diff options
66 files changed, 3786 insertions, 753 deletions
diff --git a/Documentation/device-mapper/boot.txt b/Documentation/device-mapper/boot.txt new file mode 100644 index 000000000000..adcaad5e5e32 --- /dev/null +++ b/Documentation/device-mapper/boot.txt @@ -0,0 +1,42 @@ +Boot time creation of mapped devices +=================================== + +It is possible to configure a device mapper device to act as the root +device for your system in two ways. + +The first is to build an initial ramdisk which boots to a minimal +userspace which configures the device, then pivot_root(8) in to it. + +For simple device mapper configurations, it is possible to boot directly +using the following kernel command line: + +dm="<name> <uuid> <ro>,table line 1,...,table line n" + +name = the name to associate with the device + after boot, udev, if used, will use that name to label + the device node. +uuid = may be 'none' or the UUID desired for the device. +ro = may be "ro" or "rw". If "ro", the device and device table will be + marked read-only. + +Each table line may be as normal when using the dmsetup tool except for +two variations: +1. Any use of commas will be interpreted as a newline +2. Quotation marks cannot be escaped and cannot be used without + terminating the dm= argument. + +Unless renamed by udev, the device node created will be dm-0 as the +first minor number for the device-mapper is used during early creation. + +Example +======= + +- Booting to a linear array made up of user-mode linux block devices: + + dm="lroot none 0, 0 4096 linear 98:16 0, 4096 4096 linear 98:32 0" \ + root=/dev/dm-0 + +Will boot to a rw dm-linear target of 8192 sectors split across two +block devices identified by their major:minor numbers. After boot, udev +will rename this target to /dev/mapper/lroot (depending on the rules). +No uuid was assigned. diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt index e15bc1a0fb98..89fd8f9a259f 100644 --- a/Documentation/device-mapper/verity.txt +++ b/Documentation/device-mapper/verity.txt @@ -18,11 +18,11 @@ Construction Parameters 0 is the original format used in the Chromium OS. The salt is appended when hashing, digests are stored continuously and - the rest of the block is padded with zeros. + the rest of the block is padded with zeroes. 1 is the current format that should be used for new devices. The salt is prepended when hashing and each digest is - padded with zeros to the power of two. + padded with zeroes to the power of two. <dev> This is the device containing data, the integrity of which needs to be @@ -79,6 +79,37 @@ restart_on_corruption not compatible with ignore_corruption and requires user space support to avoid restart loops. +ignore_zero_blocks + Do not verify blocks that are expected to contain zeroes and always return + zeroes instead. This may be useful if the partition contains unused blocks + that are not guaranteed to contain zeroes. + +use_fec_from_device <fec_dev> + Use forward error correction (FEC) to recover from corruption if hash + verification fails. Use encoding data from the specified device. This + may be the same device where data and hash blocks reside, in which case + fec_start must be outside data and hash areas. + + If the encoding data covers additional metadata, it must be accessible + on the hash device after the hash blocks. + + Note: block sizes for data and hash devices must match. Also, if the + verity <dev> is encrypted the <fec_dev> should be too. + +fec_roots <num> + Number of generator roots. This equals to the number of parity bytes in + the encoding data. For example, in RS(M, N) encoding, the number of roots + is M-N. + +fec_blocks <num> + The number of encoding data blocks on the FEC device. The block size for + the FEC device is <data_block_size>. + +fec_start <offset> + This is the offset, in <data_block_size> blocks, from the start of the + FEC device to the beginning of the encoding data. + + Theory of operation =================== @@ -98,6 +129,11 @@ per-block basis. This allows for a lightweight hash computation on first read into the page cache. Block hashes are stored linearly, aligned to the nearest block size. +If forward error correction (FEC) support is enabled any recovery of +corrupted data will be verified using the cryptographic hash of the +corresponding data. This is why combining error correction with +integrity checking is essential. + Hash Tree --------- diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index cd03a0faca8f..57a9b0fccbf0 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -56,6 +56,7 @@ parameter is applicable: BLACKFIN Blackfin architecture is enabled. CLK Common clock infrastructure is enabled. CMA Contiguous Memory Area support is enabled. + DM Device mapper support is enabled. DRM Direct Rendering Management support is enabled. DYNAMIC_DEBUG Build in debug messages and enable them at runtime EDD BIOS Enhanced Disk Drive Services (EDD) is enabled @@ -898,6 +899,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Disable PIN 1 of APIC timer Can be useful to work around chipset bugs. + dm= [DM] Allows early creation of a device-mapper device. + See Documentation/device-mapper/boot.txt. + + dmasound= [HW,OSS] Sound subsystem buffers + dma_debug=off If the kernel is compiled with DMA_API_DEBUG support, this option disables the debugging code at boot. diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg index 44fa01da65b9..a4cffb1840d7 100644 --- a/android/configs/android-base.cfg +++ b/android/configs/android-base.cfg @@ -44,6 +44,7 @@ CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTICAST=y CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_NF_ARPFILTER=y CONFIG_IP_NF_ARPTABLES=y diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg index 562de015f05c..e4c8aaade197 100644 --- a/android/configs/android-recommended.cfg +++ b/android/configs/android-recommended.cfg @@ -111,6 +111,10 @@ CONFIG_TABLET_USB_GTCO=y CONFIG_TABLET_USB_HANWANG=y CONFIG_TABLET_USB_KBTAB=y CONFIG_TABLET_USB_WACOM=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_TASK_XACCT=y CONFIG_TIMER_STATS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 767a988966b1..912136fad9e3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1667,6 +1667,21 @@ config HIGHPTE bool "Allocate 2nd-level pagetables from highmem" depends on HIGHMEM +config CPU_SW_DOMAIN_PAN + bool "Enable use of CPU domains to implement privileged no-access" + depends on MMU && !ARM_LPAE + default y + help + Increase kernel security by ensuring that normal kernel accesses + are unable to access userspace addresses. This can help prevent + use-after-free bugs becoming an exploitable privilege escalation + by ensuring that magic values (such as LIST_POISON) will always + fault when dereferenced. + + CPUs with low-vector mappings use a best-efforts implementation. + Their lower 1MB needs to remain accessible for the vectors, but + the remainder of userspace will become appropriately inaccessible. + config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" depends on PERF_EVENTS diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 186270b3e194..c245f15abd44 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -430,6 +430,48 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) #endif .endm + .macro uaccess_disable, tmp, isb=1 +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Whenever we re-enter userspace, the domains should always be + * set appropriately. + */ + mov \tmp, #DACR_UACCESS_DISABLE + mcr p15, 0, \tmp, c3, c0, 0 @ Set domain register + .if \isb + instr_sync + .endif +#endif + .endm + + .macro uaccess_enable, tmp, isb=1 +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Whenever we re-enter userspace, the domains should always be + * set appropriately. + */ + mov \tmp, #DACR_UACCESS_ENABLE + mcr p15, 0, \tmp, c3, c0, 0 + .if \isb + instr_sync + .endif +#endif + .endm + + .macro uaccess_save, tmp +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + mrc p15, 0, \tmp, c3, c0, 0 + str \tmp, [sp, #S_FRAME_SIZE] +#endif + .endm + + .macro uaccess_restore +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + ldr r0, [sp, #S_FRAME_SIZE] + mcr p15, 0, r0, c3, c0, 0 +#endif + .endm + .irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo .macro ret\c, reg #if __LINUX_ARM_ARCH__ < 6 diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index b274bde24905..e7335a92144e 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -40,6 +40,7 @@ do { \ "2:\t.asciz " #__file "\n" \ ".popsection\n" \ ".pushsection __bug_table,\"a\"\n" \ + ".align 2\n" \ "3:\t.word 1b, 2b\n" \ "\t.hword " #__line ", 0\n" \ ".popsection"); \ diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index 6ddbe446425e..fc8ba1663601 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -12,6 +12,7 @@ #ifndef __ASSEMBLY__ #include <asm/barrier.h> +#include <asm/thread_info.h> #endif /* @@ -34,15 +35,14 @@ */ #ifndef CONFIG_IO_36 #define DOMAIN_KERNEL 0 -#define DOMAIN_TABLE 0 #define DOMAIN_USER 1 #define DOMAIN_IO 2 #else #define DOMAIN_KERNEL 2 -#define DOMAIN_TABLE 2 #define DOMAIN_USER 1 #define DOMAIN_IO 0 #endif +#define DOMAIN_VECTORS 3 /* * Domain types @@ -55,30 +55,65 @@ #define DOMAIN_MANAGER 1 #endif -#define domain_val(dom,type) ((type) << (2*(dom))) +#define domain_mask(dom) ((3) << (2 * (dom))) +#define domain_val(dom,type) ((type) << (2 * (dom))) + +#ifdef CONFIG_CPU_SW_DOMAIN_PAN +#define DACR_INIT \ + (domain_val(DOMAIN_USER, DOMAIN_NOACCESS) | \ + domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \ + domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \ + domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)) +#else +#define DACR_INIT \ + (domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \ + domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \ + domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \ + domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)) +#endif + +#define __DACR_DEFAULT \ + domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) | \ + domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \ + domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT) + +#define DACR_UACCESS_DISABLE \ + (__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_NOACCESS)) +#define DACR_UACCESS_ENABLE \ + (__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_CLIENT)) #ifndef __ASSEMBLY__ -#ifdef CONFIG_CPU_USE_DOMAINS +static inline unsigned int get_domain(void) +{ + unsigned int domain; + + asm( + "mrc p15, 0, %0, c3, c0 @ get domain" + : "=r" (domain) + : "m" (current_thread_info()->cpu_domain)); + + return domain; +} + static inline void set_domain(unsigned val) { asm volatile( "mcr p15, 0, %0, c3, c0 @ set domain" - : : "r" (val)); + : : "r" (val) : "memory"); isb(); } +#ifdef CONFIG_CPU_USE_DOMAINS #define modify_domain(dom,type) \ do { \ - struct thread_info *thread = current_thread_info(); \ - unsigned int domain = thread->cpu_domain; \ - domain &= ~domain_val(dom, DOMAIN_MANAGER); \ - thread->cpu_domain = domain | domain_val(dom, type); \ - set_domain(thread->cpu_domain); \ + unsigned int domain = get_domain(); \ + domain &= ~domain_mask(dom); \ + domain = domain | domain_val(dom, type); \ + set_domain(domain); \ } while (0) #else -static inline void set_domain(unsigned val) { } static inline void modify_domain(unsigned dom, unsigned type) { } #endif diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index 4e78065a16aa..6795368ad023 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -22,8 +22,11 @@ #ifdef CONFIG_SMP #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ +({ \ + unsigned int __ua_flags; \ smp_mb(); \ prefetchw(uaddr); \ + __ua_flags = uaccess_save_and_enable(); \ __asm__ __volatile__( \ "1: ldrex %1, [%3]\n" \ " " insn "\n" \ @@ -34,12 +37,15 @@ __futex_atomic_ex_table("%5") \ : "=&r" (ret), "=&r" (oldval), "=&r" (tmp) \ : "r" (uaddr), "r" (oparg), "Ir" (-EFAULT) \ - : "cc", "memory") + : "cc", "memory"); \ + uaccess_restore(__ua_flags); \ +}) static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { + unsigned int __ua_flags; int ret; u32 val; @@ -49,6 +55,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, smp_mb(); /* Prefetching cannot fault */ prefetchw(uaddr); + __ua_flags = uaccess_save_and_enable(); __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" "1: ldrex %1, [%4]\n" " teq %1, %2\n" @@ -61,6 +68,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "=&r" (ret), "=&r" (val) : "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT) : "cc", "memory"); + uaccess_restore(__ua_flags); smp_mb(); *uval = val; @@ -73,6 +81,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, #include <asm/domain.h> #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ +({ \ + unsigned int __ua_flags = uaccess_save_and_enable(); \ __asm__ __volatile__( \ "1: " TUSER(ldr) " %1, [%3]\n" \ " " insn "\n" \ @@ -81,18 +91,23 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __futex_atomic_ex_table("%5") \ : "=&r" (ret), "=&r" (oldval), "=&r" (tmp) \ : "r" (uaddr), "r" (oparg), "Ir" (-EFAULT) \ - : "cc", "memory") + : "cc", "memory"); \ + uaccess_restore(__ua_flags); \ +}) static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { + unsigned int __ua_flags; int ret = 0; u32 val; if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; + preempt_disable(); + __ua_flags = uaccess_save_and_enable(); __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" "1: " TUSER(ldr) " %1, [%4]\n" " teq %1, %2\n" @@ -102,8 +117,11 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "+r" (ret), "=&r" (val) : "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT) : "cc", "memory"); + uaccess_restore(__ua_flags); *uval = val; + preempt_enable(); + return ret; } @@ -124,7 +142,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ +#ifndef CONFIG_SMP + preempt_disable(); +#endif + pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -146,7 +167,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); /* subsumes preempt_enable() */ + pagefault_enable(); +#ifndef CONFIG_SMP + preempt_enable(); +#endif if (!ret) { switch (cmp) { diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h index 