN]; char *csp; int rc; struct smk_audit_info ad; @@ -2911,10 +2996,9 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) netlbl_secattr_init(&secattr); rc = netlbl_skbuff_getattr(skb, sk->sk_family, &secattr); - if (rc == 0) { - smack_from_secattr(&secattr, smack); - csp = smack; - } else + if (rc == 0) + csp = smack_from_secattr(&secattr, ssp); + else csp = smack_net_ambient; netlbl_secattr_destroy(&secattr); @@ -2951,15 +3035,19 @@ static int smack_socket_getpeersec_stream(struct socket *sock, int __user *optlen, unsigned len) { struct socket_smack *ssp; - int slen; + char *rcp = ""; + int slen = 1; int rc = 0; ssp = sock->sk->sk_security; - slen = strlen(ssp->smk_packet) + 1; + if (ssp->smk_packet != NULL) { + rcp = ssp->smk_packet; + slen = strlen(rcp) + 1; + } if (slen > len) rc = -ERANGE; - else if (copy_to_user(optval, ssp->smk_packet, slen) != 0) + else if (copy_to_user(optval, rcp, slen) != 0) rc = -EFAULT; if (put_user(slen, optlen) != 0) @@ -2982,8 +3070,8 @@ static int smack_socket_getpeersec_dgram(struct socket *sock, { struct netlbl_lsm_secattr secattr; - struct socket_smack *sp; - char smack[SMK_LABELLEN]; + struct socket_smack *ssp = NULL; + char *sp; int family = PF_UNSPEC; u32 s = 0; /* 0 is the invalid secid */ int rc; @@ -2998,17 +3086,19 @@ static int smack_socket_getpeersec_dgram(struct socket *sock, family = sock->sk->sk_family; if (family == PF_UNIX) { - sp = sock->sk->sk_security; - s = smack_to_secid(sp->smk_out); + ssp = sock->sk->sk_security; + s = smack_to_secid(ssp->smk_out); } else if (family == PF_INET || family == PF_INET6) { /* * Translate what netlabel gave us. */ + if (sock != NULL && sock->sk != NULL) + ssp = sock->sk->sk_security; netlbl_secattr_init(&secattr); rc = netlbl_skbuff_getattr(skb, family, &secattr); if (rc == 0) { - smack_from_secattr(&secattr, smack); - s = smack_to_secid(smack); + sp = smack_from_secattr(&secattr, ssp); + s = smack_to_secid(sp); } netlbl_secattr_destroy(&secattr); } @@ -3056,7 +3146,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct netlbl_lsm_secattr secattr; struct sockaddr_in addr; struct iphdr *hdr; - char smack[SMK_LABELLEN]; + char *sp; int rc; struct smk_audit_info ad; @@ -3067,9 +3157,9 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, netlbl_secattr_init(&secattr); rc = netlbl_skbuff_getattr(skb, family, &secattr); if (rc == 0) - smack_from_secattr(&secattr, smack); + sp = smack_from_secattr(&secattr, ssp); else - strncpy(smack, smack_known_huh.smk_known, SMK_MAXLEN); + sp = smack_known_huh.smk_known; netlbl_secattr_destroy(&secattr); #ifdef CONFIG_AUDIT @@ -3082,7 +3172,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, * Receiving a packet requires that the other end be able to write * here. Read access is not required. */ - rc = smk_access(smack, ssp->smk_in, MAY_WRITE, &ad); + rc = smk_access(sp, ssp->smk_in, MAY_WRITE, &ad); if (rc != 0) return rc; @@ -3090,7 +3180,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, * Save the peer's label in the request_sock so we can later setup * smk_packet in the child socket so that SO_PEERCRED can report it. */ - req->peer_secid = smack_to_secid(smack); + req->peer_secid = smack_to_secid(sp); /* * We need to decide if we want to label the incoming connection here @@ -3103,7 +3193,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, if (smack_host_label(&addr) == NULL) { rcu_read_unlock(); netlbl_secattr_init(&secattr); - smack_to_secattr(smack, &secattr); + smack_to_secattr(sp, &secattr); rc = netlbl_req_setattr(req, &secattr); netlbl_secattr_destroy(&secattr); } else { @@ -3125,13 +3215,11 @@ static void smack_inet_csk_clone(struct sock *sk, const struct request_sock *req) { struct socket_smack *ssp = sk->sk_security; - char *smack; - if (req->peer_secid != 0) { - smack = smack_from_secid(req->peer_secid); - strncpy(ssp->smk_packet, smack, SMK_MAXLEN); - } else - ssp->smk_packet[0] = '\0'; + if (req->peer_secid != 0) + ssp->smk_packet = smack_from_secid(req->peer_secid); + else + ssp->smk_packet = NULL; } /* @@ -3409,6 +3497,8 @@ struct security_operations smack_ops = { .sb_umount = smack_sb_umount, .bprm_set_creds = smack_bprm_set_creds, + .bprm_committing_creds = smack_bprm_committing_creds, + .bprm_secureexec = smack_bprm_secureexec, .inode_alloc_security = smack_inode_alloc_security, .inode_free_security = smack_inode_free_security, @@ -3440,6 +3530,8 @@ struct security_operations smack_ops = { .file_send_sigiotask = smack_file_send_sigiotask, .file_receive = smack_file_receive, + .dentry_open = smack_dentry_open, + .cred_alloc_blank = smack_cred_alloc_blank, .cred_free = smack_cred_free, .cred_prepare = smack_cred_prepare, diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index f93460156dce..6aceef518a41 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -44,6 +44,7 @@ enum smk_inos { SMK_ONLYCAP = 9, /* the only "capable" label */ SMK_LOGGING = 10, /* logging */ SMK_LOAD_SELF = 11, /* task specific rules */ + SMK_ACCESSES = 12, /* access policy */ }; /* @@ -85,6 +86,16 @@ char *smack_onlycap; */ LIST_HEAD(smk_netlbladdr_list); + +/* + * Rule lists are maintained for each label. + * This master list is just for reading /smack/load. + */ +struct smack_master_list { + struct list_head list; + struct smack_rule *smk_rule; +}; + LIST_HEAD(smack_rule_list); static int smk_cipso_doi_value = SMACK_CIPSO_DOI_DEFAULT; @@ -92,7 +103,7 @@ static int smk_cipso_doi_value = SMACK_CIPSO_DOI_DEFAULT; const char *smack_cipso_option = SMACK_CIPSO_OPTION; -#define SEQ_READ_FINISHED 1 +#define SEQ_READ_FINISHED ((loff_t)-1) /* * Values for parsing cipso rules @@ -159,9 +170,13 @@ static int smk_set_access(struct smack_rule *srp, struct list_head *rule_list, mutex_lock(rule_lock); + /* + * Because the object label is less likely to match + * than the subject label check it first + */ list_for_each_entry_rcu(sp, rule_list, list) { - if (sp->smk_subject == srp->smk_subject && - sp->smk_object == srp->smk_object) { + if (sp->smk_object == srp->smk_object && + sp->smk_subject == srp->smk_subject) { found = 1; sp->smk_access = srp->smk_access; break; @@ -176,6 +191,99 @@ static int smk_set_access(struct smack_rule *srp, struct list_head *rule_list, } /** + * smk_parse_rule - parse Smack rule from load string + * @data: string to be parsed whose size is SMK_LOADLEN + * @rule: Smack rule + * @import: if non-zero, import labels + */ +static int smk_parse_rule(const char *data, struct smack_rule *rule, int import) +{ + char smack[SMK_LABELLEN]; + struct smack_known *skp; + + if (import) { + rule->smk_subject = smk_import(data, 0); + if (rule->smk_subject == NULL) + return -1; + + rule->smk_object = smk_import(data + SMK_LABELLEN, 0); + if (rule->smk_object == NULL) + return -1; + } else { + smk_parse_smack(data, 0, smack); + skp = smk_find_entry(smack); + if (skp == NULL) + return -1; + rule->smk_subject = skp->smk_known; + + smk_parse_smack(data + SMK_LABELLEN, 0, smack); + skp = smk_find_entry(smack); + if (skp == NULL) + return -1; + rule->smk_object = skp->smk_known; + } + + rule->smk_access = 0; + + switch (data[SMK_LABELLEN + SMK_LABELLEN]) { + case '-': + break; + case 'r': + case 'R': + rule->smk_access |= MAY_READ; + break; + default: + return -1; + } + + switch (data[SMK_LABELLEN + SMK_LABELLEN + 1]) { + case '-': + break; + case 'w': + case 'W': + rule->smk_access |= MAY_WRITE; + break; + default: + return -1; + } + + switch (data[SMK_LABELLEN + SMK_LABELLEN + 2]) { + case '-': + break; + case 'x': + case 'X': + rule->smk_access |= MAY_EXEC; + break; + default: + return -1; + } + + switch (data[SMK_LABELLEN + SMK_LABELLEN + 3]) { + case '-': + break; + case 'a': + case 'A': + rule->smk_access |= MAY_APPEND; + break; + default: + return -1; + } + + switch (data[SMK_LABELLEN + SMK_LABELLEN + 4]) { + case '-': + break; + case 't': + case 'T': + rule->smk_access |= MAY_TRANSMUTE; + break; + default: + return -1; + } + + return 0; +} + +/** * smk_write_load_list - write() for any /smack/load * @file: file pointer, not actually used * @buf: where to get the data from @@ -197,9 +305,12 @@ static ssize_t smk_write_load_list(struct file *file, const char __user *buf, struct list_head *rule_list, struct mutex *rule_lock) { + struct smack_master_list *smlp; + struct smack_known *skp; struct smack_rule *rule; char *data; int rc = -EINVAL; + int load = 0; /* * No partial writes. @@ -234,69 +345,14 @@ static ssize_t smk_write_load_list(struct file *file, const char __user *buf, goto out; } - rule->smk_subject = smk_import(data, 0); - if (rule->smk_subject == NULL) - goto out_free_rule; - - rule->smk_object = smk_import(data + SMK_LABELLEN, 0); - if (rule->smk_object == NULL) + if (smk_parse_rule(data, rule, 1)) goto out_free_rule; - rule->smk_access = 0; - - switch (data[SMK_LABELLEN + SMK_LABELLEN]) { - case '-': - break; - case 'r': - case 'R': - rule->smk_access |= MAY_READ; - break; - default: - goto out_free_rule; - } - - switch (data[SMK_LABELLEN + SMK_LABELLEN + 1]) { - case '-': - break; - case 'w': - case 'W': - rule->smk_access |= MAY_WRITE; - break; - default: - goto out_free_rule; - } - - switch (data[SMK_LABELLEN + SMK_LABELLEN + 2]) { - case '-': - break; - case 'x': - case 'X': - rule->smk_access |= MAY_EXEC; - break; - default: - goto out_free_rule; - } - - switch (data[SMK_LABELLEN + SMK_LABELLEN + 3]) { - case '-': - break; - case 'a': - case 'A': - rule->smk_access |= MAY_APPEND; - break; - default: - goto out_free_rule; - } - - switch (data[SMK_LABELLEN + SMK_LABELLEN + 4]) { - case '-': - break; - case 't': - case 'T': - rule->smk_access |= MAY_TRANSMUTE; - break; - default: - goto out_free_rule; + if (rule_list == NULL) { + load = 1; + skp = smk_find_entry(rule->smk_subject); + rule_list = &skp->smk_rules; + rule_lock = &skp->smk_rules_lock; } rc = count; @@ -304,8 +360,15 @@ static ssize_t smk_write_load_list(struct file *file, const char __user *buf, * smk_set_access returns true if there was already a rule * for the subject/object pair, and false if it was new. */ - if (!smk_set_access(rule, rule_list, rule_lock)) + if (!smk_set_access(rule, rule_list, rule_lock)) { + smlp = kzalloc(sizeof(*smlp), GFP_KERNEL); + if (smlp != NULL) { + smlp->smk_rule = rule; + list_add_rcu(&smlp->list, &smack_rule_list); + } else + rc = -ENOMEM; goto out; + } out_free_rule: kfree(rule); @@ -321,11 +384,24 @@ out: static void *load_seq_start(struct seq_file *s, loff_t *pos) { - if (*pos == SEQ_READ_FINISHED) + struct list_head *list; + + /* + * This is 0 the first time through. + */ + if (s->index == 0) + s->private = &smack_rule_list; + + if (s->private == NULL) return NULL; - if (list_empty(&smack_rule_list)) + + list = s->private; + if (list_empty(list)) return NULL; - return smack_rule_list.next; + + if (s->index == 0) + return list->next; + return list; } static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos) @@ -333,17 +409,19 @@ static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos) struct list_head *list = v; if (list_is_last(list, &smack_rule_list)) { - *pos = SEQ_READ_FINISHED; + s->private = NULL; return NULL; } + s->private = list->next; return list->next; } static int load_seq_show(struct seq_file *s, void *v) { struct list_head *list = v; - struct smack_rule *srp = - list_entry(list, struct smack_rule, list); + struct smack_master_list *smlp = + list_entry(list, struct smack_master_list, list); + struct smack_rule *srp = smlp->smk_rule; seq_printf(s, "%s %s", (char *)srp->smk_subject, (char *)srp->smk_object); @@ -412,8 +490,7 @@ static ssize_t smk_write_load(struct file *file, const char __user *buf, if (!capable(CAP_MAC_ADMIN)) return -EPERM; - return smk_write_load_list(file, buf, count, ppos, &smack_rule_list, - &smack_list_lock); + return smk_write_load_list(file, buf, count, ppos, NULL, NULL); } static const struct file_operations smk_load_ops = { @@ -1425,6 +1502,44 @@ static const struct file_operations smk_load_self_ops = { .write = smk_write_load_self, .release = seq_release, }; + +/** + * smk_write_access - handle access check transaction + * @file: file pointer + * @buf: data from user space + * @count: bytes sent + * @ppos: where to start - must be 0 + */ +static ssize_t smk_write_access(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct smack_rule rule; + char *data; + int res; + + data = simple_transaction_get(file, buf, count); + if (IS_ERR(data)) + return PTR_ERR(data); + + if (count < SMK_LOADLEN || smk_parse_rule(data, &rule, 0)) + return -EINVAL; + + res = smk_access(rule.smk_subject, rule.smk_object, rule.smk_access, + NULL); + data[0] = res == 0 ? '1' : '0'; + data[1] = '\0'; + + simple_transaction_set(file, 2); + return SMK_LOADLEN; +} + +static const struct file_operations smk_access_ops = { + .write = smk_write_access, + .read = simple_transaction_read, + .release = simple_transaction_release, + .llseek = generic_file_llseek, +}; + /** * smk_fill_super - fill the /smackfs superblock * @sb: the empty superblock @@ -1459,6 +1574,8 @@ static int smk_fill_super(struct super_block *sb, void *data, int silent) "logging", &smk_logging_ops, S_IRUGO|S_IWUSR}, [SMK_LOAD_SELF] = { "load-self", &smk_load_self_ops, S_IRUGO|S_IWUGO}, + [SMK_ACCESSES] = { + "access", &smk_access_ops, S_IRUGO|S_IWUGO}, /* last one */ {""} }; @@ -1534,6 +1651,20 @@ static int __init init_smk_fs(void) smk_cipso_doi(); smk_unlbl_ambient(NULL); + mutex_init(&smack_known_floor.smk_rules_lock); + mutex_init(&smack_known_hat.smk_rules_lock); + mutex_init(&smack_known_huh.smk_rules_lock); + mutex_init(&smack_known_invalid.smk_rules_lock); + mutex_init(&smack_known_star.smk_rules_lock); + mutex_init(&smack_known_web.smk_rules_lock); + + INIT_LIST_HEAD(&smack_known_floor.smk_rules); + INIT_LIST_HEAD(&smack_known_hat.smk_rules); + INIT_LIST_HEAD(&smack_known_huh.smk_rules); + INIT_LIST_HEAD(&smack_known_invalid.smk_rules); + INIT_LIST_HEAD(&smack_known_star.smk_rules); + INIT_LIST_HEAD(&smack_known_web.smk_rules); + return err; } diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig index 7c7f8c16c10f..8eb779b9d77f 100644 --- a/security/tomoyo/Kconfig +++ b/security/tomoyo/Kconfig @@ -1,8 +1,10 @@ config SECURITY_TOMOYO bool "TOMOYO Linux Support" depends on SECURITY + depends on NET select SECURITYFS select SECURITY_PATH + select SECURITY_NETWORK default n help This selects TOMOYO Linux, pathname-based access control. diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index 95278b71fc21..56a0c7be409e 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -1,4 +1,4 @@ -obj-y = audit.o common.o condition.o domain.o file.o gc.o group.o load_policy.o memory.o mount.o realpath.o securityfs_if.o tomoyo.o util.o +obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o $(obj)/policy/profile.conf: @mkdir -p $(obj)/policy/ @@ -27,7 +27,7 @@ $(obj)/policy/stat.conf: @touch $@ $(obj)/builtin-policy.h: $(obj)/policy/profile.conf $(obj)/policy/exception_policy.conf $(obj)/policy/domain_policy.conf $(obj)/policy/manager.conf $(obj)/policy/stat.conf - @echo Generating built-in policy for TOMOYO 2.4.x. + @echo