diff options
96 files changed, 1167 insertions, 413 deletions
diff --git a/Documentation/filesystems/sysfs-tagging.txt b/Documentation/filesystems/sysfs-tagging.txt new file mode 100644 index 00000000000..caaaf1266d8 --- /dev/null +++ b/Documentation/filesystems/sysfs-tagging.txt @@ -0,0 +1,42 @@ +Sysfs tagging +------------- + +(Taken almost verbatim from Eric Biederman's netns tagging patch +commit msg) + +The problem. Network devices show up in sysfs and with the network +namespace active multiple devices with the same name can show up in +the same directory, ouch! + +To avoid that problem and allow existing applications in network +namespaces to see the same interface that is currently presented in +sysfs, sysfs now has tagging directory support. + +By using the network namespace pointers as tags to separate out the +the sysfs directory entries we ensure that we don't have conflicts +in the directories and applications only see a limited set of +the network devices. + +Each sysfs directory entry may be tagged with zero or one +namespaces. A sysfs_dirent is augmented with a void *s_ns. If a +directory entry is tagged, then sysfs_dirent->s_flags will have a +flag between KOBJ_NS_TYPE_NONE and KOBJ_NS_TYPES, and s_ns will +point to the namespace to which it belongs. + +Each sysfs superblock's sysfs_super_info contains an array void +*ns[KOBJ_NS_TYPES]. When a a task in a tagging namespace +kobj_nstype first mounts sysfs, a new superblock is created. It +will be differentiated from other sysfs mounts by having its +s_fs_info->ns[kobj_nstype] set to the new namespace. Note that +through bind mounting and mounts propagation, a task can easily view +the contents of other namespaces' sysfs mounts. Therefore, when a +namespace exits, it will call kobj_ns_exit() to invalidate any +sysfs_dirent->s_ns pointers pointing to it. + +Users of this interface: +- define a type in the kobj_ns_type enumeration. +- call kobj_ns_type_register() with its kobj_ns_type_operations which has + - current_ns() which returns current's namespace + - netlink_ns() which returns a socket's namespace + - initial_ns() which returns the initial namesapce +- call kobj_ns_exit() when an individual tag is no longer valid diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index d979e7c7bc4..a5fffc882c7 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -53,6 +53,7 @@ static int __pci_mmap_fits(struct pci_dev *pdev, int num, /** * pci_mmap_resource - map a PCI resource into user memory space + * @filp: open sysfs file * @kobj: kobject for mapping * @attr: struct bin_attribute for the file being mapped * @vma: struct vm_area_struct passed into the mmap @@ -60,7 +61,8 @@ static int __pci_mmap_fits(struct pci_dev *pdev, int num, * * Use the bus mapping routines to map a PCI resource into userspace. */ -static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, +static int pci_mmap_resource(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, struct vm_area_struct *vma, int sparse) { struct pci_dev *pdev = to_pci_dev(container_of(kobj, @@ -89,14 +91,14 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, return hose_mmap_page_range(pdev->sysdata, vma, mmap_type, sparse); } -static int pci_mmap_resource_sparse(struct kobject *kobj, +static int pci_mmap_resource_sparse(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, struct vm_area_struct *vma) { return pci_mmap_resource(kobj, attr, vma, 1); } -static int pci_mmap_resource_dense(struct kobject *kobj, +static int pci_mmap_resource_dense(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, struct vm_area_struct *vma) { diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index adc69291f9e..575d219b800 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -905,7 +905,7 @@ struct txx9_sramc_sysdev { void __iomem *base; }; -static ssize_t txx9_sram_read(struct kobject *kobj, +static ssize_t txx9_sram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { @@ -920,7 +920,7 @@ static ssize_t txx9_sram_read(struct kobject *kobj, return size; } -static ssize_t txx9_sram_write(struct kobject *kobj, +static ssize_t txx9_sram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t size) { diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c index 1456015a22d..198f288570c 100644 --- a/arch/powerpc/sysdev/mv64x60_pci.c +++ b/arch/powerpc/sysdev/mv64x60_pci.c @@ -24,7 +24,7 @@ #define MV64X60_VAL_LEN_MAX 11 #define MV64X60_PCICFG_CPCI_HOTSWAP 