5e68278e953e..d0131ee6f6af 100644 --- a/arch/arm/include/asm/pgtable-2level-hwdef.h +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -23,6 +23,7 @@ #define PMD_PXNTABLE (_AT(pmdval_t, 1) << 2) /* v7 */ #define PMD_BIT4 (_AT(pmdval_t, 1) << 4) #define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5) +#define PMD_DOMAIN_MASK PMD_DOMAIN(0x0f) #define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */ /* * - section diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index bd32eded3e50..ae02e68b61fc 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -25,7 +25,6 @@ struct task_struct; #include <asm/types.h> -#include <asm/domain.h> typedef unsigned long mm_segment_t; @@ -74,9 +73,6 @@ struct thread_info { .flags = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ - .cpu_domain = domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \ - domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \ - domain_val(DOMAIN_IO, DOMAIN_CLIENT), \ } #define init_thread_info (init_thread_union.thread_info) diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 74b17d09ef7a..35c9db857ebe 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -50,6 +50,35 @@ struct exception_table_entry extern int fixup_exception(struct pt_regs *regs); /* + * These two functions allow hooking accesses to userspace to increase + * system integrity by ensuring that the kernel can not inadvertantly + * perform such accesses (eg, via list poison values) which could then + * be exploited for priviledge escalation. + */ +static inline unsigned int uaccess_save_and_enable(void) +{ +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + unsigned int old_domain = get_domain(); + + /* Set the current domain access to permit user accesses */ + set_domain((old_domain & ~domain_mask(DOMAIN_USER)) | + domain_val(DOMAIN_USER, DOMAIN_CLIENT)); + + return old_domain; +#else + return 0; +#endif +} + +static inline void uaccess_restore(unsigned int flags) +{ +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* Restore the user access mask */ + set_domain(flags); +#endif +} + +/* * These two are intentionally not defined anywhere - if the kernel * code generates any references to them, that's a bug. */ @@ -165,6 +194,7 @@ extern int __get_user_64t_4(void *); register typeof(x) __r2 asm("r2"); \ register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ + unsigned int __ua_flags = uaccess_save_and_enable(); \ switch (sizeof(*(__p))) { \ case 1: \ if (sizeof((x)) >= 8) \ @@ -192,6 +222,7 @@ extern int __get_user_64t_4(void *); break; \ default: __e = __get_user_bad(); break; \ } \ + uaccess_restore(__ua_flags); \ x = (typeof(*(p))) __r2; \ __e; \ }) @@ -224,6 +255,7 @@ extern int __put_user_8(void *, unsigned long long); register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \ register unsigned long __l asm("r1") = __limit; \ register int __e asm("r0"); \ + unsigned int __ua_flags = uaccess_save_and_enable(); \ switch (sizeof(*(__p))) { \ case 1: \ __put_user_x(__r2, __p, __e, __l, 1); \ @@ -239,6 +271,7 @@ extern int __put_user_8(void *, unsigned long long); break; \ default: __e = __put_user_bad(); break; \ } \ + uaccess_restore(__ua_flags); \ __e; \ }) @@ -300,20 +333,23 @@ static inline void set_fs(mm_segment_t fs) do { \ unsigned long __gu_addr = (unsigned long)(ptr); \ unsigned long __gu_val; \ + unsigned int __ua_flags; \ __chk_user_ptr(ptr); \ might_fault(); \ + __ua_flags = uaccess_save_and_enable(); \ switch (sizeof(*(ptr))) { \ case 1: __get_user_asm_byte(__gu_val, __gu_addr, err); break; \ case 2: __get_user_asm_half(__gu_val, __gu_addr, err); break; \ case 4: __get_user_asm_word(__gu_val, __gu_addr, err); break; \ default: (__gu_val) = __get_user_bad(); \ } \ + uaccess_restore(__ua_flags); \ (x) = (__typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user_asm_byte(x, addr, err) \ +#define __get_user_asm(x, addr, err, instr) \ __asm__ __volatile__( \ - "1: " TUSER(ldrb) " %1,[%2],#0\n" \ + "1: " TUSER(instr) " %1, [%2], #0\n" \ "2:\n" \ " .pushsection .text.fixup,\"ax\"\n" \ " .align 2\n" \ @@ -329,6 +365,9 @@ do { \ : "r" (addr), "i" (-EFAULT) \ : "cc") +#define __get_user_asm_byte(x, addr, err) \ + __get_user_asm(x, addr, err, ldrb) + #ifndef __ARMEB__ #define __get_user_asm_half(x, __gu_addr, err) \ ({ \ @@ -348,22 +387,7 @@ do { \ #endif #define __get_user_asm_word(x, addr, err) \ - __asm__ __volatile__( \ - "1: " TUSER(ldr) " %1,[%2],#0\n" \ - "2:\n" \ - " .pushsection .text.fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: mov %0, %3\n" \ - " mov %1, #0\n" \ - " b 2b\n" \ - " .popsection\n" \ - " .pushsection __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .popsection" \ - : "+r" (err), "=&r" (x) \ - : "r" (addr), "i" (-EFAULT) \ - : "cc") + __get_user_asm(x, addr, err, ldr) #define __put_user(x, ptr) \ ({ \ @@ -381,9 +405,11 @@ do { \ #define __put_user_err(x, ptr, err) \ do { \ unsigned long __pu_addr = (unsigned long)(ptr); \ + unsigned int __ua_flags; \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ might_fault(); \ + __ua_flags = uaccess_save_and_enable(); \ switch (sizeof(*(ptr))) { \ case 1: __put_user_asm_byte(__pu_val, __pu_addr, err); break; \ case 2: __put_user_asm_half(__pu_val, __pu_addr, err); break; \ @@ -391,11 +417,12 @@ do { \ case 8: __put_user_asm_dword(__pu_val, __pu_addr, err); break; \ default: __put_user_bad(); \ } \ + uaccess_restore(__ua_flags); \ } while (0) -#define __put_user_asm_byte(x, __pu_addr, err) \ +#define __put_user_asm(x, __pu_addr, err, instr) \ __asm__ __volatile__( \ - "1: " TUSER(strb) " %1,[%2],#0\n" \ + "1: " TUSER(instr) " %1, [%2], #0\n" \ "2:\n" \ " .pushsection .text.fixup,\"ax\"\n" \ " .align 2\n" \ @@ -410,6 +437,9 @@ do { \ : "r" (x), "r" (__pu_addr), "i" (-EFAULT) \ : "cc") +#define __put_user_asm_byte(x, __pu_addr, err) \ + __put_user_asm(x, __pu_addr, err, strb) + #ifndef __ARMEB__ #define __put_user_asm_half(x, __pu_addr, err) \ ({ \ @@ -427,21 +457,7 @@ do { \ #endif #define __put_user_asm_word(x, __pu_addr, err) \ - __asm__ __volatile__( \ - "1: " TUSER(str) " %1,[%2],#0\n" \ - "2:\n" \ - " .pushsection .text.fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: mov %0, %3\n" \ - " b 2b\n" \ - " .popsection\n" \ - " .pushsection __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .popsection" \ - : "+r" (err) \ - : "r" (x), "r" (__pu_addr), "i" (-EFAULT) \ - : "cc") + __put_user_asm(x, __pu_addr, err, str) #ifndef __ARMEB__ #define __reg_oper0 "%R2" @@ -474,11 +490,50 @@ do { \ #ifdef CONFIG_MMU -extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n); -extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n); -extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n); -extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n); -extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n); +extern unsigned long __must_check +arm_copy_from_user(void *to, const void __user *from, unsigned long n); + +static inline unsigned long __must_check +__copy_from_user(void *to, const void __user *from, unsigned long n) +{ + unsigned int __ua_flags = uaccess_save_and_enable(); + n = arm_copy_from_user(to, from, n); + uaccess_restore(__ua_flags); + return n; +} + +extern unsigned long __must_check +arm_copy_to_user(void __user *to, const void *from, unsigned long n); +extern unsigned long __must_check +__copy_to_user_std(void __user *to, const void *from, unsigned long n); + +static inline unsigned long __must_check +__copy_to_user(void __user *to, const void *from, unsigned long n) +{ +#ifndef CONFIG_UACCESS_WITH_MEMCPY + unsigned int __ua_flags = uaccess_save_and_enable(); + n = arm_copy_to_user(to, from, n); + uaccess_restore(__ua_flags); + return n; +#else + return arm_copy_to_user(to, from, n); +#endif +} + +extern unsigned long __must_check +arm_clear_user(void __user *addr, unsigned long n); +extern unsigned long __must_check +__clear_user_std(void __user *addr, unsigned long n); + +static inline unsigned long __must_check +__clear_user(void __user *addr, unsigned long n) +{ + unsigned int __ua_flags = uaccess_save_and_enable(); + n = arm_clear_user(addr, n); + uaccess_restore(__ua_flags); + return n; +} + #else #define __copy_from_user(to, from, n) (memcpy(to, (void __force *)from, n), 0) #define __copy_to_user(to, from, n) (memcpy((void __force *)to, from, n), 0) @@ -511,6 +566,7 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo return n; } +/* These are from lib/ code, and use __get_user() and friends */ extern long strncpy_from_user(char *dest, const char __user *src, long count); extern __must_check long strlen_user(const char __user *str); diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index a88671cfe1ff..a35d72d30b56 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -91,9 +91,9 @@ EXPORT_SYMBOL(__memzero); #ifdef CONFIG_MMU EXPORT_SYMBOL(copy_page); -EXPORT_SYMBOL(__copy_from_user); -EXPORT_SYMBOL(__copy_to_user); -EXPORT_SYMBOL(__clear_user); +EXPORT_SYMBOL(arm_copy_from_user); +EXPORT_SYMBOL(arm_copy_to_user); +EXPORT_SYMBOL(arm_clear_user); EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 570306c49406..a7f6e2a84465 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -147,10 +147,10 @@ ENDPROC(__und_invalid) #define SPFIX(code...) #endif - .macro svc_entry, stack_hole=0, trace=1 + .macro svc_entry, stack_hole=0, trace=1, uaccess=1 UNWIND(.fnstart ) UNWIND(.save {r0 - pc} ) - sub sp, sp, #(S_FRAME_SIZE + \stack_hole - 4) + sub sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4) #ifdef CONFIG_THUMB2_KERNEL SPFIX( str r0, [sp] ) @ temporarily saved SPFIX( mov r0, sp ) @@ -165,7 +165,7 @@ ENDPROC(__und_invalid) ldmia r0, {r3 - r5} add r7, sp, #S_SP - 4 @ here for interlock avoidance mov r6, #-1 @ "" "" "" "" - add r2, sp, #(S_FRAME_SIZE + \stack_hole - 4) + add r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4) SPFIX( addeq r2, r2, #4 ) str r3, [sp, #-4]! @ save the "real" r0 copied @ from the exception stack @@ -183,6 +183,11 @@ ENDPROC(__und_invalid) @ stmia r7, {r2 - r6} + uaccess_save r0 + .if \uaccess + uaccess_disable r0 + .endif + .if \trace #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off @@ -192,7 +197,7 @@ ENDPROC(__und_invalid) .align 5 __dabt_svc: - svc_entry + svc_entry uaccess=0 mov r2, sp dabt_helper THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR @@ -366,7 +371,7 @@ ENDPROC(__fiq_abt) #error "sizeof(struct pt_regs) must be a multiple of 8" #endif - .macro usr_entry, trace=1 + .macro usr_entry, trace=1, uaccess=1 UNWIND(.fnstart ) UNWIND(.cantunwind ) @ don't unwind the user space sub sp, sp, #S_FRAME_SIZE @@ -398,6 +403,10 @@ ENDPROC(__fiq_abt) ARM( stmdb r0, {sp, lr}^ ) THUMB( store_user_sp_lr r0, r1, S_SP - S_PC ) + .if \uaccess + uaccess_disable ip + .endif + @ Enable the alignment trap while in kernel mode ATRAP( teq r8, r7) ATRAP( mcrne p15, 0, r8, c1, c0, 0) @@ -433,7 +442,7 @@ ENDPROC(__fiq_abt) .align 5 __dabt_usr: - usr_entry + usr_entry uaccess=0 kuser_cmpxchg_check mov r2, sp dabt_helper @@ -456,7 +465,7 @@ ENDPROC(__irq_usr) .align 5 __und_usr: - usr_entry + usr_entry uaccess=0 mov r2, r4 mov r3, r5 @@ -482,6 +491,8 @@ __und_usr: 1: ldrt r0, [r4] ARM_BE8(rev r0, r0) @ little endian instruction + uaccess_disable ip + @ r0 = 32-bit ARM instruction which caused the exception @ r2 = PC value for the following instruction (:= regs->ARM_pc) @ r4 = PC value for the faulting instruction @@ -516,9 +527,10 @@ __und_usr_thumb: 2: ldrht r5, [r4] ARM_BE8(rev16 r5, r5) @ little endian instruction cmp r5, #0xe800 @ 32bit instruction if xx != 0 - blo __und_usr_fault_16 @ 16bit undefined instruction + blo __und_usr_fault_16_pan @ 16bit undefined instruction 3: ldrht r0, [r2] ARM_BE8(rev16 r0, r0) @ little endian instruction + uaccess_disable ip add r2, r2, #2 @ r2 is PC + 2, make it PC + 4 str r2, [sp, #S_PC] @ it's a 2x16bit instr, update orr r0, r0, r5, lsl #16 @@ -713,6 +725,8 @@ ENDPROC(no_fp) __und_usr_fault_32: mov r1, #4 b 1f +__und_usr_fault_16_pan: + uaccess_disable ip __und_usr_fault_16: mov r1, #2 1: mov r0, sp @@ -768,6 +782,8 @@ ENTRY(__switch_to) ldr r4, [r2, #TI_TP_VALUE] ldr r5, [r2, #TI_TP_VALUE + 4] #ifdef CONFIG_CPU_USE_DOMAINS + mrc p15, 0, r6, c3, c0, 0 @ Get domain register + str r6, [r1, #TI_CPU_DOMAIN] @ Save old domain register ldr r6, [r2, #TI_CPU_DOMAIN] #endif switch_tls r1, r4, r5, r3, r7 diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 4e7f40c577e6..617b8de8b747 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -173,6 +173,8 @@ ENTRY(vector_swi) USER( ldr scno, [lr, #-4] ) @ get SWI instruction #endif + uaccess_disable tbl + adr tbl, sys_call_table @ load syscall table pointer #if defined(CONFIG_OABI_COMPAT) diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 1a0045abead7..0d22ad206d52 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -196,7 +196,7 @@ msr cpsr_c, \rtemp @ switch back to the SVC mode .endm -#ifndef CONFIG_THUMB2_KERNEL + .macro svc_exit, rpsr, irq = 0 .if \irq != 0 @ IRQs already off @@ -215,6 +215,10 @@ blne trace_hardirqs_off #endif .endif + uaccess_restore + +#ifndef CONFIG_THUMB2_KERNEL + @ ARM mode SVC restore msr spsr_cxsf, \rpsr #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) @ We must avoid clrex due to Cortex-A15 erratum #830321 @@ -222,6 +226,20 @@ strex r1, r2, [r0] @ clear the exclusive monitor #endif ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr +#else + @ Thumb mode SVC restore + ldr lr, [sp, #S_SP] @ top of the stack + ldrd r0, r1, [sp, #S_LR] @ calling lr and pc + + @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor + + stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context + ldmia sp, {r0 - r12} + mov sp, lr + ldr lr, [sp], #4 + rfeia sp! +#endif .endm @ @@ -241,6 +259,9 @@ @ on the stack remains correct). @ .macro svc_exit_via_fiq + uaccess_restore +#ifndef CONFIG_THUMB2_KERNEL + @ ARM mode restore mov r0, sp ldmib r0, {r1 - r14} @ abort is deadly from here onward (it will @ clobber state restored below) @@ -250,9 +271,27 @@ msr spsr_cxsf, r9 ldr r0, [r0, #S_R0] ldmia r8, {pc}^ +#else + @ Thumb mode restore + add r0, sp, #S_R2 + ldr lr, [sp, #S_LR] + ldr sp, [sp, #S_SP] @ abort is deadly from here onward (it will + @ clobber state restored below) + ldmia