Generating built-in policy for TOMOYO 2.5.x. @echo "static char tomoyo_builtin_profile[] __initdata =" > $@.tmp @sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/"\1\\n"/' < $(obj)/policy/profile.conf >> $@.tmp @echo "\"\";" >> $@.tmp diff --git a/security/tomoyo/audit.c b/security/tomoyo/audit.c index 5dbb1f7617c0..075c3a6d1649 100644 --- a/security/tomoyo/audit.c +++ b/security/tomoyo/audit.c @@ -313,6 +313,7 @@ static unsigned int tomoyo_log_count; */ static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index, + const struct tomoyo_acl_info *matched_acl, const bool is_granted) { u8 mode; @@ -324,6 +325,9 @@ static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns, p = tomoyo_profile(ns, profile); if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG]) return false; + if (is_granted && matched_acl && matched_acl->cond && + matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO) + return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES; mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[category]; @@ -350,7 +354,8 @@ void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, char *buf; struct tomoyo_log *entry; bool quota_exceeded = false; - if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type, r->granted)) + if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type, + r->matched_acl, r->granted)) goto out; buf = tomoyo_init_log(r, len, fmt, args); if (!buf) diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 2e43aec1c36b..150911c7ff08 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -20,6 +20,7 @@ const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = { /* String table for /sys/kernel/security/tomoyo/profile */ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX] = { + /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = "execute", [TOMOYO_MAC_FILE_OPEN] = "open", [TOMOYO_MAC_FILE_CREATE] = "create", @@ -43,7 +44,28 @@ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX [TOMOYO_MAC_FILE_MOUNT] = "mount", [TOMOYO_MAC_FILE_UMOUNT] = "unmount", [TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root", + /* CONFIG::network group */ + [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind", + [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen", + [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect", + [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind", + [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send", + [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind", + [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send", + [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind", + [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen", + [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect", + [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind", + [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send", + [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind", + [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen", + [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect", + /* CONFIG::misc group */ + [TOMOYO_MAC_ENVIRON] = "env", + /* CONFIG group */ [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file", + [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network", + [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* String table for conditions. */ @@ -130,10 +152,20 @@ const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_UMOUNT] = "unmount", }; +/* String table for socket's operation. */ +const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = { + [TOMOYO_NETWORK_BIND] = "bind", + [TOMOYO_NETWORK_LISTEN] = "listen", + [TOMOYO_NETWORK_CONNECT] = "connect", + [TOMOYO_NETWORK_SEND] = "send", +}; + /* String table for categories. */ static const char * const tomoyo_category_keywords [TOMOYO_MAX_MAC_CATEGORY_INDEX] = { - [TOMOYO_MAC_CATEGORY_FILE] = "file", + [TOMOYO_MAC_CATEGORY_FILE] = "file", + [TOMOYO_MAC_CATEGORY_NETWORK] = "network", + [TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* Permit policy management by non-root user? */ @@ -230,13 +262,17 @@ static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string) WARN_ON(1); } +static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, + ...) __printf(2, 3); + /** * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @fmt: The printf()'s format string, followed by parameters. */ -void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) +static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, + ...) { va_list args; size_t len; @@ -313,7 +349,7 @@ void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns) INIT_LIST_HEAD(&ns->group_list[idx]); for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++) INIT_LIST_HEAD(&ns->policy_list[idx]); - ns->profile_version = 20100903; + ns->profile_version = 20110903; tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list); list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list); } @@ -466,8 +502,10 @@ static struct tomoyo_profile *tomoyo_assign_profile TOMOYO_CONFIG_WANT_REJECT_LOG; memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT, sizeof(ptr->config)); - ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = 1024; - ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = 2048; + ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = + CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG; + ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = + CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY; mb(); /* Avoid out-of-order execution. */ ns->profile_ptr[profile] = ptr; entry = NULL; @@ -951,14 +989,12 @@ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) { struct task_struct *p; rcu_read_lock(); - read_lock(&tasklist_lock); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_real_domain(p); - read_unlock(&tasklist_lock); rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) @@ -982,6 +1018,48 @@ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, } /** + * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry. + * + * @a: Pointer to "struct tomoyo_acl_info". + * @b: Pointer to "struct tomoyo_acl_info". + * + * Returns true if @a == @b, false otherwise. + */ +static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a, + const struct tomoyo_acl_info *b) +{ + const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head); + const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head); + return p1->domainname == p2->domainname; +} + +/** + * tomoyo_write_task - Update task related list. + * + * @param: Pointer to "struct tomoyo_acl_param". + * + * Returns 0 on success, negative value otherwise. + * + * Caller holds tomoyo_read_lock(). + */ +static int tomoyo_write_task(struct tomoyo_acl_param *param) +{ + int error = -EINVAL; + if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) { + struct tomoyo_task_acl e = { + .head.type = TOMOYO_TYPE_MANUAL_TASK_ACL, + .domainname = tomoyo_get_domainname(param), + }; + if (e.domainname) + error = tomoyo_update_domain(&e.head, sizeof(e), param, + tomoyo_same_task_acl, + NULL); + tomoyo_put_name(e.domainname); + } + return error; +} + +/** * tomoyo_delete_domain - Delete a domain. * * @domainname: The name of domain. @@ -1039,11 +1117,16 @@ static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns, static const struct { const char *keyword; int (*write) (struct tomoyo_acl_param *); - } tomoyo_callback[1] = { + } tomoyo_callback[5] = { { "file ", tomoyo_write_file }, + { "network inet ", tomoyo_write_inet_network }, + { "network unix ", tomoyo_write_unix_network }, + { "misc ", tomoyo_write_misc }, + { "task ", tomoyo_write_task }, }; u8 i; - for (i = 0; i < 1; i++) { + + for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) { if (!tomoyo_str_starts(¶m.data, tomoyo_callback[i].keyword)) continue; @@ -1127,6 +1210,10 @@ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, case 0: head->r.cond_index = 0; head->r.cond_step++; + if (cond->transit) { + tomoyo_set_space(head); + tomoyo_set_string(head, cond->transit->name); + } /* fall through */ case 1: { @@ -1239,6 +1326,10 @@ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, head->r.cond_step++; /* fall through */ case 3: + if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) + tomoyo_io_printf(head, " grant_log=%s", + tomoyo_yesno(cond->grant_log == + TOMOYO_GRANTLOG_YES)); tomoyo_set_lf(head); return true; } @@ -1306,6 +1397,12 @@ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, if (first) return true; tomoyo_print_name_union(head, &ptr->name); + } else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) { + struct tomoyo_task_acl *ptr = + container_of(acl, typeof(*ptr), head); + tomoyo_set_group(head, "task "); + tomoyo_set_string(head, "manual_domain_transition "); + tomoyo_set_string(head, ptr->domainname->name); } else if (head->r.print_transition_related_only) { return true; } else if (acl_type == TOMOYO_TYPE_PATH2_ACL) { @@ -1370,6 +1467,60 @@ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, tomoyo_print_number_union(head, &ptr->mode); tomoyo_print_number_union(head, &ptr->major); tomoyo_print_number_union(head, &ptr->minor); + } else if (acl_type == TOMOYO_TYPE_INET_ACL) { + struct tomoyo_inet_acl *ptr = + container_of(acl, typeof(*ptr), head); + const u8 perm = ptr->perm; + + for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { + if (!(perm & (1 << bit))) + continue; + if (first) { + tomoyo_set_group(head, "network inet "); + tomoyo_set_string(head, tomoyo_proto_keyword + [ptr->protocol]); + tomoyo_set_space(head); + first = false; + } else { + tomoyo_set_slash(head); + } + tomoyo_set_string(head, tomoyo_socket_keyword[bit]); + } + if (first) + return true; + tomoyo_set_space(head); + if (ptr->address.group) { + tomoyo_set_string(head, "@"); + tomoyo_set_string(head, ptr->address.group->group_name + ->name); + } else { + char buf[128]; + tomoyo_print_ip(buf, sizeof(buf), &ptr->address); + tomoyo_io_printf(head, "%s", buf); + } + tomoyo_print_number_union(head, &ptr->port); + } else if (acl_type == TOMOYO_TYPE_UNIX_ACL) { + struct tomoyo_unix_acl *ptr = + container_of(acl, typeof(*ptr), head); + const u8 perm = ptr->perm; + + for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { + if (!(perm & (1 << bit))) + continue; + if (first) { + tomoyo_set_group(head, "network unix "); + tomoyo_set_string(head, tomoyo_proto_keyword + [ptr->protocol]); + tomoyo_set_space(head); + first = false; + } else { + tomoyo_set_slash(head); + } + tomoyo_set_string(head, tomoyo_socket_keyword[bit]); + } + if (first) + return true; + tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) { struct tomoyo_mount_acl *ptr = container_of(acl, typeof(*ptr), head); @@ -1378,6 +1529,12 @@ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, tomoyo_print_name_union(head, &ptr->dir_name); tomoyo_print_name_union(head, &ptr->fs_type); tomoyo_print_number_union(head, &ptr->flags); + } else if (acl_type == TOMOYO_TYPE_ENV_ACL) { + struct tomoyo_env_acl *ptr = + container_of(acl, typeof(*ptr), head); + + tomoyo_set_group(head, "misc env "); + tomoyo_set_string(head, ptr->env->name); } if (acl->cond) { head->r.print_cond_part = true; @@ -1510,14 +1667,12 @@ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) global_pid = true; pid = (unsigned int) simple_strtoul(buf, NULL, 10); rcu_read_lock(); - read_lock(&tasklist_lock); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_real_domain(p); - read_unlock(&tasklist_lock); rcu_read_unlock(); if (!domain) return; @@ -1537,8 +1692,9 @@ static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = { /* String table for grouping keywords. */ static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = { - [TOMOYO_PATH_GROUP] = "path_group ", - [TOMOYO_NUMBER_GROUP] = "number_group ", + [TOMOYO_PATH_GROUP] = "path_group ", + [TOMOYO_NUMBER_GROUP] = "number_group ", + [TOMOYO_ADDRESS_GROUP] = "address_group ", }; /** @@ -1580,7 +1736,7 @@ static int tomoyo_write_exception(struct tomoyo_io_buffer *head) } /** - * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group" list. + * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. @@ -1617,6 +1773,15 @@ static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx) (ptr, struct tomoyo_number_group, head)->number); + } else if (idx == TOMOYO_ADDRESS_GROUP) { + char buffer[128]; + + struct tomoyo_address_group *member = + container_of(ptr, typeof(*member), + head); + tomoyo_print_ip(buffer, sizeof(buffer), + &member->address); + tomoyo_io_printf(head, " %s", buffer); } tomoyo_set_lf(head); } @@ -2066,27 +2231,7 @@ static int tomoyo_write_answer(struct tomoyo_io_buffer *head) static void tomoyo_read_version(struct tomoyo_io_buffer *head) { if (!head->r.eof) { - tomoyo_io_printf(head, "2.4.0"); - head->r.eof = true; - } -} - -/** - * tomoyo_read_self_domain - Get the current process's domainname. - * - * @head: Pointer to "struct tomoyo_io_buffer". - * - * Returns the current process's domainname. - */ -static void tomoyo_read_self_domain(struct tomoyo_io_buffer *head) -{ - if (!head->r.eof) { - /* - * tomoyo_domain()->domainname != NULL - * because every process belongs to a domain and - * the domain's name cannot be NULL. - */ - tomoyo_io_printf(head, "%s", tomoyo_domain()->domainname->name); + tomoyo_io_printf(head, "2.5.0"); head->r.eof = true; } } @@ -2221,10 +2366,6 @@ int tomoyo_open_control(const u8 type, struct file *file) head->poll = tomoyo_poll_log; head->read = tomoyo_read_log; break; - case TOMOYO_SELFDOMAIN: - /* /sys/kernel/security/tomoyo/self_domain */ - head->read = tomoyo_read_self_domain; - break; case TOMOYO_PROCESS_STATUS: /* /sys/kernel/security/tomoyo/.process_status */ head->write = tomoyo_write_pid; @@ -2453,6 +2594,7 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, return -EFAULT; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; + head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ while (avail_len > 0) { @@ -2562,11 +2704,11 @@ void tomoyo_check_profile(void) struct tomoyo_domain_info *domain; const int idx = tomoyo_read_lock(); tomoyo_policy_loaded = true; - printk(KERN_INFO "TOMOYO: 2.4.0\n"); + printk(KERN_INFO "TOMOYO: 2.5.0\n"); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { const u8 profile = domain->profile; const struct tomoyo_policy_namespace *ns = domain->ns; - if (ns->profile_version != 20100903) + if (ns->profile_version != 20110903) printk(KERN_ERR "Profile version %u is not supported.\n", ns->profile_version); @@ -2577,9 +2719,9 @@ void tomoyo_check_profile(void) else continue; printk(KERN_ERR - "Userland tools for TOMOYO 2.4 must be installed and " + "Userland tools for TOMOYO 2.5 must be installed and " "policy must be initialized.\n"); - printk(KERN_ERR "Please see http://tomoyo.sourceforge.jp/2.4/ " + printk(KERN_ERR "Please see http://tomoyo.sourceforge.jp/2.5/ " "for more information.