0x68 -static ssize_t mv64x60_hs_reg_read(struct kobject *kobj, +static ssize_t mv64x60_hs_reg_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -45,7 +45,7 @@ static ssize_t mv64x60_hs_reg_read(struct kobject *kobj, return sprintf(buf, "0x%08x\n", v); } -static ssize_t mv64x60_hs_reg_write(struct kobject *kobj, +static ssize_t mv64x60_hs_reg_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 72c8b0d070c..a689070be28 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -403,8 +403,9 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj, static struct kobj_attribute sys_ipl_device_attr = __ATTR(device, S_IRUGO, sys_ipl_device_show, NULL); -static ssize_t ipl_parameter_read(struct kobject *kobj, struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static ssize_t ipl_parameter_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { return memory_read_from_buffer(buf, count, &off, IPL_PARMBLOCK_START, IPL_PARMBLOCK_SIZE); @@ -419,8 +420,9 @@ static struct bin_attribute ipl_parameter_attr = { .read = &ipl_parameter_read, }; -static ssize_t ipl_scp_data_read(struct kobject *kobj, struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) { unsigned int size = IPL_PARMBLOCK_START->ipl_info.fcp.scp_data_len; void *scp_data = &IPL_PARMBLOCK_START->ipl_info.fcp.scp_data; @@ -694,7 +696,7 @@ static struct kobj_attribute sys_reipl_ccw_vmparm_attr = /* FCP reipl device attributes */ -static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj, +static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { @@ -704,7 +706,7 @@ static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, scp_data, size); } -static ssize_t reipl_fcp_scpdata_write(struct kobject *kobj, +static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { diff --git a/drivers/acpi/system.c b/drivers/acpi/system.c index e35525b39f6..c79e789ed03 100644 --- a/drivers/acpi/system.c +++ b/drivers/acpi/system.c @@ -71,7 +71,7 @@ struct acpi_table_attr { struct list_head node; }; -static ssize_t acpi_table_show(struct kobject *kobj, +static ssize_t acpi_table_show(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t offset, size_t count) { diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index fd52c48ee76..ef38aff737e 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -18,9 +18,9 @@ config UEVENT_HELPER_PATH config DEVTMPFS bool "Maintain a devtmpfs filesystem to mount at /dev" - depends on HOTPLUG && SHMEM && TMPFS + depends on HOTPLUG help - This creates a tmpfs filesystem instance early at bootup. + This creates a tmpfs/ramfs filesystem instance early at bootup. In this filesystem, the kernel driver core maintains device nodes with their default names and permissions for all registered devices with an assigned major/minor number. @@ -33,6 +33,9 @@ config DEVTMPFS functional /dev without any further help. It also allows simple rescue systems, and reliably handles dynamic major/minor numbers. + Notice: if CONFIG_TMPFS isn't enabled, the simpler ramfs + file system will be used instead. + config DEVTMPFS_MOUNT bool "Automount devtmpfs at /dev, after the kernel mounted the rootfs" depends on DEVTMPFS diff --git a/drivers/base/class.c b/drivers/base/class.c index 9c6a0d6408e..8e231d05b40 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -63,6 +63,14 @@ static void class_release(struct kobject *kobj) kfree(cp); } +static const struct kobj_ns_type_operations *class_child_ns_type(struct kobject *kobj) +{ + struct class_private *cp = to_class(kobj); + struct class *class = cp->class; + + return class->ns_type; +} + static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, @@ -71,6 +79,7 @@ static const struct sysfs_ops class_sysfs_ops = { static struct kobj_type class_ktype = { .sysfs_ops = &class_sysfs_ops, .release = class_release, + .child_ns_type = class_child_ns_type, }; /* Hotplug events for classes go to the class class_subsys */ diff --git a/drivers/base/core.c b/drivers/base/core.c index b56a0ba31d4..9630fbdf4e6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -20,7 +20,6 @@ #include <linux/notifier.h> #include <linux/genhd.h> #include <linux/kallsyms.h> -#include <linux/semaphore.h> #include <linux/mutex.h> #include <linux/async.h> @@ -132,9 +131,21 @@ static void device_release(struct kobject *kobj) kfree(p); } +static const void *device_namespace(struct kobject *kobj) +{ + struct device *dev = to_dev(kobj); + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} |