\n"); panic("STOP!"); } diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index f7fbaa66e443..ed311d7a8ce0 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -3,7 +3,7 @@ * * Header file for TOMOYO. * - * Copyright (C) 2005-2010 NTT DATA CORPORATION + * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H @@ -23,6 +23,16 @@ #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> +#include <linux/net.h> +#include <linux/inet.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/un.h> +#include <net/sock.h> +#include <net/af_unix.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/udp.h> /********** Constants definitions. **********/ @@ -34,8 +44,17 @@ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) +/* + * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. + * Therefore, we don't need SOCK_MAX. + */ +#define TOMOYO_SOCK_MAX 6 + #define TOMOYO_EXEC_TMPSIZE 4096 +/* Garbage collector is trying to kfree() this element. */ +#define TOMOYO_GC_IN_PROGRESS -1 + /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 @@ -136,6 +155,7 @@ enum tomoyo_mode_index { /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, + TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, @@ -162,10 +182,21 @@ enum tomoyo_domain_info_flags_index { TOMOYO_MAX_DOMAIN_INFO_FLAGS }; +/* Index numbers for audit type. */ +enum tomoyo_grant_log { + /* Follow profile's configuration. */ + TOMOYO_GRANTLOG_AUTO, + /* Do not generate grant log. */ + TOMOYO_GRANTLOG_NO, + /* Generate grant_log. */ + TOMOYO_GRANTLOG_YES, +}; + /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, + TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; @@ -196,6 +227,10 @@ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, + TOMOYO_TYPE_INET_ACL, + TOMOYO_TYPE_UNIX_ACL, + TOMOYO_TYPE_ENV_ACL, + TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ @@ -228,6 +263,15 @@ enum tomoyo_mkdev_acl_index { TOMOYO_MAX_MKDEV_OPERATION }; +/* Index numbers for socket operations. */ +enum tomoyo_network_acl_index { + TOMOYO_NETWORK_BIND, /* bind() operation. */ + TOMOYO_NETWORK_LISTEN, /* listen() operation. */ + TOMOYO_NETWORK_CONNECT, /* connect() operation. */ + TOMOYO_NETWORK_SEND, /* send() operation. */ + TOMOYO_MAX_NETWORK_OPERATION +}; + /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, @@ -255,7 +299,6 @@ enum tomoyo_securityfs_interface_index { TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, - TOMOYO_SELFDOMAIN, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, @@ -300,12 +343,30 @@ enum tomoyo_mac_index { TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, + TOMOYO_MAC_NETWORK_INET_STREAM_BIND, + TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, + TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, + TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, + TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, + TOMOYO_MAC_NETWORK_INET_RAW_BIND, + TOMOYO_MAC_NETWORK_INET_RAW_SEND, + TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, + TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, + TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, + TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, + TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, + TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, + TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, + TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, + TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, + TOMOYO_MAC_CATEGORY_NETWORK, + TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; @@ -340,7 +401,7 @@ enum tomoyo_pref_index { /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; - bool is_deleted; + s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ @@ -397,13 +458,36 @@ struct tomoyo_request_info { u8 operation; } path_number; struct { + const struct tomoyo_path_info *name; + } environ; + struct { + const __be32 *address; + u16 port; + /* One of values smaller than TOMOYO_SOCK_MAX. */ + u8 protocol; + /* One of values in "enum tomoyo_network_acl_index". */ + u8 operation; + bool is_ipv6; + } inet_network; + struct { + const struct tomoyo_path_info *address; + /* One of values smaller than TOMOYO_SOCK_MAX. */ + u8 protocol; + /* One of values in "enum tomoyo_network_acl_index". */ + u8 operation; + } unix_network; + struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; + struct { + const struct tomoyo_path_info *domainname; + } task; } param; + struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; @@ -442,7 +526,14 @@ struct tomoyo_number_union { u8 value_type[2]; }; -/* Structure for "path_group"/"number_group" directive. */ +/* Structure for holding an IP address. */ +struct tomoyo_ipaddr_union { + struct in6_addr ip[2]; /* Big endian. */ + struct tomoyo_group *group; /* Pointer to address group. */ + bool is_ipv6; /* Valid only if @group == NULL. */ +}; + +/* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; @@ -461,6 +552,13 @@ struct tomoyo_number_group { struct tomoyo_number_union number; }; +/* Structure for "address_group" directive. */ +struct tomoyo_address_group { + struct tomoyo_acl_head head; + /* Structure for holding an IP address. */ + struct tomoyo_ipaddr_union address; +}; + /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { uid_t uid; @@ -520,6 +618,7 @@ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; + const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ @@ -554,6 +653,8 @@ struct tomoyo_condition { u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ + u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ + const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; @@ -567,7 +668,7 @@ struct tomoyo_condition { struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ - bool is_deleted; + s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; @@ -587,6 +688,15 @@ struct tomoyo_domain_info { }; /* + * Structure for "task manual_domain_transition" directive. + */ +struct tomoyo_task_acl { + struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ + /* Pointer to domainname. */ + const struct tomoyo_path_info *domainname; +}; + +/* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. @@ -638,6 +748,29 @@ struct tomoyo_mount_acl { struct tomoyo_number_union flags; }; +/* Structure for "misc env" directive in domain policy. */ +struct tomoyo_env_acl { + struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ + const struct tomoyo_path_info *env; /* environment variable */ +}; + +/* Structure for "network inet" directive. */ +struct tomoyo_inet_acl { + struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ + u8 protocol; + u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ + struct tomoyo_ipaddr_union address; + struct tomoyo_number_union port; +}; + +/* Structure for "network unix" directive. */ +struct tomoyo_unix_acl { + struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ + u8 protocol; + u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ + struct tomoyo_name_union name; +}; + /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; @@ -773,7 +906,7 @@ struct tomoyo_policy_namespace { struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; - /* Profile version. Currently only 20100903 is defined. */ + /* Profile version. Currently only 20110903 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; @@ -781,6 +914,8 @@ struct tomoyo_policy_namespace { /********** Function prototypes. **********/ +bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, + const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, @@ -796,6 +931,8 @@ bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); +bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, + struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, @@ -805,6 +942,7 @@ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); +char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args); char *tomoyo_read_token(struct tomoyo_acl_param *param); @@ -814,12 +952,17 @@ const char *tomoyo_get_exe(void); const char *tomoyo_yesno(const unsigned int value); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); +const struct tomoyo_path_info *tomoyo_get_domainname +(struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, struct path *path, const int flag); int tomoyo_close_control(struct tomoyo_io_buffer *head); +int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env); +int tomoyo_execute_permission(struct tomoyo_request_info *r, + const struct tomoyo_path_info *filename); int tomoyo_find_next_domain(struct linux_binprm *bprm); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); @@ -838,10 +981,15 @@ int tomoyo_path_number_perm(const u8 operation, struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, struct path *path, const char *target); -int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, - const struct tomoyo_path_info *filename); int tomoyo_poll_control(struct file *file, poll_table *wait); int tomoyo_poll_log(struct file *file, poll_table *wait); +int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, + int addr_len); +int tomoyo_socket_connect_permission(struct socket *sock, + struct sockaddr *addr, int addr_len); +int tomoyo_socket_listen_permission(struct socket *sock); +int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, + int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, @@ -860,8 +1008,11 @@ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); +int tomoyo_write_misc(struct tomoyo_acl_param *param); +int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); +int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, @@ -891,12 +1042,11 @@ void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); -void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) - __printf(2, 3); void tomoyo_load_policy(const char *filename); -void tomoyo_memory_free(void *ptr); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); +void tomoyo_print_ip(char *buf, const unsigned int size, + const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); @@ -919,6 +1069,8 @@ extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; +extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; +extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; @@ -1098,6 +1250,21 @@ static inline bool tomoyo_same_number_union } /** + * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. + * + * @a: Pointer to "struct tomoyo_ipaddr_union". + * @b: Pointer to "struct tomoyo_ipaddr_union". + * + * Returns true if @a == @b, false otherwise. + */ +static inline bool tomoyo_same_ipaddr_union +(const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) +{ + return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && + a->is_ipv6 == b->is_ipv6; +} + +/** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. diff --git a/security/tomoyo/condition.c b/security/tomoyo/condition.c index 8a05f71eaf67..986330b8c73e 100644 --- a/security/tomoyo/condition.c +++ b/security/tomoyo/condition.c @@ -348,6 +348,7 @@ static inline bool tomoyo_same_condition(const struct tomoyo_condition *a, a->numbers_count == b->numbers_count && a->names_count == b->names_count && a->argc == b->argc && a->envc == b->envc && + a->grant_log == b->grant_log && a->transit == b->transit && !memcmp(a + 1, b + 1, a->size - sizeof(*a)); } @@ -399,8 +400,9 @@ static struct tomoyo_condition *tomoyo_commit_condition found = true; goto out; } - list_for_each_entry_rcu(ptr, &tomoyo_condition_list, head.list) { - if (!tomoyo_same_condition(ptr, entry)) + list_for_each_entry(ptr, &tomoyo_condition_list, head.list) { + if (!tomoyo_same_condition(ptr, entry) || + atomic_read(&ptr->head.users) == TOMOYO_GC_IN_PROGRESS) continue; /* Same entry found. Share this entry. */ atomic_inc(&ptr->head.users); @@ -410,8 +412,7 @@ static struct tomoyo_condition *tomoyo_commit_condition if (!found) { if (tomoyo_memory_ok(entry)) { atomic_set(&entry->head.users, 1); - list_add_rcu(&entry->head.list, - &tomoyo_condition_list); + list_add(&entry->head.list, &tomoyo_condition_list); } else { found = true; ptr = NULL; @@ -428,6 +429,46 @@ out: } /** + * tomoyo_get_transit_preference - Parse domain transition preference for execve(). + * + * @param: Pointer to "struct tomoyo_acl_param". + * @e: Pointer to "struct tomoyo_condition". + * + * Returns the condition string part. + */ +static char *tomoyo_get_transit_preference(struct tomoyo_acl_param *param, + struct tomoyo_condition *e) +{ + char * const pos = param->data; + bool flag; + if (*pos == '<') { + e->transit = tomoyo_get_domainname(param); + goto done; + } + { + char *cp = strchr(pos, ' '); + if (cp) + *cp = '\0'; + flag = tomoyo_correct_path(pos) || !strcmp(pos, "keep") || + !strcmp(pos, "initialize") || !strcmp(pos, "reset") || + !strcmp(pos, "child") || !strcmp(pos, "parent"); + if (cp) + *cp = ' '; + } + if (!flag) + return pos; + e->transit = tomoyo_get_name(tomoyo_read_token(param)); +done: + if (e->transit) + return param->data; + /* + * Return a bad read-only condition string that will let + * tomoyo_get_condition() return NULL. + */ + return "/"; +} + +/** * tomoyo_get_condition - Parse condition part. * * @param: Pointer to "struct tomoyo_acl_param". @@ -443,7 +484,8 @@ struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param) struct tomoyo_argv *argv = NULL; struct tomoyo_envp *envp = NULL; struct tomoyo_condition e = { }; - char * const start_of_string = param->data; + char * const start_of_string = + tomoyo_get_transit_preference(param, &e); char * const end_of_string = start_of_string + strlen(start_of_string); char *pos; rerun: @@ -486,6 +528,20 @@ rerun: goto out; dprintk(KERN_WARNING "%u: <%s>%s=<%s>\n", __LINE__, left_word, is_not ? "!" : "", right_word); + if (!strcmp(left_word, "grant_log")) { + if (entry) { + if (is_not || + entry->grant_log != TOMOYO_GRANTLOG_AUTO) + goto out; + else if (!strcmp(right_word, "yes")) + entry->grant_log = TOMOYO_GRANTLOG_YES; + else if (!strcmp(right_word, "no")) + entry->grant_log = TOMOYO_GRANTLOG_NO; + else + goto out; + } + continue; + } if (!strncmp(left_word, "exec.argv[", 10)) { if (!argv) { e.argc++; @@ -593,8 +649,9 @@ store_value: + e.envc * sizeof(struct tomoyo_envp); entry = kzalloc(e.size, GFP_NOFS); if (!entry) - return NULL; + goto out2; *entry = e; + e.transit = NULL; condp = (struct tomoyo_condition_element *) (entry + 1); numbers_p = (struct tomoyo_number_union *) (condp + e.condc); names_p = (struct tomoyo_name_union *) (numbers_p + e.numbers_count); @@ -621,6 +678,8 @@ out: tomoyo_del_condition(&entry->head.list); kfree(entry); } +out2: + tomoyo_put_name(e.transit); return NULL; } diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index cd0f92d88bb4..9027ac1534af 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -39,6 +39,8 @@ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list) { + if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) + continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; @@ -102,10 +104,21 @@ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; + /* + * Domain transition preference is allowed for only + * "file execute" entries. + */ + if (new_entry->cond->transit && + !(new_entry->type == TOMOYO_TYPE_PATH_ACL && + container_of(new_entry, struct tomoyo_path_acl, head) + ->perm == 1 << TOMOYO_TYPE_EXECUTE)) + goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list) { + if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) + continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; @@ -157,6 +170,7 @@ retry: continue; if (!tomoyo_condition(r, ptr->cond)) continue; + r->matched_acl = ptr; r->granted = true; return; } @@ -501,7 +515,8 @@ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ - if (!entry->ns->profile_ptr[entry->profile]) + if (tomoyo_policy_loaded && + !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; @@ -557,12 +572,99 @@ out: tomoyo_write_log(&r, "use_profile %u\n", entry->profile); tomoyo_write_log(&r, "use_group %u\n", entry->group); + tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** + * tomoyo_environ - Check permission for environment variable names. + * + * @ee: Pointer to "struct tomoyo_execve". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_environ(struct tomoyo_execve *ee) +{ + struct tomoyo_request_info *r = &ee->r; + struct linux_binprm *bprm = ee->bprm; + /* env_page.data is allocated by tomoyo_dump_page(). */ + struct tomoyo_page_dump env_page = { }; + char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ + int arg_len = 0; + unsigned long pos = bprm->p; + int offset = pos % PAGE_SIZE; + int argv_count = bprm->argc; + int envp_count = bprm->envc; + int error = -ENOMEM; + + ee->r.type = TOMOYO_MAC_ENVIRON; + ee->r.profile = r->domain->profile; + ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, + TOMOYO_MAC_ENVIRON); + if (!r->mode || !envp_count) + return 0; + arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); + if (!arg_ptr) + goto out; + while (error == -ENOMEM) { + if (!tomoyo_dump_page(bprm, pos, &env_page)) + goto out; + pos += PAGE_SIZE - offset; + /* Read. */ + while (argv_count && offset < PAGE_SIZE) { + if (!env_page.data[offset++]) + argv_count--; + } + if (argv_count) { + offset = 0; + continue; + } + while (offset < PAGE_SIZE) { + const unsigned char c = env_page.data[offset++]; + + if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { + if (c == '=') { + arg_ptr[arg_len++] = '\0'; + } else if (c == '\\') { + arg_ptr[arg_len++] = '\\'; + arg_ptr[arg_len++] = '\\'; + } else if (c > ' ' && c < 127) { + arg_ptr[arg_len++] = c; + } else { + arg_ptr[arg_len++] = '\\'; + arg_ptr[arg_len++] = (c >> 6) + '0'; + arg_ptr[arg_len++] + = ((c >> 3) & 7) + '0'; + arg_ptr[arg_len++] = (c & 7) + '0'; + } + } else { + arg_ptr[arg_len] = '\0'; + } + if (c) + continue; + if (tomoyo_env_perm(r, arg_ptr)) { + error = -EPERM; + break; + } + if (!--envp_count) { + error = 0; + break; + } + arg_len = 0; + } + offset = 0; + } +out: + if (r->mode != TOMOYO_CONFIG_ENFORCING) + error = 0; + kfree(env_page.data); + kfree(arg_ptr); + return error; +} + +/** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". @@ -577,10 +679,11 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; - bool need_kfree = false; bool reject_on_transition_failure = false; - struct tomoyo_path_info rn = { }; /* real name */ + const struct tomoyo_path_info *candidate; + struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc(sizeof(*ee), GFP_NOFS); + if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); @@ -594,40 +697,32 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; - retry: - if (need_kfree) { - kfree(rn.name); - need_kfree = false; - } /* Get symlink's pathname of program. */ retval = -ENOENT; - rn.name = tomoyo_realpath_nofollow(original_name); - if (!rn.name) + exename.name = tomoyo_realpath_nofollow(original_name); + if (!exename.name) goto out; - tomoyo_fill_path_info(&rn); - need_kfree = true; - + tomoyo_fill_path_info(&exename); +retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ + candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list) { if (ptr->head.is_deleted || - !tomoyo_path_matches_pattern(&rn, + !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; - kfree(rn.name); - need_kfree = false; - /* This is OK because it is read only. */ - rn = *ptr->aggregated_name; + candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ - retval = tomoyo_path_permission(&ee->r, TOMOYO_TYPE_EXECUTE, &rn); + retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) @@ -638,20 +733,51 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ - if (ee->r.param.path.matched_path) { - if (need_kfree) - kfree(rn.name); - need_kfree = false; - /* This is OK because it is read only. */ - rn = *ee->r.param.path.matched_path; - } + if (ee->r.param.path.matched_path) + candidate = ee->r.param.path.matched_path; - /* Calculate domain to transit to. */ + /* + * Check for domain transition preference if "file execute" matched. + * If preference is given, make do_execve() fail if domain transition + * has failed, for domain transition preference should be used with + * destination domain defined. + */ + if (ee->transition) { + const char *domainname = ee->transition->name; + reject_on_transition_failure = true; + if (!strcmp(domainname, "keep")) + goto force_keep_domain; + if (!strcmp(domainname, "child")) + goto force_child_domain; + if (!strcmp(domainname, "reset")) + goto force_reset_domain; + if (!strcmp(domainname, "initialize")) + goto force_initialize_domain; + if (!strcmp(domainname, "parent")) { + char *cp; + strncpy(ee->tmp, old_domain->domainname->name, + TOMOYO_EXEC_TMPSIZE - 1); + cp = strrchr(ee->tmp, ' '); + if (cp) + *cp = '\0'; + } else if (*domainname == '<') + strncpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE - 1); + else + snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", + old_domain->domainname->name, domainname); + goto force_jump_domain; + } + /* + * No domain transition preference specified. + * Calculate domain to transit to. + */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, - &rn)) { + candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: +force_reset_domain: /* Transit to the root of specified namespace. */ - snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", rn.name); + snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", + candidate->name); /* * Make do_execve() fail if domain transition across namespaces * has failed. @@ -659,11 +785,13 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: +force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", - old_domain->ns->name, rn.name); + old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: +force_keep_domain: /* Keep current domain. */ domain = old_domain; break; @@ -677,13 +805,15 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) * before /sbin/init. */ domain = old_domain; - } else { - /* Normal domain transition. */ - snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", - old_domain->domainname->name, rn.name); + break; } +force_child_domain: + /* Normal domain transition. */ + snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", + old_domain->domainname->name, candidate->name); break; } +force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) @@ -711,8 +841,11 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) /* Update reference count on "struct tomoyo_domain_info". */ atomic_inc(&domain->users); bprm->cred->security = domain; - if (need_kfree) - kfree(rn.name); + kfree(exename.name); + if (!retval) { + ee->r.domain = domain; + retval = tomoyo_environ(ee); + } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); @@ -732,7 +865,8 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; - /* dump->data is released by tomoyo_finish_execve(). */ + + /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) @@ -753,6 +887,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, * So do I. */ char *kaddr = kmap_atomic(page, KM_USER0); + dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); diff --git a/security/tomoyo/environ.c b/security/tomoyo/environ.c new file mode 100644 index 000000000000..ad4c6e18a437 --- /dev/null +++ b/security/tomoyo/environ.c @@ -0,0 +1,122 @@ +/* + * security/tomoyo/environ.c + * + * Copyright (C) 2005-2011 NTT DATA CORPORATION + */ + +#include "common.h" + +/** + * tomoyo_check_env_acl - Check permission for environment variable's name. + * + * @r: Pointer to "struct tomoyo_request_info". + * @ptr: Pointer to "struct tomoyo_acl_info". + * + * Returns true if granted, false otherwise. + */ +static bool tomoyo_check_env_acl(struct tomoyo_request_info *r, + const struct tomoyo_acl_info *ptr) +{ + const struct tomoyo_env_acl *acl = + container_of(ptr, typeof(*acl), head); + + return tomoyo_path_matches_pattern(r->param.environ.name, acl->env); +} + +/** + * tomoyo_audit_env_log - Audit environment variable name log. + * + * @r: Pointer to "struct tomoyo_request_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_audit_env_log(struct tomoyo_request_info *r) +{ + return tomoyo_supervisor(r, "misc env %s\n", + r->param.environ.name->name); +} + +/** + * tomoyo_env_perm - Check permission for environment variable's name. + * + * @r: Pointer to "struct tomoyo_request_info". + * @env: The name of environment variable. + * + * Returns 0 on success, negative value otherwise. + * + * Caller holds tomoyo_read_lock(). + */ +int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env) +{ + struct tomoyo_path_info environ; + int error; + + if (!env || !*env) + return 0; + environ.name = env; + tomoyo_fill_path_info(&environ); + r->param_type = TOMOYO_TYPE_ENV_ACL; + r->param.environ.name = &environ; + do { + tomoyo_check_acl(r, tomoyo_check_env_acl); + error = tomoyo_audit_env_log(r); + } while (error == TOMOYO_RETRY_REQUEST); + return error; +} + +/** + * tomoyo_same_env_acl - Check for duplicated "struct tomoyo_env_acl" entry. + * + * @a: Pointer to "struct tomoyo_acl_info". + * @b: Pointer to "struct tomoyo_acl_info". + * + * Returns true if @a == @b, false otherwise. + */ +static bool tomoyo_same_env_acl(const struct tomoyo_acl_info *a, + const struct tomoyo_acl_info *b) +{ + const struct tomoyo_env_acl *p1 = container_of(a, typeof(*p1), head); + const struct tomoyo_env_acl *p2 = container_of(b, typeof(*p2), head); + + return p1->env == p2->env; +} + +/** + * tomoyo_write_env - Write "struct tomoyo_env_acl" list. + * + * @param: Pointer to "struct tomoyo_acl_param". + * + * Returns 0 on success, negative value otherwise. + * + * Caller holds tomoyo_read_lock(). + */ +static int tomoyo_write_env(struct tomoyo_acl_param *param) +{ + struct tomoyo_env_acl e = { .head.type = TOMOYO_TYPE_ENV_ACL }; + int error = -ENOMEM; + const char *data = tomoyo_read_token(param); + + if (!tomoyo_correct_word(data) || strchr(data, '=')) + return -EINVAL; + e.env = tomoyo_get_name(data); + if (!e.env) + return error; + error = tomoyo_update_domain(&e.head, sizeof(e), param, + tomoyo_same_env_acl, NULL); + tomoyo_put_name(e.env); + return error; +} + +/** + * tomoyo_write_misc - Update environment variable list. + * + * @param: Pointer to "struct tomoyo_acl_param". + * + * Returns 0 on success, negative value otherwise. + */ +int tomoyo_write_misc(struct tomoyo_acl_param *param) +{ + if (tomoyo_str_starts(¶m->data, "env ")) + return tomoyo_write_env(param); + return -EINVAL; +} diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c index 743c35f5084a..400390790745 100644 --- a/security/tomoyo/file.c +++ b/security/tomoyo/file.c @@ -555,8 +555,8 @@ static int tomoyo_update_path2_acl(const u8 perm, * * Caller holds tomoyo_read_lock(). */ -int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, - const struct tomoyo_path_info *filename) +static int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, + const struct tomoyo_path_info *filename) { int error; @@ -570,16 +570,42 @@ int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, do { tomoyo_check_acl(r, tomoyo_check_path_acl); error = tomoyo_audit_path_log(r); - /* - * Do not retry for execute request, for alias may have - * changed. - */ - } while (error == TOMOYO_RETRY_REQUEST && - operation != TOMOYO_TYPE_EXECUTE); + } while (error == TOMOYO_RETRY_REQUEST); return error; } /** + * tomoyo_execute_permission - Check permission for execute operation. + * + * @r: Pointer to "struct tomoyo_request_info". + * @filename: Filename to check. + * + * Returns 0 on success, negative value otherwise. + * + * Caller holds tomoyo_read_lock(). + */ +int tomoyo_execute_permission(struct tomoyo_request_info *r, + const struct tomoyo_path_info *filename) +{ + /* + * Unlike other permission checks, this check is done regardless of + * profile mode settings in order to check for domain transition + * preference. + */ + r->type = TOMOYO_MAC_FILE_EXECUTE; + r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); + r->param_type = TOMOYO_TYPE_PATH_ACL; + r->param.path.filename = filename; + r->param.path.operation = TOMOYO_TYPE_EXECUTE; + tomoyo_check_acl(r, tomoyo_check_path_acl); + r->ee->transition = r->matched_acl && r->matched_acl->cond ? + r->matched_acl->cond->transit : NULL; + if (r->mode != TOMOYO_CONFIG_DISABLED) + return tomoyo_audit_path_log(r); + return 0; +} + +/** * tomoyo_same_path_number_acl - Check for duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". diff --git a/security/tomoyo/gc.c b/security/tomoyo/gc.c index ae135fbbbe95..986a6a756868 100644 --- a/security/tomoyo/gc.c +++ b/security/tomoyo/gc.c @@ -8,36 +8,26 @@ #include <linux/kthread.h> #include <linux/slab.h> +/** + * tomoyo_memory_free - Free memory for elements. + * + * @ptr: Pointer to allocated memory. + * + * Returns nothing. + * + * Caller holds tomoyo_policy_lock mutex. + */ +static inline void tomoyo_memory_free(void *ptr) +{ + tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= ksize(ptr); + kfree(ptr); +} + /* The list for "struct tomoyo_io_buffer". */ static LIST_HEAD(tomoyo_io_buffer_list); /* Lock for protecting tomoyo_io_buffer_list. */ static DEFINE_SPINLOCK(tomoyo_io_buffer_list_lock); -/* Size of an element. */ -static const u8 tomoyo_element_size[TOMOYO_MAX_POLICY] = { - [TOMOYO_ID_GROUP] = sizeof(struct tomoyo_group), - [TOMOYO_ID_PATH_GROUP] = sizeof(struct tomoyo_path_group), - [TOMOYO_ID_NUMBER_GROUP] = sizeof(struct tomoyo_number_group), - [TOMOYO_ID_AGGREGATOR] = sizeof(struct tomoyo_aggregator), - [TOMOYO_ID_TRANSITION_CONTROL] = - sizeof(struct tomoyo_transition_control), - [TOMOYO_ID_MANAGER] = sizeof(struct tomoyo_manager), - /* [TOMOYO_ID_CONDITION] = "struct tomoyo_condition"->size, */ - /* [TOMOYO_ID_NAME] = "struct tomoyo_name"->size, */ - /* [TOMOYO_ID_ACL] = - tomoyo_acl_size["struct tomoyo_acl_info"->type], */ - [TOMOYO_ID_DOMAIN] = sizeof(struct tomoyo_domain_info), -}; - -/* Size of a domain ACL element. */ -static const u8 tomoyo_acl_size[] = { - [TOMOYO_TYPE_PATH_ACL] = sizeof(struct tomoyo_path_acl), - [TOMOYO_TYPE_PATH2_ACL] = sizeof(struct tomoyo_path2_acl), - [TOMOYO_TYPE_PATH_NUMBER_ACL] = sizeof(struct tomoyo_path_number_acl), - [TOMOYO_TYPE_MKDEV_ACL] = sizeof(struct tomoyo_mkdev_acl), - [TOMOYO_TYPE_MOUNT_ACL] = sizeof(struct tomoyo_mount_acl), -}; - /** * tomoyo_struct_used_by_io_buffer - Check whether the list element is used by /sys/kernel/security/tomoyo/ users or not. * @@ -55,15 +45,11 @@ static bool tomoyo_struct_used_by_io_buffer(const struct list_head *element) list_for_each_entry(head, &tomoyo_io_buffer_list, list) { head->users++; spin_unlock(&tomoyo_io_buffer_list_lock); - if (mutex_lock_interruptible(&head->io_sem)) { - in_use = true; - goto out; - } + mutex_lock(&head->io_sem); if (head->r.domain == element || head->r.group == element || head->r.acl == element || &head->w.domain->list == element) in_use = true; mutex_unlock(&head->io_sem); -out: spin_lock(&tomoyo_io_buffer_list_lock); head->users--; if (in_use) @@ -77,15 +63,14 @@ out: * tomoyo_name_used_by_io_buffer - Check whether the string is used by /sys/kernel/security/tomoyo/ users or not. * * @string: String to check. - * @size: Memory allocated for @string . * * Returns true if @string is used by /sys/kernel/security/tomoyo/ users, * false otherwise. */ -static bool tomoyo_name_used_by_io_buffer(const char *string, - const size_t size) +static bool tomoyo_name_used_by_io_buffer(const char *string) { struct tomoyo_io_buffer *head; + const size_t size = strlen(string) + 1; bool in_use = false; spin_lock(&tomoyo_io_buffer_list_lock); @@ -93,10 +78,7 @@ static bool tomoyo_name_used_by_io_buffer(const char *string, int i; head->users++; spin_unlock(&tomoyo_io_buffer_list_lock); - if (mutex_lock_interruptible(&head->io_sem)) { - in_use = true; - goto out; - } + mutex_lock(&head->io_sem); for (i = 0; i < TOMOYO_MAX_IO_READ_QUEUE; i++) { const char *w = head->r.w[i]; if (w < string || w > string + size) @@ -105,7 +87,6 @@ static bool tomoyo_name_used_by_io_buffer(const char *string, break; } mutex_unlock(&head->io_sem); -out: spin_lock(&tomoyo_io_buffer_list_lock); head->users--; if (in_use) @@ -115,84 +96,6 @@ out: return in_use; } -/* Structure for garbage collection. */ -struct tomoyo_gc { - struct list_head list; - enum tomoyo_policy_id type; - size_t size; - struct list_head *element; -}; -/* List of entries to be deleted. */ -static LIST_HEAD(tomoyo_gc_list); -/* Length of tomoyo_gc_list. */ -static int tomoyo_gc_list_len; - -/** - * tomoyo_add_to_gc - Add an entry to to be deleted list. - * - * @type: One of values in "enum tomoyo_policy_id". - * @element: Pointer to "struct list_head". - * - * Returns true on success, false otherwise. - * - * Caller holds tomoyo_policy_lock mutex. - * - * Adding an entry needs kmalloc(). Thus, if we try to add thousands of - * entries at once, it will take too long time. Thus, do not add more than 128 - * entries per a scan. But to be able to handle worst case where all entries - * are in-use, we accept one more entry per a scan. - * - * If we use singly linked list using "struct list_head"->prev (which is - * LIST_POISON2), we can avoid kmalloc(). - */ -static bool tomoyo_add_to_gc(const int type, struct list_head *element) -{ - struct tomoyo_gc *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); - if (!entry) - return false; - entry->type = type; - if (type == TOMOYO_ID_ACL) - entry->size = tomoyo_acl_size[ - container_of(element, - typeof(struct tomoyo_acl_info), - list)->type]; - else if (type == TOMOYO_ID_NAME) - entry->size = strlen(container_of(element, - typeof(struct tomoyo_name), - head.list)->entry.name) + 1; - else if (type == TOMOYO_ID_CONDITION) - entry->size = - container_of(element, typeof(struct tomoyo_condition), - head.list)->size; - else - entry->size = tomoyo_element_size[type]; - entry->element = element; - list_add(&entry->list, &tomoyo_gc_list); - list_del_rcu(element); - return tomoyo_gc_list_len++ < 128; -} - -/** - * tomoyo_element_linked_by_gc - Validate next element of an entry. - * - * @element: Pointer to an element. - * @size: Size of @element in byte. - * - * Returns true if @element is linked by other elements in the garbage - * collector's queue, false otherwise. - */ -static bool tomoyo_element_linked_by_gc(const u8 *element, const size_t size) -{ - struct tomoyo_gc *p; - list_for_each_entry(p, &tomoyo_gc_list, list) { - const u8 *ptr = (const u8 *) p->element->next; - if (ptr < element || element + size < ptr) - continue; - return true; - } - return false; -} - /** * tomoyo_del_transition_control - Delete members in "struct tomoyo_transition_control". * @@ -200,7 +103,7 @@ static bool tomoyo_element_linked_by_gc(const u8 *element, const size_t size) * * Returns nothing. */ -static void tomoyo_del_transition_control(struct list_head *element) +static inline void tomoyo_del_transition_control(struct list_head *element) { struct tomoyo_transition_control *ptr = container_of(element, typeof(*ptr), head.list); @@ -215,7 +118,7 @@ static void tomoyo_del_transition_control(struct list_head *element) * * Returns nothing. */ -static void tomoyo_del_aggregator(struct list_head *element) +static inline void tomoyo_del_aggregator(struct list_head *element) { struct tomoyo_aggregator *ptr = container_of(element, typeof(*ptr), head.list); @@ -230,7 +133,7 @@ static void tomoyo_del_aggregator(struct list_head *element) * * Returns nothing. */ -static void tomoyo_del_manager(struct list_head *element) +static inline void tomoyo_del_manager(struct list_head *element) { struct tomoyo_manager *ptr = container_of(element, typeof(*ptr), head.list); @@ -293,6 +196,38 @@ static void tomoyo_del_acl(struct list_head *element) tomoyo_put_number_union(&entry->flags); } break; + case TOMOYO_TYPE_ENV_ACL: + { + struct tomoyo_env_acl *entry = + container_of(acl, typeof(*entry), head); + + tomoyo_put_name(entry->env); + } + break; + case TOMOYO_TYPE_INET_ACL: + { + struct tomoyo_inet_acl *entry = + container_of(acl, typeof(*entry), head); + + tomoyo_put_group(entry->address.group); + tomoyo_put_number_union(&entry->port); + } + break; + case TOMOYO_TYPE_UNIX_ACL: + { + struct tomoyo_unix_acl *entry = + container_of(acl, typeof(*entry), head); + + tomoyo_put_name_union(&entry->name); + } + break; + case TOMOYO_TYPE_MANUAL_TASK_ACL: + { + struct tomoyo_task_acl *entry = + container_of(acl, typeof(*entry), head); + tomoyo_put_name(entry->domainname); + } + break; } } @@ -301,44 +236,26 @@ static void tomoyo_del_acl(struct list_head *element) * * @element: Pointer to "struct list_head". * - * Returns true if deleted, false otherwise. + * Returns nothing. + * + * Caller holds tomoyo_policy_lock mutex. */ -static bool tomoyo_del_domain(struct list_head *element) +static inline void tomoyo_del_domain(struct list_head *element) { struct tomoyo_domain_info *domain = container_of(element, typeof(*domain), list); struct tomoyo_acl_info *acl; struct tomoyo_acl_info *tmp; /* - * Since we don't protect whole execve() operation using SRCU, - * we need to recheck domain->users at this point. - * - * (1) Reader starts SRCU section upon execve(). - * (2) Reader traverses tomoyo_domain_list and finds this domain. - * (3) Writer marks this domain as deleted. - * (4) Garbage collector removes this domain from tomoyo_domain_list - * because this domain is marked as deleted and used by nobody. - * (5) Reader saves reference to this domain into - * "struct linux_binprm"->cred->security . - * (6) Reader finishes SRCU section, although execve() operation has - * not finished yet. - * (7) Garbage collector waits for SRCU synchronization. - * (8) Garbage collector kfree() this domain because this domain is - * used by nobody. - * (9) Reader finishes execve() operation and restores this domain from - * "struct linux_binprm"->cred->security. - * - * By updating domain->users at (5), we can solve this race problem - * by rechecking domain->users at (8). + * Since this domain is referenced from neither + * "struct tomoyo_io_buffer" nor "struct cred"->security, we can delete + * elements without checking for is_deleted flag. */ - if (atomic_read(&domain->users)) - return false; list_for_each_entry_safe(acl, tmp, &domain->acl_info_list, list) { tomoyo_del_acl(&acl->list); tomoyo_memory_free(acl); } tomoyo_put_name(domain->domainname); - return true; } /** @@ -387,10 +304,9 @@ void tomoyo_del_condition(struct list_head *element) * * Returns nothing. */ -static void tomoyo_del_name(struct list_head *element) +static inline void tomoyo_del_name(struct list_head *element) { - const struct tomoyo_name *ptr = - container_of(element, typeof(*ptr), head.list); + /* Nothing to do. */ } /** @@ -400,7 +316,7 @@ static void tomoyo_del_name(struct list_head *element) * * Returns nothing. */ -static void tomoyo_del_path_group(struct list_head *element) +static inline void tomoyo_del_path_group(struct list_head *element) { struct tomoyo_path_group *member = container_of(element, typeof(*member), head.list); @@ -414,7 +330,7 @@ static void tomoyo_del_path_group(struct list_head *element) * * Returns nothing. */ -static void tomoyo_del_group(struct list_head *element) +static inline void tomoyo_del_group(struct list_head *element) { struct tomoyo_group *group = container_of(element, typeof(*group), head.list); @@ -422,16 +338,128 @@ static void tomoyo_del_group(struct list_head *element) } /** + * tomoyo_del_address_group - Delete members in "struct tomoyo_address_group". + * + * @element: Pointer to "struct list_head". + * + * Returns nothing. + */ +static inline void tomoyo_del_address_group(struct list_head *element) +{ + /* Nothing to do. */ +} + +/** * tomoyo_del_number_group - Delete members in "struct tomoyo_number_group". * * @element: Pointer to "struct list_head". * * Returns nothing. */ -static void tomoyo_del_number_group(struct list_head *element) +static inline void tomoyo_del_number_group(struct list_head *element) { - struct tomoyo_number_group *member = - container_of(element, typeof(*member), head.list); + /* Nothing to do. */ +} + +/** + * tomoyo_try_to_gc - Try to kfree() an entry. + * + * @type: One of values in "enum tomoyo_policy_id". + * @element: Pointer to "struct list_head". + * + * Returns nothing. + * + * Caller holds tomoyo_policy_lock mutex. + */ +static void tomoyo_try_to_gc(const enum tomoyo_policy_id type, + struct list_head *element) +{ + /* + * __list_del_entry() guarantees that the list element became no longer + * reachable from the list which the element was originally on (e.g. + * tomoyo_domain_list). Also, synchronize_srcu() guarantees that the + * list element became no longer referenced by syscall users. + */ + __list_del_entry(element); + mutex_unlock(&tomoyo_policy_lock); + synchronize_srcu(&tomoyo_ss); + /* + * However, there are two users which may still be using the list + * element. We need to defer until both users forget this element. + * + * Don't kfree() until "struct tomoyo_io_buffer"->r.{domain,group,acl} + * and "struct tomoyo_io_buffer"->w.domain forget this element. + */ + if (tomoyo_struct_used_by_io_buffer(element)) + goto reinject; + switch (type) { + case TOMOYO_ID_TRANSITION_CONTROL: + tomoyo_del_transition_control(element); + break; + case TOMOYO_ID_MANAGER: + tomoyo_del_manager(element); + break; + case TOMOYO_ID_AGGREGATOR: + tomoyo_del_aggregator(element); + break; + case TOMOYO_ID_GROUP: + tomoyo_del_group(element); + break; + case TOMOYO_ID_PATH_GROUP: + tomoyo_del_path_group(element); + break; + case TOMOYO_ID_ADDRESS_GROUP: + tomoyo_del_address_group(element); + break; + case TOMOYO_ID_NUMBER_GROUP: + tomoyo_del_number_group(element); + break; + case TOMOYO_ID_CONDITION: + tomoyo_del_condition(element); + break; + case TOMOYO_ID_NAME: + /* + * Don't kfree() until all "struct tomoyo_io_buffer"->r.w[] + * forget this element. + */ + if (tomoyo_name_used_by_io_buffer + (container_of(element, typeof(struct tomoyo_name), + head.list)->entry.name)) + goto reinject; + tomoyo_del_name(element); + break; + case TOMOYO_ID_ACL: + tomoyo_del_acl(element); + break; + case TOMOYO_ID_DOMAIN: + /* + * Don't kfree() until all "struct cred"->security forget this + * element. + */ + if (atomic_read(&container_of + (element, typeof(struct tomoyo_domain_info), + list)->users)) + goto reinject; + break; + case TOMOYO_MAX_POLICY: + break; + } + mutex_lock(&tomoyo_policy_lock); + if (type == TOMOYO_ID_DOMAIN) + tomoyo_del_domain(element); + tomoyo_memory_free(element); + return; +reinject: + /* + * We can safely reinject this element here bacause + * (1) Appending list elements and removing list elements are protected + * by tomoyo_policy_lock mutex. + * (2) Only this function removes list elements and this function is + * exclusively executed by tomoyo_gc_mutex mutex. + * are true. + */ + mutex_lock(&tomoyo_policy_lock); + list_add_rcu(element, element->prev); } /** @@ -440,19 +468,19 @@ static void tomoyo_del_number_group(struct list_head *element) * @id: One of values in "enum tomoyo_policy_id". * @member_list: Pointer to "struct list_head". * - * Returns true if some elements are deleted, false otherwise. + * Returns nothing. */ -static bool tomoyo_collect_member(const enum tomoyo_policy_id id, +static void tomoyo_collect_member(const enum tomoyo_policy_id id, struct list_head *member_list) { struct tomoyo_acl_head *member; - list_for_each_entry(member, member_list, list) { + struct tomoyo_acl_head *tmp; + list_for_each_entry_safe(member, tmp, member_list, list) { if (!member->is_deleted) continue; - if (!tomoyo_add_to_gc(id, &member->list)) - return false; + member->is_deleted = TOMOYO_GC_IN_PROGRESS; + tomoyo_try_to_gc(id, &member->list); } - return true; } /** @@ -460,22 +488,22 @@ static bool tomoyo_collect_member(const enum tomoyo_policy_id id, * * @list: Pointer to "struct list_head". * - * Returns true if some elements are deleted, false otherwise. + * Returns nothing. */ -static bool tomoyo_collect_acl(struct list_head *list) +static void tomoyo_collect_acl(struct list_head *list) { struct tomoyo_acl_info *acl; - list_for_each_entry(acl, list, list) { + struct tomoyo_acl_info *tmp; + list_for_each_entry_safe(acl, tmp, list, list) { if (!acl->is_deleted) continue; - if (!tomoyo_add_to_gc(TOMOYO_ID_ACL, &acl->list)) - return false; + acl->is_deleted = TOMOYO_GC_IN_PROGRESS; + tomoyo_try_to_gc(TOMOYO_ID_ACL, &acl->list); } - return true; } /** - * tomoyo_collect_entry - Scan lists for deleted elements. + * tomoyo_collect_entry - Try to kfree() deleted elements. * * Returns nothing. */ @@ -484,174 +512,82 @@ static void tomoyo_collect_entry(void) int i; enum tomoyo_policy_id id; struct tomoyo_policy_namespace *ns; - int idx; - if (mutex_lock_interruptible(&tomoyo_policy_lock)) - return; - idx = tomoyo_read_lock(); + mutex_lock(&tomoyo_policy_lock); { struct tomoyo_domain_info *domain; - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { - if (!tomoyo_collect_acl(&domain->acl_info_list)) - goto unlock; + struct tomoyo_domain_info *tmp; + list_for_each_entry_safe(domain, tmp, &tomoyo_domain_list, + list) { + tomoyo_collect_acl(&domain->acl_info_list); if (!domain->is_deleted || atomic_read(&domain->users)) continue; - /* - * Nobody is referring this domain. But somebody may - * refer this domain after successful execve(). - * We recheck domain->users after SRCU synchronization. - */ - if (!tomoyo_add_to_gc(TOMOYO_ID_DOMAIN, &domain->list)) - goto unlock; + tomoyo_try_to_gc(TOMOYO_ID_DOMAIN, &domain->list); } } - list_for_each_entry_rcu(ns, &tomoyo_namespace_list, namespace_list) { + list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { for (id = 0; id < TOMOYO_MAX_POLICY; id++) - if (!tomoyo_collect_member(id, &ns->policy_list[id])) - goto unlock; + tomoyo_collect_member(id, &ns->policy_list[id]); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) - if (!tomoyo_collect_acl(&ns->acl_group[i])) - goto unlock; + tomoyo_collect_acl(&ns->acl_group[i]); + } + { + struct tomoyo_shared_acl_head *ptr; + struct tomoyo_shared_acl_head *tmp; + list_for_each_entry_safe(ptr, tmp, &tomoyo_condition_list, + list) { + if (atomic_read(&ptr->users) > 0) + continue; + atomic_set(&ptr->users, TOMOYO_GC_IN_PROGRESS); + tomoyo_try_to_gc(TOMOYO_ID_CONDITION, &ptr->list); + } + } + list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { for (i = 0; i < TOMOYO_MAX_GROUP; i++) { struct list_head *list = &ns->group_list[i]; struct tomoyo_group *group; + struct tomoyo_group *tmp; switch (i) { case 0: id = TOMOYO_ID_PATH_GROUP; break; - default: + case 1: id = TOMOYO_ID_NUMBER_GROUP; break; + default: + id = TOMOYO_ID_ADDRESS_GROUP; + break; } - list_for_each_entry(group, list, head.list) { - if (!tomoyo_collect_member - (id, &group->member_list)) - goto unlock; + list_for_each_entry_safe(group, tmp, list, head.list) { + tomoyo_collect_member(id, &group->member_list); if (!list_empty(&group->member_list) || - atomic_read(&group->head.users)) + atomic_read(&group->head.users) > 0) continue; - if (!tomoyo_add_to_gc(TOMOYO_ID_GROUP, - &group->head.list)) - goto unlock; + atomic_set(&group->head.users, + TOMOYO_GC_IN_PROGRESS); + tomoyo_try_to_gc(TOMOYO_ID_GROUP, + &group->head.list); } } } - id = TOMOYO_ID_CONDITION; - for (i = 0; i < TOMOYO_MAX_HASH + 1; i++) { - struct list_head *list = !i ? - &tomoyo_condition_list : &tomoyo_name_list[i - 1]; + for (i = 0; i < TOMOYO_MAX_HASH; i++) { + struct list_head *list = &tomoyo_name_list[i]; struct tomoyo_shared_acl_head *ptr; - list_for_each_entry(ptr, list, list) { - if (atomic_read(&ptr->users)) + struct tomoyo_shared_acl_head *tmp; + list_for_each_entry_safe(ptr, tmp, list, list) { + if (atomic_read(&ptr->users) > 0) continue; - if (!tomoyo_add_to_gc(id, &ptr->list)) - goto unlock; + atomic_set(&ptr->users, TOMOYO_GC_IN_PROGRESS); + tomoyo_try_to_gc(TOMOYO_ID_NAME, &ptr->list); } - id = TOMOYO_ID_NAME; } -unlock: - tomoyo_read_unlock(idx); mutex_unlock(&tomoyo_policy_lock); } /** - * tomoyo_kfree_entry - Delete entries in tomoyo_gc_list. - * - * Returns true if some entries were kfree()d, false otherwise. - */ -static bool tomoyo_kfree_entry(void) -{ - struct tomoyo_gc *p; - struct tomoyo_gc *tmp; - bool result = false; - - list_for_each_entry_safe(p, tmp, &tomoyo_gc_list, list) { - struct list_head *element = p->element; - - /* - * list_del_rcu() in tomoyo_add_to_gc() guarantees that the - * list element became no longer reachable from the list which - * the element was originally on (e.g. tomoyo_domain_list). - * Also, synchronize_srcu() in tomoyo_gc_thread() guarantees - * that the list element became no longer referenced by syscall - * users. - * - * However, there are three users which may still be using the - * list element. We need to defer until all of these users - * forget the list element. - * - * Firstly, defer until "struct tomoyo_io_buffer"->r.{domain, - * group,acl} and "struct tomoyo_io_buffer"->w.domain forget - * the list element. - */ - if (tomoyo_struct_used_by_io_buffer(element)) - continue; - /* - * Secondly, defer until all other elements in the - * tomoyo_gc_list list forget the list element. - */ - if (tomoyo_element_linked_by_gc((const u8 *) element, p->size)) - continue; - switch (p->type) { - case TOMOYO_ID_TRANSITION_CONTROL: - tomoyo_del_transition_control(element); - break; - case TOMOYO_ID_AGGREGATOR: - tomoyo_del_aggregator(element); - break; - case TOMOYO_ID_MANAGER: - tomoyo_del_manager(element); - break; - case TOMOYO_ID_CONDITION: - tomoyo_del_condition(element); - break; - case TOMOYO_ID_NAME: - /* - * Thirdly, defer until all "struct tomoyo_io_buffer" - * ->r.w[] forget the list element. - */ - if (tomoyo_name_used_by_io_buffer( - container_of(element, typeof(struct tomoyo_name), - head.list)->entry.name, p->size)) - continue; - tomoyo_del_name(element); - break; - case TOMOYO_ID_ACL: - tomoyo_del_acl(element); - break; - case TOMOYO_ID_DOMAIN: - if (!tomoyo_del_domain(element)) - continue; - break; - case TOMOYO_ID_PATH_GROUP: - tomoyo_del_path_group(element); - break; - case TOMOYO_ID_GROUP: - tomoyo_del_group(element); - break; - case TOMOYO_ID_NUMBER_GROUP: - tomoyo_del_number_group(element); - break; - case TOMOYO_MAX_POLICY: - break; - } - tomoyo_memory_free(element); - list_del(&p->list); - kfree(p); - tomoyo_gc_list_len--; - result = true; - } - return result; -} - -/** * tomoyo_gc_thread - Garbage collector thread function. * * @unused: Unused. * - * In case OOM-killer choose this thread for termination, we create this thread - * as a short live thread whenever /sys/kernel/security/tomoyo/ interface was - * close()d. - * * Returns 0. */ static int tomoyo_gc_thread(void *unused) @@ -660,13 +596,7 @@ static int tomoyo_gc_thread(void *unused) static DEFINE_MUTEX(tomoyo_gc_mutex); if (!mutex_trylock(&tomoyo_gc_mutex)) goto out; - daemonize("GC for TOMOYO"); - do { - tomoyo_collect_entry(); - if (list_empty(&tomoyo_gc_list)) - break; - synchronize_srcu(&tomoyo_ss); - } while (tomoyo_kfree_entry()); + tomoyo_collect_entry(); { struct tomoyo_io_buffer *head; struct tomoyo_io_buffer *tmp; diff --git a/security/tomoyo/group.c b/security/tomoyo/group.c index 5fb0e1298400..50092534ec54 100644 --- a/security/tomoyo/group.c +++ b/security/tomoyo/group.c @@ -42,7 +42,26 @@ static bool tomoyo_same_number_group(const struct tomoyo_acl_head *a, } /** - * tomoyo_write_group - Write "struct tomoyo_path_group"/"struct tomoyo_number_group" list. + * tomoyo_same_address_group - Check for duplicated "struct tomoyo_address_group" entry. + * + * @a: Pointer to "struct tomoyo_acl_head". + * @b: Pointer to "struct tomoyo_acl_head". + * + * Returns true if @a == @b, false otherwise. + */ +static bool tomoyo_same_address_group(const struct tomoyo_acl_head *a, + const struct tomoyo_acl_head *b) +{ + const struct tomoyo_address_group *p1 = container_of(a, typeof(*p1), + head); + const struct tomoyo_address_group *p2 = container_of(b, typeof(*p2), + head); + + return tomoyo_same_ipaddr_union(&p1->address, &p2->address); +} + +/** + * tomoyo_write_group - Write "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this group. @@ -77,6 +96,14 @@ int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type) * tomoyo_put_number_union() is not needed because * param->data[0] != '@'. */ + } else { + struct tomoyo_address_group e = { }; + + if (param->data[0] == '@' || + !tomoyo_parse_ipaddr_union(param, &e.address)) + goto out; + error = tomoyo_update_policy(&e.head, sizeof(e), param, + tomoyo_same_address_group); } out: tomoyo_put_group(group); @@ -137,3 +164,35 @@ bool tomoyo_number_matches_group(const unsigned long min, } return matched; } + +/** + * tomoyo_address_matches_group - Check whether the given address matches members of the given address group. + * + * @is_ipv6: True if @address is an IPv6 address. + * @address: An IPv4 or IPv6 address. + * @group: Pointer to "struct tomoyo_address_group". + * + * Returns true if @address matches addresses in @group group, false otherwise. + * + * Caller holds tomoyo_read_lock(). + */ +bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, + const struct tomoyo_group *group) +{ + struct tomoyo_address_group *member; + bool matched = false; + const u8 size = is_ipv6 ? 16 : 4; + + list_for_each_entry_rcu(member, &group->member_list, head.list) { + if (member->head.is_deleted) + continue; + if (member->address.is_ipv6 != is_ipv6) + continue; + if (memcmp(&member->address.ip[0], address, size) > 0 || + memcmp(address, &member->address.ip[1], size) > 0) + continue; + matched = true; + break; + } + return matched; +} diff --git a/security/tomoyo/memory.c b/security/tomoyo/memory.c index 7a56051146c2..0e995716cc25 100644 --- a/security/tomoyo/memory.c +++ b/security/tomoyo/memory.c @@ -27,8 +27,6 @@ void tomoyo_warn_oom(const char *function) panic("MAC Initialization failed.\n"); } -/* Lock for protecting tomoyo_memory_used. */ -static DEFINE_SPINLOCK(tomoyo_policy_memory_lock); /* Memoy currently used by policy/audit log/query. */ unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; /* Memory quota for "policy"/"audit log"/"query". */ @@ -42,22 +40,19 @@ unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; * Returns true on success, false otherwise. * * Returns true if @ptr is not NULL and quota not exceeded, false otherwise. + * + * Caller holds tomoyo_policy_lock mutex. */ bool tomoyo_memory_ok(void *ptr) { if (ptr) { const size_t s = ksize(ptr); - bool result; - spin_lock(&tomoyo_policy_memory_lock); tomoyo_memory_used[TOMOYO_MEMORY_POLICY] += s; - result = !tomoyo_memory_quota[TOMOYO_MEMORY_POLICY] || - tomoyo_memory_used[TOMOYO_MEMORY_POLICY] <= - tomoyo_memory_quota[TOMOYO_MEMORY_POLICY]; - if (!result) - tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= s; - spin_unlock(&tomoyo_policy_memory_lock); - if (result) + if (!tomoyo_memory_quota[TOMOYO_MEMORY_POLICY] || + tomoyo_memory_used[TOMOYO_MEMORY_POLICY] <= + tomoyo_memory_quota[TOMOYO_MEMORY_POLICY]) return true; + tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= s; } tomoyo_warn_oom(__func__); return false; @@ -71,6 +66,8 @@ bool tomoyo_memory_ok(void *ptr) * * Returns pointer to allocated memory on success, NULL otherwise. * @data is zero-cleared on success. + * + * Caller holds tomoyo_policy_lock mutex. */ void *tomoyo_commit_ok(void *data, const unsigned int size) { @@ -85,20 +82,6 @@ void *tomoyo_commit_ok(void *data, const unsigned int size) } /** - * tomoyo_memory_free - Free memory for elements. - * - * @ptr: Pointer to allocated memory. - */ -void tomoyo_memory_free(void *ptr) -{ - size_t s = ksize(ptr); - spin_lock(&tomoyo_policy_memory_lock); - tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= s; - spin_unlock(&tomoyo_policy_memory_lock); - kfree(ptr); -} - -/** * tomoyo_get_group - Allocate memory for "struct tomoyo_path_group"/"struct tomoyo_number_group". * * @param: Pointer to "struct tomoyo_acl_param". @@ -123,7 +106,8 @@ struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, goto out; list = ¶m->ns->group_list[idx]; list_for_each_entry(group, list, head.list) { - if (e.group_name != group->group_name) + if (e.group_name != group->group_name || + atomic_read(&group->head.users) == TOMOYO_GC_IN_PROGRESS) continue; atomic_inc(&group->head.users); found = true; @@ -175,7 +159,8 @@ const struct tomoyo_path_info *tomoyo_get_name(const char *name) if (mutex_lock_interruptible(&tomoyo_policy_lock)) return NULL; list_for_each_entry(ptr, head, head.list) { - if (hash != ptr->entry.hash || strcmp(name, ptr->entry.name)) + if (hash != ptr->entry.hash || strcmp(name, ptr->entry.name) || + atomic_read(&ptr->head.users) == TOMOYO_GC_IN_PROGRESS) continue; atomic_inc(&ptr->head.users); goto out; diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c new file mode 100644 index 000000000000..97527710a72a --- /dev/null +++ b/security/tomoyo/network.c @@ -0,0 +1,771 @@ +/* + * security/tomoyo/network.c + * + * Copyright (C) 2005-2011 NTT DATA CORPORATION + */ + +#include "common.h" +#include <linux/slab.h> + +/* Structure for holding inet domain socket's address. */ +struct tomoyo_inet_addr_info { + __be16 port; /* In network byte order. */ + const __be32 *address; /* In network byte order. */ + bool is_ipv6; +}; + +/* Structure for holding unix domain socket's address. */ +struct tomoyo_unix_addr_info { + u8 *addr; /* This may not be '\0' terminated string. */ + unsigned int addr_len; +}; + +/* Structure for holding socket address. */ +struct tomoyo_addr_info { + u8 protocol; + u8 operation; + struct tomoyo_inet_addr_info inet; + struct tomoyo_unix_addr_info unix0; +}; + +/* String table for socket's protocols. */ +const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX] = { + [SOCK_STREAM] = "stream", + [SOCK_DGRAM] = "dgram", + [SOCK_RAW] = "raw", + [SOCK_SEQPACKET] = "seqpacket", + [0] = " ", /* Dummy for avoiding NULL pointer dereference. */ + [4] = " ", /* Dummy for avoiding NULL pointer dereference. */ +}; + +/** + * tomoyo_parse_ipaddr_union - Parse an IP address. + * + * @param: Pointer to "struct tomoyo_acl_param". + * @ptr: Pointer to "struct tomoyo_ipaddr_union". + * + * Returns true on success, false otherwise. + */ +bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, + struct tomoyo_ipaddr_union *ptr) +{ + u8 * const min = ptr->ip[0].in6_u.u6_addr8; + u8 * const max = ptr->ip[1].in6_u.u6_addr8; + char *address = tomoyo_read_token(param); + const char *end; + + if (!strchr(address, ':') && + in4_pton(address, -1, min, '-', &end) > 0) { + ptr->is_ipv6 = false; + if (!*end) + ptr->ip[1].s6_addr32[0] = ptr->ip[0].s6_addr32[0]; + else if (*end++ != '-' || + in4_pton(end, -1, max, '\0', &end) <= 0 || *end) + return false; + return true; + } + if (in6_pton(address, -1, min, '-', &end) > 0) { + ptr->is_ipv6 = true; + if (!*end) + memmove(max, min, sizeof(u16) * 8); + else if (*end++ != '-' || + in6_pton(end, -1, max, '\0', &end) <= 0 || *end) + return false; + return true; + } + return false; +} + +/** + * tomoyo_print_ipv4 - Print an IPv4 address. + * + * @buffer: Buffer to write to. + * @buffer_len: Size of @buffer. + * @min_ip: Pointer to __be32. + * @max_ip: Pointer to __be32. + * + * Returns nothing. + */ +static void tomoyo_print_ipv4(char *buffer, const unsigned int buffer_len, + const __be32 *min_ip, const __be32 *max_ip) +{ + snprintf(buffer, buffer_len, "%pI4%c%pI4", min_ip, + *min_ip == *max_ip ? '\0' : '-', max_ip); +} + +/** + * tomoyo_print_ipv6 - Print an IPv6 address. + * + * @buffer: Buffer to write to. + * @buffer_len: Size of @buffer. + * @min_ip: Pointer to "struct in6_addr". + * @max_ip: Pointer to "struct in6_addr". + * + * Returns nothing. + */ +static void tomoyo_print_ipv6(char *buffer, const unsigned int buffer_len, + const struct in6_addr *min_ip, + const struct in6_addr *max_ip) +{ + snprintf(buffer, buffer_len, "%pI6c%c%pI6c", min_ip, + !memcmp(min_ip, max_ip, 16) ? '\0' : '-', max_ip); +} + +/** + * tomoyo_print_ip - Print an IP address. + * + * @buf: Buffer to write to. + * @size: Size of @buf. + * @ptr: Pointer to "struct ipaddr_union". + * + * Returns nothing. + */ +void tomoyo_print_ip(char *buf, const unsigned int size, + const struct tomoyo_ipaddr_union *ptr) +{ + if (ptr->is_ipv6) + tomoyo_print_ipv6(buf, size, &ptr->ip[0], &ptr->ip[1]); + else + tomoyo_print_ipv4(buf, size, &ptr->ip[0].s6_addr32[0], + &ptr->ip[1].s6_addr32[0]); +} + +/* + * Mapping table from "enum tomoyo_network_acl_index" to + * "enum tomoyo_mac_index" for inet domain socket. + */ +static const u8 tomoyo_inet2mac +[TOMOYO_SOCK_MAX][TOMOYO_MAX_NETWORK_OPERATION] = { + [SOCK_STREAM] = { + [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_INET_STREAM_BIND, + [TOMOYO_NETWORK_LISTEN] = + TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, + [TOMOYO_NETWORK_CONNECT] = + TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, + }, + [SOCK_DGRAM] = { + [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, + [TOMOYO_NETWORK_SEND] = TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, + }, + [SOCK_RAW] = { + [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_INET_RAW_BIND, + [TOMOYO_NETWORK_SEND] = TOMOYO_MAC_NETWORK_INET_RAW_SEND, + }, +}; + +/* + * Mapping table from "enum tomoyo_network_acl_index" to + * "enum tomoyo_mac_index" for unix domain socket. + */ +static const u8 tomoyo_unix2mac +[TOMOYO_SOCK_MAX][TOMOYO_MAX_NETWORK_OPERATION] = { + [SOCK_STREAM] = { + [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, + [TOMOYO_NETWORK_LISTEN] = + TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, + [TOMOYO_NETWORK_CONNECT] = + TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, + }, + [SOCK_DGRAM] = { + [TOMOYO_NETWORK_BIND] = TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, + [TOMOYO_NETWORK_SEND] = TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, + }, + [SOCK_SEQPACKET] = { + [TOMOYO_NETWORK_BIND] = + TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, + [TOMOYO_NETWORK_LISTEN] = + TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, + [TOMOYO_NETWORK_CONNECT] = + TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, + }, +}; + +/** + * tomoyo_same_inet_acl - Check for duplicated "struct tomoyo_inet_acl" entry. + * + * @a: Pointer to "struct tomoyo_acl_info". + * @b: Pointer to "struct tomoyo_acl_info". + * + * Returns true if @a == @b except permission bits, false otherwise. + */ +static bool tomoyo_same_inet_acl(const struct tomoyo_acl_info *a, + const struct tomoyo_acl_info *b) +{ + const struct tomoyo_inet_acl *p1 = container_of(a, typeof(*p1), head); + const struct tomoyo_inet_acl *p2 = container_of(b, typeof(*p2), head); + + return p1->protocol == p2->protocol && + tomoyo_same_ipaddr_union(&p1->address, &p2->address) && + tomoyo_same_number_union(&p1->port, &p2->port); +} + +/** + * tomoyo_same_unix_acl - Check for duplicated "struct tomoyo_unix_acl" entry. + * + * @a: Pointer to "struct tomoyo_acl_info". + * @b: Pointer to "struct tomoyo_acl_info". + * + * Returns true if @a == @b except permission bits, false otherwise. + */ +static bool tomoyo_same_unix_acl(const struct tomoyo_acl_info *a, + const struct tomoyo_acl_info *b) +{ + const struct tomoyo_unix_acl *p1 = container_of(a, typeof(*p1), head); + const struct tomoyo_unix_acl *p2 = container_of(b, typeof(*p2), head); + + return p1->protocol == p2->protocol && + tomoyo_same_name_union(&p1->name, &p2->name); +} + +/** + * tomoyo_merge_inet_acl - Merge duplicated "struct tomoyo_inet_acl" entry. + * + * @a: Pointer to "struct tomoyo_acl_info". + * @b: Pointer to "struct tomoyo_acl_info". + * @is_delete: True for @a &= ~@b, false for @a |= @b. + * + * Returns true if @a is empty, false otherwise. + */ +static bool tomoyo_merge_inet_acl(struct tomoyo_acl_info *a, + struct tomoyo_acl_info *b, + const bool is_delete) +{ + u8 * const a_perm = + &container_of(a, struct tomoyo_inet_acl, head)->perm; + u8 perm = *a_perm; + const u8 b_perm = container_of(b, struct tomoyo_inet_acl, head)->perm; + + if (is_delete) + perm &= ~b_perm; + else + perm |= b_perm; + *a_perm = perm; + return !perm; +} + +/** + * tomoyo_merge_unix_acl - Merge duplicated "struct tomoyo_unix_acl" entry. + * + * @a: Pointer to "struct tomoyo_acl_info". + * @b: Pointer to "struct tomoyo_acl_info". + * @is_delete: True for @a &= ~@b, false for @a |= @b. + * + * Returns true if @a is empty, false otherwise. + */ +static bool tomoyo_merge_unix_acl(struct tomoyo_acl_info *a, + struct tomoyo_acl_info *b, + const bool is_delete) +{ + u8 * const a_perm = + &container_of(a, struct tomoyo_unix_acl, head)->perm; + u8 perm = *a_perm; + const u8 b_perm = container_of(b, struct tomoyo_unix_acl, head)->perm; + + if (is_delete) + perm &= ~b_perm; + else + perm |= b_perm; + *a_perm = perm; + return !perm; +} + +/** + * tomoyo_write_inet_network - Write "struct tomoyo_inet_acl" list. + * + * @param: Pointer to "struct tomoyo_acl_param". + * + * Returns 0 on success, negative value otherwise. + * + * Caller holds tomoyo_read_lock(). + */ +int tomoyo_write_inet_network(struct tomoyo_acl_param *param) +{ + struct tomoyo_inet_acl e = { .head.type = TOMOYO_TYPE_INET_ACL }; + int error = -EINVAL; + u8 type; + const char *protocol = tomoyo_read_token(param); + const char *operation = tomoyo_read_token(param); + + for (e.protocol = 0; e.protocol < TOMOYO_SOCK_MAX; e.protocol++) + if (!strcmp(protocol, tomoyo_proto_keyword[e.protocol])) + break; + for (type = 0; type < TOMOYO_MAX_NETWORK_OPERATION; type++) + if (tomoyo_permstr(operation, tomoyo_socket_keyword[type])) + e.perm |= 1 << type; + if (e.protocol == TOMOYO_SOCK_MAX || !e.perm) + return -EINVAL; + if (param->data[0] == '@') { + param->data++; + e.address.group = + tomoyo_get_group(param, TOMOYO_ADDRESS_GROUP); + if (!e.address.group) + return -ENOMEM; + } else { + if (!tomoyo_parse_ipaddr_union(param, &e.address)) + goto out; + } + if (!tomoyo_parse_number_union(param, &e.port) || + e.port.values[1] > 65535) + goto out; + error = tomoyo_update_domain(&e.head, sizeof(e), param, + tomoyo_same_inet_acl, + tomoyo_merge_inet_acl); +out: + tomoyo_put_group(e.address.group); + tomoyo_put_number_union(&e.port); + return error; +} + +/** + * tomoyo_write_unix_network - Write "struct tomoyo_unix_acl" list. + * + * @param: Pointer to "struct tomoyo_acl_param". + * + * Returns 0 on success, negative value otherwise. + */ +int tomoyo_write_unix_network(struct tomoyo_acl_param *param) +{ + struct tomoyo_unix_acl e = { .head.type = TOMOYO_TYPE_UNIX_ACL }; + int error; + u8 type; + const char *protocol = tomoyo_read_token(param); + const char *operation = tomoyo_read_token(param); + + for (e.protocol = 0; e.protocol < TOMOYO_SOCK_MAX; e.protocol++) + if (!strcmp(protocol, tomoyo_proto_keyword[e.protocol])) + break; + for (type = 0; type < TOMOYO_MAX_NETWORK_OPERATION; type++) + if (tomoyo_permstr(operation, tomoyo_socket_keyword[type])) + e.perm |= 1 << type; + if (e.protocol == TOMOYO_SOCK_MAX || !e.perm) + return -EINVAL; + if (!tomoyo_parse_name_union(param, &e.name)) + return -EINVAL; + error = tomoyo_update_domain(&e.head, sizeof(e), param, + tomoyo_same_unix_acl, + tomoyo_merge_unix_acl); + tomoyo_put_name_union(&e.name); + return error; +} + +/** + * tomoyo_audit_net_log - Audit network log. + * + * @r: Pointer to "struct tomoyo_request_info". + * @family: Name of socket family ("inet" or "unix"). + * @protocol: Name of protocol in @family. + * @operation: Name of socket operation. + * @address: Name of address. + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_audit_net_log(struct tomoyo_request_info *r, + const char *family, const u8 protocol, + const u8 operation, const char *address) +{ + return tomoyo_supervisor(r, "network %s %s %s %s\n", family, + tomoyo_proto_keyword[protocol], + tomoyo_socket_keyword[operation], address); +} + +/** + * tomoyo_audit_inet_log - Audit INET network log. + * + * @r: Pointer to "struct tomoyo_request_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_audit_inet_log(struct tomoyo_request_info *r) +{ + char buf[128]; + int len; + const __be32 *address = r->param.inet_network.address; + + if (r->param.inet_network.is_ipv6) + tomoyo_print_ipv6(buf, sizeof(buf), (const struct in6_addr *) + address, (const struct in6_addr *) address); + else + tomoyo_print_ipv4(buf, sizeof(buf), address, address); + len = strlen(buf); + snprintf(buf + len, sizeof(buf) - len, " %u", + r->param.inet_network.port); + return tomoyo_audit_net_log(r, "inet", r->param.inet_network.protocol, + r->param.inet_network.operation, buf); +} + +/** + * tomoyo_audit_unix_log - Audit UNIX network log. + * + * @r: Pointer to "struct tomoyo_request_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_audit_unix_log(struct tomoyo_request_info *r) +{ + return tomoyo_audit_net_log(r, "unix", r->param.unix_network.protocol, + r->param.unix_network.operation, + r->param.unix_network.address->name); +} + +/** + * tomoyo_check_inet_acl - Check permission for inet domain socket operation. + * + * @r: Pointer to "struct tomoyo_request_info". + * @ptr: Pointer to "struct tomoyo_acl_info". + * + * Returns true if granted, false otherwise. + */ +static bool tomoyo_check_inet_acl(struct tomoyo_request_info *r, + const struct tomoyo_acl_info *ptr) +{ + const struct tomoyo_inet_acl *acl = + container_of(ptr, typeof(*acl), head); + const u8 size = r->param.inet_network.is_ipv6 ? 16 : 4; + + if (!(acl->perm & (1 << r->param.inet_network.operation)) || + !tomoyo_compare_number_union(r->param.inet_network.port, + &acl->port)) + return false; + if (acl->address.group) + return tomoyo_address_matches_group + (r->param.inet_network.is_ipv6, + r->param.inet_network.address, acl->address.group); + return acl->address.is_ipv6 == r->param.inet_network.is_ipv6 && + memcmp(&acl->address.ip[0], + r->param.inet_network.address, size) <= 0 && + memcmp(r->param.inet_network.address, + &acl->address.ip[1], size) <= 0; +} + +/** + * tomoyo_check_unix_acl - Check permission for unix domain socket operation. + * + * @r: Pointer to "struct tomoyo_request_info". + * @ptr: Pointer to "struct tomoyo_acl_info". + * + * Returns true if granted, false otherwise. + */ +static bool tomoyo_check_unix_acl(struct tomoyo_request_info *r, + const struct tomoyo_acl_info *ptr) +{ + const struct tomoyo_unix_acl *acl = + container_of(ptr, typeof(*acl), head); + + return (acl->perm & (1 << r->param.unix_network.operation)) && + tomoyo_compare_name_union(r->param.unix_network.address, + &acl->name); +} + +/** + * tomoyo_inet_entry - Check permission for INET network operation. + * + * @address: Pointer to "struct tomoyo_addr_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_inet_entry(const struct tomoyo_addr_info *address) +{ + const int idx = tomoyo_read_lock(); + struct tomoyo_request_info r; + int error = 0; + const u8 type = tomoyo_inet2mac[address->protocol][address->operation]; + + if (type && tomoyo_init_request_info(&r, NULL, type) + != TOMOYO_CONFIG_DISABLED) { + r.param_type = TOMOYO_TYPE_INET_ACL; + r.param.inet_network.protocol = address->protocol; + r.param.inet_network.operation = address->operation; + r.param.inet_network.is_ipv6 = address->inet.is_ipv6; + r.param.inet_network.address = address->inet.address; + r.param.inet_network.port = ntohs(address->inet.port); + do { + tomoyo_check_acl(&r, tomoyo_check_inet_acl); + error = tomoyo_audit_inet_log(&r); + } while (error == TOMOYO_RETRY_REQUEST); + } + tomoyo_read_unlock(idx); + return error; +} + +/** + * tomoyo_check_inet_address - Check permission for inet domain socket's operation. + * + * @addr: Pointer to "struct sockaddr". + * @addr_len: Size of @addr. + * @port: Port number. + * @address: Pointer to "struct tomoyo_addr_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_check_inet_address(const struct sockaddr *addr, + const unsigned int addr_len, + const u16 port, + struct tomoyo_addr_info *address) +{ + struct tomoyo_inet_addr_info *i = &address->inet; + + switch (addr->sa_family) { + case AF_INET6: + if (addr_len < SIN6_LEN_RFC2133) + goto skip; + i->is_ipv6 = true; + i->address = (__be32 *) + ((struct sockaddr_in6 *) addr)->sin6_addr.s6_addr; + i->port = ((struct sockaddr_in6 *) addr)->sin6_port; + break; + case AF_INET: + if (addr_len < sizeof(struct sockaddr_in)) + goto skip; + i->is_ipv6 = false; + i->address = (__be32 *) + &((struct sockaddr_in *) addr)->sin_addr; + i->port = ((struct sockaddr_in *) addr)->sin_port; + break; + default: + goto skip; + } + if (address->protocol == SOCK_RAW) + i->port = htons(port); + return tomoyo_inet_entry(address); +skip: + return 0; +} + +/** + * tomoyo_unix_entry - Check permission for UNIX network operation. + * + * @address: Pointer to "struct tomoyo_addr_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_unix_entry(const struct tomoyo_addr_info *address) +{ + const int idx = tomoyo_read_lock(); + struct tomoyo_request_info r; + int error = 0; + const u8 type = tomoyo_unix2mac[address->protocol][address->operation]; + + if (type && tomoyo_init_request_info(&r, NULL, type) + != TOMOYO_CONFIG_DISABLED) { + char *buf = address->unix0.addr; + int len = address->unix0.addr_len - sizeof(sa_family_t); + + if (len <= 0) { + buf = "anonymous"; + len = 9; + } else if (buf[0]) { + len = strnlen(buf, len); + } + buf = tomoyo_encode2(buf, len); + if (buf) { + struct tomoyo_path_info addr; + + addr.name = buf; + tomoyo_fill_path_info(&addr); + r.param_type = TOMOYO_TYPE_UNIX_ACL; + r.param.unix_network.protocol = address->protocol; + r.param.unix_network.operation = address->operation; + r.param.unix_network.address = &addr; + do { + tomoyo_check_acl(&r, tomoyo_check_unix_acl); + error = tomoyo_audit_unix_log(&r); + } while (error == TOMOYO_RETRY_REQUEST); + kfree(buf); + } else + error = -ENOMEM; + } + tomoyo_read_unlock(idx); + return error; +} + +/** + * tomoyo_check_unix_address - Check permission for unix domain socket's operation. + * + * @addr: Pointer to "struct sockaddr". + * @addr_len: Size of @addr. + * @address: Pointer to "struct tomoyo_addr_info". + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_check_unix_address(struct sockaddr *addr, + const unsigned int addr_len, + struct tomoyo_addr_info *address) +{ + struct tomoyo_unix_addr_info *u = &address->unix0; + + if (addr->sa_family != AF_UNIX) + return 0; + u->addr = ((struct sockaddr_un *) addr)->sun_path; + u->addr_len = addr_len; + return tomoyo_unix_entry(address); +} + +/** + * tomoyo_kernel_service - Check whether I'm kernel service or not. + * + * Returns true if I'm kernel service, false otherwise. + */ +static bool tomoyo_kernel_service(void) +{ + /* Nothing to do if I am a kernel service. */ + return segment_eq(get_fs(), KERNEL_DS); +} + +/** + * tomoyo_sock_family - Get socket's family. + * + * @sk: Pointer to "struct sock". + * + * Returns one of PF_INET, PF_INET6, PF_UNIX or 0. + */ +static u8 tomoyo_sock_family(struct sock *sk) +{ + u8 family; + + if (tomoyo_kernel_service()) + return 0; + family = sk->sk_family; + switch (family) { + case PF_INET: + case PF_INET6: + case PF_UNIX: + return family; + default: + return 0; + } +} + +/** + * tomoyo_socket_listen_permission - Check permission for listening a socket. + * + * @sock: Pointer to "struct socket". + * + * Returns 0 on success, negative value otherwise. + */ +int tomoyo_socket_listen_permission(struct socket *sock) +{ + struct tomoyo_addr_info address; + const u8 family = tomoyo_sock_family(sock->sk); + const unsigned int type = sock->type; + struct sockaddr_storage addr; + int addr_len; + + if (!family || (type != SOCK_STREAM && type != SOCK_SEQPACKET)) + return 0; + { + const int error = sock->ops->getname(sock, (struct sockaddr *) + &addr, &addr_len, 0); + + if (error) + return error; + } + address.protocol = type; + address.operation = TOMOYO_NETWORK_LISTEN; + if (family == PF_UNIX) + return tomoyo_check_unix_address((struct sockaddr *) &addr, + addr_len, &address); + return tomoyo_check_inet_address((struct sockaddr *) &addr, addr_len, + 0, &address); +} + +/** + * tomoyo_socket_connect_permission - Check permission for setting the remote address of a socket. + * + * @sock: Pointer to "struct socket". + * @addr: Pointer to "struct sockaddr". + * @addr_len: Size of @addr. + * + * Returns 0 on success, negative value otherwise. + */ +int tomoyo_socket_connect_permission(struct socket *sock, + struct sockaddr *addr, int addr_len) +{ + struct tomoyo_addr_info address; + const u8 family = tomoyo_sock_family(sock->sk); + const unsigned int type = sock->type; + + if (!family) + return 0; + address.protocol = type; + switch (type) { + case SOCK_DGRAM: + case SOCK_RAW: + address.operation = TOMOYO_NETWORK_SEND; + break; + case SOCK_STREAM: + case SOCK_SEQPACKET: + address.operation = TOMOYO_NETWORK_CONNECT; + break; + default: + return 0; + } + if (family == PF_UNIX) + return tomoyo_check_unix_address(addr, addr_len, &address); + return tomoyo_check_inet_address(addr, addr_len, sock->sk->sk_protocol, + &address); +} + +/** + * tomoyo_socket_bind_permission - Check permission for setting the local address of a socket. + * + * @sock: Pointer to "struct socket". + * @addr: Pointer to "struct sockaddr". + * @addr_len: Size of @addr. + * + * Returns 0 on success, negative value otherwise. + */ +int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, + int addr_len) +{ + struct tomoyo_addr_info address; + const u8 family = tomoyo_sock_family(sock->sk); + const unsigned int type = sock->type; + + if (!family) + return 0; + switch (type) { + case SOCK_STREAM: + case SOCK_DGRAM: + case SOCK_RAW: + case SOCK_SEQPACKET: + address.protocol = type; + address.operation = TOMOYO_NETWORK_BIND; + break; + default: + return 0; + } + if (family == PF_UNIX) + return tomoyo_check_unix_address(addr, addr_len, &address); + return tomoyo_check_inet_address(addr, addr_len, sock->sk->sk_protocol, + &address); +} + +/** + * tomoyo_socket_sendmsg_permission - Check permission for sending a datagram. + * + * @sock: Pointer to "struct socket". + * @msg: Pointer to "struct msghdr". + * @size: Unused. + * + * Returns 0 on success, negative value otherwise. + */ +int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, + int size) +{ + struct tomoyo_addr_info address; + const u8 family = tomoyo_sock_family(sock->sk); + const unsigned int type = sock->type; + + if (!msg->msg_name || !family || + (type != SOCK_DGRAM && type != SOCK_RAW)) + return 0; + address.protocol = type; + address.operation = TOMOYO_NETWORK_SEND; + if (family == PF_UNIX) + return tomoyo_check_unix_address((struct sockaddr *) + msg->msg_name, + msg->msg_namelen, &address); + return tomoyo_check_inet_address((struct sockaddr *) msg->msg_name, + msg->msg_namelen, + sock->sk->sk_protocol, &address); +} diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index 6c601bd300f3..738bbdf8d4c7 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -15,17 +15,19 @@ #include "../../fs/internal.h" /** - * tomoyo_encode: Convert binary string to ascii string. + * tomoyo_encode2 - Encode binary string to ascii string. * - * @str: String in binary format. + * @str: String in binary format. + * @str_len: Size of @str in byte. * * Returns pointer to @str in ascii format on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ -char *tomoyo_encode(const char *str) +char *tomoyo_encode2(const char *str, int str_len) { + int i; int len = 0; const char *p = str; char *cp; @@ -33,8 +35,9 @@ char *tomoyo_encode(const char *str) if (!p) return NULL; - while (*p) { - const unsigned char c = *p++; + for (i = 0; i < str_len; i++) { + const unsigned char c = p[i]; + if (c == '\\') len += 2; else if (c > ' ' && c < 127) @@ -49,8 +52,8 @@ char *tomoyo_encode(const char *str) return NULL; cp0 = cp; p = str; - while (*p) { - const unsigned char c = *p++; + for (i = 0; i < str_len; i++) { + const unsigned char c = p[i]; if (c == '\\') { *cp++ = '\\'; @@ -68,6 +71,21 @@ char *tomoyo_encode(const char *str) } /** + * tomoyo_encode - Encode binary string to ascii string. + * + * @str: String in binary format. + * + * Returns pointer to @str in ascii format on success, NULL otherwise. + * + * This function uses kzalloc(), so caller must kfree() if this function + * didn't return NULL. + */ +char *tomoyo_encode(const char *str) +{ + return str ? tomoyo_encode2(str, strlen(str)) : NULL; +} + +/** * tomoyo_get_absolute_path - Get the path of a dentry but ignores chroot'ed root. * * @path: Pointer to "struct path". diff --git a/security/tomoyo/securityfs_if.c b/security/tomoyo/securityfs_if.c index a49c3bfd4dd5..2672ac4f3beb 100644 --- a/security/tomoyo/securityfs_if.c +++ b/security/tomoyo/securityfs_if.c @@ -8,6 +8,124 @@ #include "common.h" /** + * tomoyo_check_task_acl - Check permission for task operation. + * + * @r: Pointer to "struct tomoyo_request_info". + * @ptr: Pointer to "struct tomoyo_acl_info". + * + * Returns true if granted, false otherwise. + */ +static bool tomoyo_check_task_acl(struct tomoyo_request_info *r, + const struct tomoyo_acl_info *ptr) +{ + const struct tomoyo_task_acl *acl = container_of(ptr, typeof(*acl), + head); + return !tomoyo_pathcmp(r->param.task.domainname, acl->domainname); +} + +/** + * tomoyo_write_self - write() for /sys/kernel/security/tomoyo/self_domain interface. + * + * @file: Pointer to "struct file". + * @buf: Domainname to transit to. + * @count: Size of @buf. + * @ppos: Unused. + * + * Returns @count on success, negative value otherwise. + * + * If domain transition was permitted but the domain transition failed, this + * function returns error rather than terminating current thread with SIGKILL. + */ +static ssize_t tomoyo_write_self(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + char *data; + int error; + if (!count || count >= TOMOYO_EXEC_TMPSIZE - 10) + return -ENOMEM; + data = kzalloc(count + 1, GFP_NOFS); + if (!data) + return -ENOMEM; + if (copy_from_user(data, buf, count)) { + error = -EFAULT; + goto out; + } + tomoyo_normalize_line(data); + if (tomoyo_correct_domain(data)) { + const int idx = tomoyo_read_lock(); + struct tomoyo_path_info name; + struct tomoyo_request_info r; + name.name = data; + tomoyo_fill_path_info(&name); + /* Check "task manual_domain_transition" permission. */ + tomoyo_init_request_info(&r, NULL, TOMOYO_MAC_FILE_EXECUTE); + r.param_type = TOMOYO_TYPE_MANUAL_TASK_ACL; + r.param.task.domainname = &name; + tomoyo_check_acl(&r, tomoyo_check_task_acl); + if (!r.granted) + error = -EPERM; + else { + struct tomoyo_domain_info *new_domain = + tomoyo_assign_domain(data, true); + if (!new_domain) { + error = -ENOENT; + } else { + struct cred *cred = prepare_creds(); + if (!cred) { + error = -ENOMEM; + } else { + struct tomoyo_domain_info *old_domain = + cred->security; + cred->security = new_domain; + atomic_inc(&new_domain->users); + atomic_dec(&old_domain->users); + commit_creds(cred); + error = 0; + } + } + } + tomoyo_read_unlock(idx); + } else + error = -EINVAL; +out: + kfree(data); + return error ? error : count; +} + +/** + * tomoyo_read_self - read() for /sys/kernel/security/tomoyo/self_domain interface. + * + * @file: Pointer to "struct file". + * @buf: Domainname which current thread belongs to. + * @count: Size of @buf. + * @ppos: Bytes read by now. + * + * Returns read size on success, negative value otherwise. + */ +static ssize_t tomoyo_read_self(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + const char *domain = tomoyo_domain()->domainname->name; + loff_t len = strlen(domain); + loff_t pos = *ppos; + if (pos >= len || !count) + return 0; + len -= pos; + if (count < len) + len = count; + if (copy_to_user(buf, domain + pos, len)) + return -EFAULT; + *ppos += len; + return len; +} + +/* Operations for /sys/kernel/security/tomoyo/self_domain interface. */ +static const struct file_operations tomoyo_self_operations = { + .write = tomoyo_write_self, + .read = tomoyo_read_self, +}; + +/** * tomoyo_open - open() for /sys/kernel/security/tomoyo/ interface. * * @inode: Pointer to "struct inode". @@ -135,8 +253,6 @@ static int __init tomoyo_initerface_init(void) TOMOYO_EXCEPTIONPOLICY); tomoyo_create_entry("audit", 0400, tomoyo_dir, TOMOYO_AUDIT); - tomoyo_create_entry("self_domain", 0400, tomoyo_dir, - TOMOYO_SELFDOMAIN); tomoyo_create_entry(".process_status", 0600, tomoyo_dir, TOMOYO_PROCESS_STATUS); tomoyo_create_entry("stat", 0644, tomoyo_dir, @@ -147,6 +263,9 @@ static int __init tomoyo_initerface_init(void) TOMOYO_MANAGER); tomoyo_create_entry("version", 0400, tomoyo_dir, TOMOYO_VERSION); + securityfs_create_file("self_domain", 0666, tomoyo_dir, NULL, + &tomoyo_self_operations); + tomoyo_load_builtin_policy(); return 0; } diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index f776400a8f31..4b327b691745 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -442,6 +442,64 @@ static int tomoyo_sb_pivotroot(struct path *old_path, struct path *new_path) return tomoyo_path2_perm(TOMOYO_TYPE_PIVOT_ROOT, new_path, old_path); } +/** + * tomoyo_socket_listen - Check permission for listen(). + * + * @sock: Pointer to "struct socket". + * @backlog: Backlog parameter. + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_socket_listen(struct socket *sock, int backlog) +{ + return tomoyo_socket_listen_permission(sock); +} + +/** + * tomoyo_socket_connect - Check permission for connect(). + * + * @sock: Pointer to "struct socket". + * @addr: Pointer to "struct sockaddr". + * @addr_len: Size of @addr. + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_socket_connect(struct socket *sock, struct sockaddr *addr, + int addr_len) +{ + return tomoyo_socket_connect_permission(sock, addr, addr_len); +} + +/** + * tomoyo_socket_bind - Check permission for bind(). + * + * @sock: Pointer to "struct socket". + * @addr: Pointer to "struct sockaddr". + * @addr_len: Size of @addr. + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_socket_bind(struct socket *sock, struct sockaddr *addr, + int addr_len) +{ + return tomoyo_socket_bind_permission(sock, addr, addr_len); +} + +/** + * tomoyo_socket_sendmsg - Check permission for sendmsg(). + * + * @sock: Pointer to "struct socket". + * @msg: Pointer to "struct msghdr". + * @size: Size of message. + * + * Returns 0 on success, negative value otherwise. + */ +static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg, + int size) +{ + return tomoyo_socket_sendmsg_permission(sock, msg, size); +} + /* * tomoyo_security_ops is a "struct security_operations" which is used for * registering TOMOYO. @@ -472,6 +530,10 @@ static struct security_operations tomoyo_security_ops = { .sb_mount = tomoyo_sb_mount, .sb_umount = tomoyo_sb_umount, .sb_pivotroot = tomoyo_sb_pivotroot, + .socket_bind = tomoyo_socket_bind, + .socket_connect = tomoyo_socket_connect, + .socket_listen = tomoyo_socket_listen, + .socket_sendmsg = tomoyo_socket_sendmsg, }; /* Lock for GC. */ diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index c36bd1107fc8..4a9b4b2eb755 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -42,6 +42,39 @@ const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX] = { [TOMOYO_MAC_FILE_MOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UMOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_PIVOT_ROOT] = TOMOYO_MAC_CATEGORY_FILE, + /* CONFIG::network group */ + [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = + TOMOYO_MAC_CATEGORY_NETWORK, + [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = + TOMOYO_MAC_CATEGORY_NETWORK, + /* CONFIG::misc group */ + [TOMOYO_MAC_ENVIRON] = TOMOYO_MAC_CATEGORY_MISC, }; /** @@ -126,6 +159,31 @@ char *tomoyo_read_token(struct tomoyo_acl_param *param) } /** + * tomoyo_get_domainname - Read a domainname from a line. + * + * @param: Pointer to "struct tomoyo_acl_param". + * + * Returns a domainname on success, NULL otherwise. + */ +const struct tomoyo_path_info *tomoyo_get_domainname +(struct tomoyo_acl_param *param) +{ + char *start = param->data; + char *pos = start; + while (*pos) { + if (*pos++ != ' ' || *pos++ == '/') + continue; + pos -= 2; + *pos++ = '\0'; + break; + } + param->data = pos; + if (tomoyo_correct_domain(start)) + return tomoyo_get_name(start); + return NULL; +} + +/** * tomoyo_parse_ulong - Parse an "unsigned long" value. * * @result: Pointer to "unsigned long". @@ -920,14 +978,17 @@ int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index) { u8 mode; - const u8 category = TOMOYO_MAC_CATEGORY_FILE; + struct tomoyo_profile *p; + if (!tomoyo_policy_loaded) return TOMOYO_CONFIG_DISABLED; - mode = tomoyo_profile(ns, profile)->config[index]; + p = tomoyo_profile(ns, profile); + mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) - mode = tomoyo_profile(ns, profile)->config[category]; + mode = p->config[tomoyo_index2category[index] + + TOMOYO_MAX_MAC_INDEX]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) - mode = tomoyo_profile(ns, profile)->default_config; + mode = p->default_config; return mode & 3; } @@ -996,6 +1057,17 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) perm = container_of(ptr, struct tomoyo_mkdev_acl, head)->perm; break; + case TOMOYO_TYPE_INET_ACL: + perm = container_of(ptr, struct tomoyo_inet_acl, + head)->perm; + break; + case TOMOYO_TYPE_UNIX_ACL: + perm = container_of(ptr, struct tomoyo_unix_acl, + head)->perm; + break; + case TOMOYO_TYPE_MANUAL_TASK_ACL: + perm = 0; + break; default: perm = 1; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e9a2a8795d1b..191284a1c0ae 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2370,6 +2370,7 @@ static int azx_dev_free(struct snd_device *device) static struct snd_pci_quirk position_fix_list[] __devinitdata = { SND_PCI_QUIRK(0x1028, 0x01cc, "Dell D820", POS_FIX_LPIB), SND_PCI_QUIRK(0x1028, 0x01de, "Dell Precision 390", POS_FIX_LPIB), + SND_PCI_QUIRK(0x1028, 0x02c6, "Dell Inspiron 1010", POS_FIX_LPIB), SND_PCI_QUIRK(0x103c, 0x306d, "HP dv3", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x813d, "ASUS P5AD2", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB), diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 7696d05b9356..76752d8ea733 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -3110,6 +3110,7 @@ static const struct snd_pci_quirk cxt5066_cfg_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x21c5, "Thinkpad Edge 13", CXT5066_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x21c6, "Thinkpad Edge 13", CXT5066_ASUS), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo Thinkpad", CXT5066_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x21cf, "Lenovo T520 & W520", CXT5066_AUTO), SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT5066_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT5066_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo U350", CXT5066_ASUS), |