r0, {r2 - r12} + mov r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT + msr cpsr_c, r1 + sub r0, #S_R2 + add r8, r0, #S_PC + ldmia r0, {r0 - r1} + rfeia r8 +#endif .endm + .macro restore_user_regs, fast = 0, offset = 0 + uaccess_enable r1, isb=0 +#ifndef CONFIG_THUMB2_KERNEL + @ ARM mode restore mov r2, sp ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr ldr lr, [r2, #\offset + S_PC]! @ get pc @@ -270,72 +309,16 @@ @ after ldm {}^ add sp, sp, #\offset + S_FRAME_SIZE movs pc, lr @ return & move spsr_svc into cpsr - .endm - -#else /* CONFIG_THUMB2_KERNEL */ - .macro svc_exit, rpsr, irq = 0 - .if \irq != 0 - @ IRQs already off -#ifdef CONFIG_TRACE_IRQFLAGS - @ The parent context IRQs must have been enabled to get here in - @ the first place, so there's no point checking the PSR I bit. - bl trace_hardirqs_on -#endif - .else - @ IRQs off again before pulling preserved data off the stack - disable_irq_notrace -#ifdef CONFIG_TRACE_IRQFLAGS - tst \rpsr, #PSR_I_BIT - bleq trace_hardirqs_on - tst \rpsr, #PSR_I_BIT - blne trace_hardirqs_off -#endif - .endif - ldr lr, [sp, #S_SP] @ top of the stack - ldrd r0, r1, [sp, #S_LR] @ calling lr and pc - - @ We must avoid clrex due to Cortex-A15 erratum #830321 - strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor - - stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context - ldmia sp, {r0 - r12} - mov sp, lr - ldr lr, [sp], #4 - rfeia sp! - .endm - - @ - @ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit - @ - @ For full details see non-Thumb implementation above. - @ - .macro svc_exit_via_fiq - add r0, sp, #S_R2 - ldr lr, [sp, #S_LR] - ldr sp, [sp, #S_SP] @ abort is deadly from here onward (it will - @ clobber state restored below) - ldmia r0, {r2 - r12} - mov r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT - msr cpsr_c, r1 - sub r0, #S_R2 - add r8, r0, #S_PC - ldmia r0, {r0 - r1} - rfeia r8 - .endm - -#ifdef CONFIG_CPU_V7M - /* - * Note we don't need to do clrex here as clearing the local monitor is - * part of each exception entry and exit sequence. - */ - .macro restore_user_regs, fast = 0, offset = 0 +#elif defined(CONFIG_CPU_V7M) + @ V7M restore. + @ Note that we don't need to do clrex here as clearing the local + @ monitor is part of the exception entry and exit sequence. .if \offset add sp, #\offset .endif v7m_exception_slow_exit ret_r0 = \fast - .endm -#else /* ifdef CONFIG_CPU_V7M */ - .macro restore_user_regs, fast = 0, offset = 0 +#else + @ Thumb mode restore mov r2, sp load_user_sp_lr r2, r3, \offset + S_SP @ calling sp, lr ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr @@ -353,9 +336,8 @@ .endif add sp, sp, #S_FRAME_SIZE - S_SP movs pc, lr @ return & move spsr_svc into cpsr - .endm -#endif /* ifdef CONFIG_CPU_V7M / else */ #endif /* !CONFIG_THUMB2_KERNEL */ + .endm /* * Context tracking subsystem. Used to instrument transitions diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 3637973a9708..b96475bdef86 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -441,10 +441,7 @@ __enable_mmu: bic r0, r0, #CR_I #endif #ifndef CONFIG_ARM_LPAE - mov r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \ - domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \ - domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \ - domain_val(DOMAIN_IO, DOMAIN_CLIENT)) + mov r5, #DACR_INIT mcr p15, 0, r5, c3, c0, 0 @ load domain access register mcr p15, 0, r4, c2, c0, 0 @ load page table pointer #endif diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index c49a915ef811..eafe6b2089c9 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -214,12 +214,36 @@ void __show_regs(struct pt_regs *regs) buf[4] = '\0'; #ifndef CONFIG_CPU_V7M - printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n", - buf, interrupts_enabled(regs) ? "n" : "ff", - fast_interrupts_enabled(regs) ? "n" : "ff", - processor_modes[processor_mode(regs)], - isa_modes[isa_mode(regs)], - get_fs() == get_ds() ? "kernel" : "user"); + { + unsigned int domain = get_domain(); + const char *segment; + +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Get the domain register for the parent context. In user + * mode, we don't save the DACR, so lets use what it should + * be. For other modes, we place it after the pt_regs struct. + */ + if (user_mode(regs)) + domain = DACR_UACCESS_ENABLE; + else + domain = *(unsigned int *)(regs + 1); +#endif + + if ((domain & domain_mask(DOMAIN_USER)) == + domain_val(DOMAIN_USER, DOMAIN_NOACCESS)) + segment = "none"; + else if (get_fs() == get_ds()) + segment = "kernel"; + else + segment = "user"; + + printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n", + buf, interrupts_enabled(regs) ? "n" : "ff", + fast_interrupts_enabled(regs) ? "n" : "ff", + processor_modes[processor_mode(regs)], + isa_modes[isa_mode(regs)], segment); + } #else printk("xPSR: %08lx\n", regs->ARM_cpsr); #endif @@ -231,10 +255,9 @@ void __show_regs(struct pt_regs *regs) buf[0] = '\0'; #ifdef CONFIG_CPU_CP15_MMU { - unsigned int transbase, dac; + unsigned int transbase, dac = get_domain(); asm("mrc p15, 0, %0, c2, c0\n\t" - "mrc p15, 0, %1, c3, c0\n" - : "=r" (transbase), "=r" (dac)); + : "=r" (transbase)); snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x", transbase, dac); } @@ -297,6 +320,16 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start, memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save)); +#ifdef CONFIG_CPU_USE_DOMAINS + /* + * Copy the initial value of the domain access control register + * from the current thread: thread->addr_limit will have been + * copied from the current thread via setup_thread_stack() in + * kernel/fork.c + */ + thread->cpu_domain = get_domain(); +#endif + if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->ARM_r0 = 0; diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index 1361756782c7..5b26e7efa9ea 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -141,11 +141,14 @@ static int emulate_swpX(unsigned int address, unsigned int *data, while (1) { unsigned long temp; + unsigned int __ua_flags; + __ua_flags = uaccess_save_and_enable(); if (type == TYPE_SWPB) __user_swpb_asm(*data, address, res, temp); else __user_swp_asm(*data, address, res, temp); + uaccess_restore(__ua_flags); if (likely(res != -EAGAIN) || signal_pending(current)) break; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 3dce1a342030..4837003aad6a 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -878,7 +878,6 @@ void __init early_trap_init(void *vectors_base) kuser_init(vectors_base); flush_icache_range(vectors, vectors + PAGE_SIZE * 2); - modify_domain(DOMAIN_USER, DOMAIN_CLIENT); #else /* ifndef CONFIG_CPU_V7M */ /* * on V7-M there is no need to copy the vector table to a dedicated diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S index 1710fd7db2d5..970d6c043774 100644 --- a/arch/arm/lib/clear_user.S +++ b/arch/arm/lib/clear_user.S @@ -12,14 +12,14 @@ .text -/* Prototype: int __clear_user(void *addr, size_t sz) +/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz) * Purpose : clear some user memory * Params : addr - user memory address to clear * : sz - number of bytes to clear * Returns : number of bytes NOT cleared */ ENTRY(__clear_user_std) -WEAK(__clear_user) +WEAK(arm_clear_user) stmfd sp!, {r1, lr} mov r2, #0 cmp r1, #4 @@ -44,7 +44,7 @@ WEAK(__clear_user) USER( strnebt r2, [r0]) mov r0, #0 ldmfd sp!, {r1, pc} -ENDPROC(__clear_user) +ENDPROC(arm_clear_user) ENDPROC(__clear_user_std) .pushsection .text.fixup,"ax" diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S index 7a235b9952be..1512bebfbf1b 100644 --- a/arch/arm/lib/copy_from_user.S +++ b/arch/arm/lib/copy_from_user.S @@ -17,7 +17,7 @@ /* * Prototype: * - * size_t __copy_from_user(void *to, const void *from, size_t n) + * size_t arm_copy_from_user(void *to, const void *from, size_t n) * * Purpose: * @@ -89,11 +89,11 @@ .text -ENTRY(__copy_from_user) +ENTRY(arm_copy_from_user) #include "copy_template.S" -ENDPROC(__copy_from_user) +ENDPROC(arm_copy_from_user) .pushsection .fixup,"ax" .align 0 diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S index 9648b0675a3e..caf5019d8161 100644 --- a/arch/arm/lib/copy_to_user.S +++ b/arch/arm/lib/copy_to_user.S @@ -17,7 +17,7 @@ /* * Prototype: * - * size_t __copy_to_user(void *to, const void *from, size_t n) + * size_t arm_copy_to_user(void *to, const void *from, size_t n) * * Purpose: * @@ -93,11 +93,11 @@ .text ENTRY(__copy_to_user_std) -WEAK(__copy_to_user) +WEAK(arm_copy_to_user) #include "copy_template.S" -ENDPROC(__copy_to_user) +ENDPROC(arm_copy_to_user) ENDPROC(__copy_to_user_std) .pushsection .text.fixup,"ax" diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S index 1d0957e61f89..1712f132b80d 100644 --- a/arch/arm/lib/csumpartialcopyuser.S +++ b/arch/arm/lib/csumpartialcopyuser.S @@ -17,6 +17,19 @@ .text +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + .macro save_regs + mrc p15, 0, ip, c3, c0, 0 + stmfd sp!, {r1, r2, r4 - r8, ip, lr} + uaccess_enable ip + .endm + + .macro load_regs + ldmfd sp!, {r1, r2, r4 - r8, ip, lr} + mcr p15, 0, ip, c3, c0, 0 + ret lr + .endm +#else .macro save_regs stmfd sp!, {r1, r2, r4 - r8, lr} .endm @@ -24,6 +37,7 @@ .macro load_regs ldmfd sp!, {r1, r2, r4 - r8, pc} .endm +#endif .macro load1b, reg1 ldrusr \reg1, r0, 1 diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 3e58d710013c..b3e68086b347 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -88,6 +88,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) static unsigned long noinline __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) { + unsigned long ua_flags; int atomic; if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { @@ -118,7 +119,9 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memcpy((void *)to, from, tocopy); + uaccess_restore(ua_flags); to += tocopy; from += tocopy; n -= tocopy; @@ -136,7 +139,7 @@ out: } unsigned long -__copy_to_user(void __user *to, const void *from, unsigned long n) +arm_copy_to_user(void __user *to, const void *from, unsigned long n) { /* * This test is stubbed out of the main function above to keep @@ -145,14 +148,21 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) * With frame pointer disabled, tail call optimization kicks in * as well making this test almost invisible. */ - if (n < 64) - return __copy_to_user_std(to, from, n); - return __copy_to_user_memcpy(to, from, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __copy_to_user_std(to, from, n); + uaccess_restore(ua_flags); + } else { + n = __copy_to_user_memcpy(to, from, n); + } + return n; } static unsigned long noinline __clear_user_memset(void __user *addr, unsigned long n) { + unsigned long ua_flags; + if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { memset((void *)addr, 0, n); return 0; @@ -175,7 +185,9 @@ __clear_user_memset(void __user *addr, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memset((void *)addr, 0, tocopy); + uaccess_restore(ua_flags); addr += tocopy; n -= tocopy; @@ -190,12 +202,17 @@ out: return n; } -unsigned long __clear_user(void __user *addr, unsigned long n) +unsigned long arm_clear_user(void __user *addr, unsigned long n) { /* See rational for this in __copy_to_user() above. */ - if (n < 64) - return __clear_user_std(addr, n); - return __clear_user_memset(addr, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __clear_user_std(addr, n); + uaccess_restore(ua_flags); + } else { + n = __clear_user_memset(addr, n); + } + return n; } #if 0 diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S index 54473cd4aba9..b3b31e30cadd 100644 --- a/arch/arm/mm/abort-ev4.S +++ b/arch/arm/mm/abort-ev4.S @@ -19,6 +19,7 @@ ENTRY(v4_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR ldr r3, [r4] @ read aborted ARM instruction + uaccess_disable ip @ disable userspace access bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR tst r3, #1 << 20 @ L = 1 -> write? orreq r1, r1, #1 << 11 @ yes. diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S index a0908d4653a3..a6a381a6caa5 100644 --- a/arch/arm/mm/abort-ev5t.S +++ b/arch/arm/mm/abort-ev5t.S @@ -21,8 +21,10 @@ ENTRY(v5t_early_abort) mrc p15, 0, r0, c6, c0, 0 @ get FAR do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 ldreq r3, [r4] @ read aborted ARM instruction + uaccess_disable ip @ disable user access bic r1, r1, #1 << 11 @ clear bits 11 of FSR - do_ldrd_abort tmp=ip, insn=r3 + teq_ldrd tmp=ip, insn=r3 @ insn was LDRD? + beq do_DataAbort @ yes tst r3, #1 << 20 @ check write orreq r1, r1, #1 << 11 b do_DataAbort diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S index 4006b7a61264..00ab011bef58 100644 --- a/arch/arm/mm/abort-ev5tj.S +++ b/arch/arm/mm/abort-ev5tj.S @@ -24,7 +24,9 @@ ENTRY(v5tj_early_abort) bne do_DataAbort do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 ldreq r3, [r4] @ read aborted ARM instruction - do_ldrd_abort tmp=ip, insn=r3 + uaccess_disable ip @ disable userspace access + teq_ldrd tmp=ip, insn=r3 @ insn was LDRD? + beq do_DataAbort @ yes tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. b do_DataAbort diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 8c48c5c22a33..8801a15aa105 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -26,16 +26,18 @@ ENTRY(v6_early_abort) ldr ip, =0x4107b36 mrc p15, 0, r3, c0, c0, 0 @ get processor id teq ip, r3, lsr #4 @ r0 ARM1136? - bne do_DataAbort + bne 1f tst r5, #PSR_J_BIT @ Java? tsteq r5, #PSR_T_BIT @ Thumb? - bne do_DataAbort + bne 1f bic r1, r1, #1 << 11 @ clear bit 11 of FSR ldr r3, [r4] @ read aborted ARM instruction ARM_BE8(rev r3, r3) - do_ldrd_abort tmp=ip, insn=r3 + teq_ldrd tmp=ip, insn=r3 @ insn was LDRD? + beq 1f @ yes tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. #endif +1: uaccess_disable ip @ disable userspace access b do_DataAbort diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index 4812ad054214..e8d0e08c227f 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -15,6 +15,7 @@ ENTRY(v7_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR + uaccess_disable ip @ disable userspace access /* * V6 code adjusts the returned DFSR. diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index f3982580c273..6d8e8e3365d1 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -26,6 +26,7 @@ ENTRY(v4t_late_abort) #endif bne .data_thumb_abort ldr r8, [r4] @ read arm instruction + uaccess_disable ip @ disable userspace access tst r8, #1 << 20 @ L = 1 -> write? orreq r1, r1, #1 << 11 @ yes. and r7, r8, #15 << 24 @@ -155,6 +156,7 @@ ENTRY(v4t_late_abort) .data_thumb_abort: ldrh r8, [r4] @ read instruction + uaccess_disable ip @ disable userspace access tst r8, #1 << 11 @ L = 1 -> write? orreq r1, r1, #1 << 8 @ yes and r7, r8, #15 << 12 diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S index 2cbf68ef0e83..4509bee4e081 100644 --- a/arch/arm/mm/abort-macro.S +++ b/arch/arm/mm/abort-macro.S @@ -13,6 +13,7 @@ tst \psr, #PSR_T_BIT beq not_thumb ldrh \tmp, [\pc] @ Read aborted Thumb instruction + uaccess_disable ip @ disable userspace access and \tmp, \tmp, # 0xfe00 @ Mask opcode field cmp \tmp, # 0x5600 @ Is it ldrsb? orreq \tmp, \tmp, #1 << 11 @ Set L-bit if yes @@ -29,12 +30,9 @@ not_thumb: * [7:4] == 1101 * [20] == 0 */ - .macro do_ldrd_abort, tmp, insn - tst \insn, #0x0e100000 @ [27:25,20] == 0 - bne not_ldrd - and \tmp, \insn, #0x000000f0 @ [7:4] == 1101 - cmp \tmp, #0x000000d0 - beq do_DataAbort -not_ldrd: + .macro teq_ldrd, tmp, insn + mov \tmp, #0x0e100000 + orr \tmp, #0x000000f0 + and \tmp, \insn, \tmp + teq \tmp, #0x000000d0 .endm - diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 9769f1eefe3b..00b7f7de28a1 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -365,15 +365,21 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r user: if (LDST_L_BIT(instr)) { unsigned long val; + unsigned int __ua_flags = uaccess_save_and_enable(); + get16t_unaligned_check(val, addr); + uaccess_restore(__ua_flags); /* signed half-word? */ if (instr & 0x40) val = (signed long)((signed short) val); regs->uregs[rd] = val; - } else + } else { + unsigned int __ua_flags = uaccess_save_and_enable(); put16t_unaligned_check(regs->uregs[rd], addr); + uaccess_restore(__ua_flags); + } return TYPE_LDST; @@ -420,14 +426,21 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr, user: if (load) { - unsigned long val; + unsigned long val, val2; + unsigned int __ua_flags = uaccess_save_and_enable(); + get32t_unaligned_check(val, addr); + get32t_unaligned_check(val2, addr + 4); + + uaccess_restore(__ua_flags); + regs->uregs[rd] = val; - get32t_unaligned_check(val, addr + 4); - regs->uregs[rd2] = val; + regs->uregs[rd2] = val2; } else { + unsigned int __ua_flags = uaccess_save_and_enable(); put32t_unaligned_check(regs->uregs[rd], addr); put32t_unaligned_check(regs->uregs[rd2], addr + 4); + uaccess_restore(__ua_flags); } return TYPE_LDST; @@ -458,10 +471,15 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg trans: if (LDST_L_BIT(instr)) { unsigned int val; + unsigned int __ua_flags = uaccess_save_and_enable(); get32t_unaligned_check(val, addr); + uaccess_restore(__ua_flags); regs->uregs[rd] = val; - } else + } else { + unsigned int __ua_flags = uaccess_save_and_enable(); put32t_unaligned_check(regs->uregs[rd], addr); + uaccess_restore(__ua_flags); + } return TYPE_LDST; fault: @@ -531,6 +549,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg #endif if (user_mode(regs)) { + unsigned int __ua_flags = uaccess_save_and_enable(); for (regbits = REGMASK_BITS(instr), rd = 0; regbits; regbits >>= 1, rd += 1) if (regbits & 1) { @@ -542,6 +561,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg put32t_unaligned_check(regs->uregs[rd], eaddr); eaddr += 4; } + uaccess_restore(__ua_flags); } else { for (regbits = REGMASK_BITS(instr), rd = 0; regbits; regbits >>= 1, rd += 1) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 7186382672b5..ddb5a7b38b56 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -291,13 +291,13 @@ static struct mem_type mem_types[] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_RDONLY, .prot_l1 = PMD_TYPE_TABLE, - .domain = DOMAIN_USER, + .domain = DOMAIN_VECTORS, }, [MT_HIGH_VECTORS] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_USER | L_PTE_RDONLY, .prot_l1 = PMD_TYPE_TABLE, - .domain = DOMAIN_USER, + .domain = DOMAIN_VECTORS, }, [MT_MEMORY_RWX] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index a3681f11dd9f..e683db1b90a3 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -84,6 +84,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm) if (!new_pte) goto no_pte; +#ifndef CONFIG_ARM_LPAE + /* + * Modify the PTE pointer to have the correct domain. This + * needs to be the vectors domain to avoid the low vectors + * being unmapped. + */ + pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK; + pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS); +#endif + init_pud = pud_offset(init_pgd, 0); init_pmd = pmd_offset(init_pud, 0); init_pte = pte_offset_map(init_pmd, 0); diff --git a/arch/arm/nwfpe/entry.S b/arch/arm/nwfpe/entry.S index 71df43547659..39c20afad7ed 100644 --- a/arch/arm/nwfpe/entry.S +++ b/arch/arm/nwfpe/entry.S @@ -95,9 +95,10 @@ emulate: reteq r4 @ no, return failure next: + uaccess_enable r3 .Lx1: ldrt r6, [r5], #4 @ get the next instruction and @ increment PC - + uaccess_disable r3 and r2, r6, #0x0F000000 @ test for FP insns teq r2, #0x0C000000 teqne r2, #0x0D000000 diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index b056369fd47d..3d1ce766d570 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -134,7 +134,7 @@ static int os_lock_notify(struct notifier_block *self, unsigned long action, void *data) { int cpu = (unsigned long)data; - if (action == CPU_ONLINE) + if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) smp_call_function_single(cpu, clear_os_lock, NULL, 1); return NOTIFY_OK; } diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index e7d934d3afe0..9f548fd7b8af 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -885,7 +885,7 @@ static int hw_breakpoint_reset_notify(struct notifier_block *self, void *hcpu) { int cpu = (long)hcpu; - if (action == CPU_ONLINE) + if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1); return NOTIFY_OK; } diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 61c761156371..fd4100d56d8c 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -125,6 +125,7 @@ static const struct xpad_device { { 0x045e, 0x0289, "Microsoft X-Box pad v2 (US)", 0, XTYPE_XBOX }, { 0x045e, 0x028e, "Microsoft X-Box 360 pad", 0, XTYPE_XBOX360 }, { 0x045e, 0x02d1, "Microsoft X-Box One pad", 0, XTYPE_XBOXONE }, + { 0x045e, 0x02dd, "Microsoft X-Box One pad (Covert Forces)", 0, XTYPE_XBOXONE }, { 0x045e, 0x0291, "Xbox 360 Wireless Receiver (XBOX)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, { 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, { 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX }, @@ -204,7 +205,7 @@ static const struct xpad_device { { 0x1bad, 0xf900, "Harmonix Xbox 360 Controller", 0, XTYPE_XBOX360 }, { 0x1bad, 0xf901, "Gamestop Xbox 360 Controller", 0, XTYPE_XBOX360 }, { 0x1bad, 0xf903, "Tron Xbox 360 controller", 0, XTYPE_XBOX360 }, - { 0x24c6, 0x5000, "Razer Atrox Arcade Stick", 0, XTYPE_XBOX360 }, + { 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 }, { 0x24c6, 0x5303, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 }, { 0x24c6, 0x5500, "Hori XBOX 360 EX 2 with Turbo", 0, XTYPE_XBOX360 }, @@ -242,7 +243,6 @@ static const signed short xpad_btn_triggers[] = { -1 }; - static const signed short xpad360_btn[] = { /* buttons for x360 controller */ BTN_TL, BTN_TR, /* Button LB/RB */ BTN_MODE, /* The big X button */ @@ -328,9 +328,6 @@ struct usb_xpad { unsigned char *idata; /* input data */ dma_addr_t idata_dma; - struct urb *bulk_out; - unsigned char *bdata; - struct urb *irq_out; /* urb for interrupt out report */ unsigned char *odata; /* output data */ dma_addr_t odata_dma; @@ -344,6 +341,8 @@ struct usb_xpad { int mapping; /* map d-pad to buttons or to axes */ int xtype; /* type of xbox device */ + int pad_nr; /* the order x360 pads were attached */ + const char *name; /* name of the device */ }; /* @@ -355,7 +354,6 @@ struct usb_xpad { * The used report descriptor was taken from ITO Takayukis website: * http://euc.jp/periphs/xbox-controller.ja.html */ - static void xpad_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data) { struct input_dev *dev = xpad->dev; @@ -438,7 +436,16 @@ static void xpad360_process_packet(struct usb_xpad *xpad, input_report_key(dev, BTN_TRIGGER_HAPPY2, data[2] & 0x08); input_report_key(dev, BTN_TRIGGER_HAPPY3, data[2] & 0x01); input_report_key(dev, BTN_TRIGGER_HAPPY4, data[2] & 0x02); - } else { + } + + /* + * This should be a simple else block. However historically + * xbox360w has mapped DPAD to buttons while xbox360 did not. This + * made no sense, but now we can not just switch back and have to + * support both behaviors. + */ + if (!(xpad->mapping & MAP_DPAD_TO_BUTTONS) || + xpad->xtype == XTYPE_XBOX360W) { input_report_abs(dev, ABS_HAT0X, !!(data[2] & 0x08) - !!(data[2] & 0x04)); input_report_abs(dev, ABS_HAT0Y, @@ -488,6 +495,8 @@ static void xpad360_process_packet(struct usb_xpad *xpad, input_sync(dev); } +static void xpad_identify_controller(struct usb_xpad *xpad); + /* * xpad360w_process_packet * @@ -502,14 +511,17 @@ static void xpad360_process_packet(struct usb_xpad *xpad, * 01.1 - Pad state (Bytes 4+) valid * */ - static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data) { /* Presence change */ if (data[0] & 0x08) { if (data[1] & 0x80) { xpad->pad_present = 1; - usb_submit_urb(xpad->bulk_out, GFP_ATOMIC); + /* + * Light up the segment corresponding to + * controller number. + */ + xpad_identify_controller(xpad); } else xpad->pad_present = 0; } @@ -666,28 +678,6 @@ exit: __func__, retval); } -static void xpad_bulk_out(struct urb *urb) -{ - struct usb_xpad *xpad = urb->context; - struct device *dev = &xpad->intf->dev; - - switch (urb->status) { - case 0: - /* success */ - break; - case -ECONNRESET: - case -ENOENT: - case -ESHUTDOWN: - /* this urb is terminated, clean up */ - dev_dbg(dev, "%s - urb shutting down with status: %d\n", - __func__, urb->status); - break; - default: - dev_dbg(dev, "%s - nonzero urb status received: %d\n", - __func__, urb->status); - } -} - static void xpad_irq_out(struct urb *urb) { struct usb_xpad *xpad = urb->context; @@ -778,84 +768,109 @@ static void xpad_deinit_output(struct usb_xpad *xpad) } } +static int xpad_inquiry_pad_presence(struct usb_xpad *xpad) +{ + int retval; + + mutex_lock(&xpad->odata_mutex); + + xpad->odata[0] = 0x08; + xpad->odata[1] = 0x00; + xpad->odata[2] = 0x0F; + xpad->odata[3] = 0xC0; + xpad->odata[4] = 0x00; + xpad->odata[5] = 0x00; + xpad->odata[6] = 0x00; + xpad->odata[7] = 0x00; + xpad->odata[8] = 0x00; + xpad->odata[9] = 0x00; + xpad->odata[10] = 0x00; + xpad->odata[11] = 0x00; + xpad->irq_out->transfer_buffer_length = 12; + + retval = usb_submit_urb(xpad->irq_out, GFP_KERNEL); + + mutex_unlock(&xpad->odata_mutex); + + return retval; +} + #ifdef CONFIG_JOYSTICK_XPAD_FF static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { struct usb_xpad *xpad = input_get_drvdata(dev); + __u16 strong; + __u16 weak; - if (effect->type == FF_RUMBLE) { - __u16 strong = effect->u.rumble.strong_magnitude; - __u16 weak = effect->u.rumble.weak_magnitude; - - switch (xpad->xtype) { - - case XTYPE_XBOX: - xpad->odata[0] = 0x00; - xpad->odata[1] = 0x06; - xpad->odata[2] = 0x00; - xpad->odata[3] = strong / 256; /* left actuator */ - xpad->odata[4] = 0x00; - xpad->odata[5] = weak / 256; /* right actuator */ - xpad->irq_out->transfer_buffer_length = 6; - - return usb_submit_urb(xpad->irq_out, GFP_ATOMIC); - - case XTYPE_XBOX360: - xpad->odata[0] = 0x00; - xpad->odata[1] = 0x08; - xpad->odata[2] = 0x00; - xpad->odata[3] = strong / 256; /* left actuator? */ - xpad->odata[4] = weak / 256; /* right actuator? */ - xpad->odata[5] = 0x00; - xpad->odata[6] = 0x00; - xpad->odata[7] = 0x00; - xpad->irq_out->transfer_buffer_length = 8; - - return usb_submit_urb(xpad->irq_out, GFP_ATOMIC); - - case XTYPE_XBOX360W: - xpad->odata[0] = 0x00; - xpad->odata[1] = 0x01; - xpad->odata[2] = 0x0F; - xpad->odata[3] = 0xC0; - xpad->odata[4] = 0x00; - xpad->odata[5] = strong / 256; - xpad->odata[6] = weak / 256; - xpad->odata[7] = 0x00; - xpad->odata[8] = 0x00; - xpad->odata[9] = 0x00; - xpad->odata[10] = 0x00; - xpad->odata[11] = 0x00; - xpad->irq_out->transfer_buffer_length = 12; - - return usb_submit_urb(xpad->irq_out, GFP_ATOMIC); - - case XTYPE_XBOXONE: - xpad->odata[0] = 0x09; /* activate rumble */ - xpad->odata[1] = 0x08; - xpad->odata[2] = 0x00; - xpad->odata[3] = 0x08; /* continuous effect */ - xpad->odata[4] = 0x00; /* simple rumble mode */ - xpad->odata[5] = 0x03; /* L and R actuator only */ - xpad->odata[6] = 0x00; /* TODO: LT actuator */ - xpad->odata[7] = 0x00; /* TODO: RT actuator */ - xpad->odata[8] = strong / 256; /* left actuator */ - xpad->odata[9] = weak / 256; /* right actuator */ - xpad->odata[10] = 0x80; /* length of pulse */ - xpad->odata[11] = 0x00; /* stop period of pulse */ - xpad->irq_out->transfer_buffer_length = 12; - - return usb_submit_urb(xpad->irq_out, GFP_ATOMIC); - - default: - dev_dbg(&xpad->dev->dev, - "%s - rumble command sent to unsupported xpad type: %d\n", - __func__, xpad->xtype); - return -1; - } + if (effect->type != FF_RUMBLE) + return 0; + + strong = effect->u.rumble.strong_magnitude; + weak = effect->u.rumble.weak_magnitude; + + switch (xpad->xtype) { + case XTYPE_XBOX: + xpad->odata[0] = 0x00; + xpad->odata[1] = 0x06; + xpad->odata[2] = 0x00; + xpad->odata[3] = strong / 256; /* left actuator */ + xpad->odata[4] = 0x00; + xpad->odata[5] = weak / 256; /* right actuator */ + xpad->irq_out->transfer_buffer_length = 6; + break; + + case XTYPE_XBOX360: + xpad->odata[0] = 0x00; + xpad->odata[1] = 0x08; + xpad->odata[2] = 0x00; + xpad->odata[3] = strong / 256; /* left actuator? */ + xpad->odata[4] = weak / 256; /* right actuator? */ + xpad->odata[5] = 0x00; + xpad->odata[6] = 0x00; + xpad->odata[7] = 0x00; + xpad->irq_out->transfer_buffer_length = 8; + break; + + case XTYPE_XBOX360W: + xpad->odata[0] = 0x00; + xpad->odata[1] = 0x01; + xpad->odata[2] = 0x0F; + xpad->odata[3] = 0xC0; + xpad->odata[4] = 0x00; + xpad->odata[5] = strong / 256; + xpad->odata[6] = weak / 256; + xpad->odata[7] = 0x00; + xpad->odata[8] = 0x00; + xpad->odata[9] = 0x00; + xpad->odata[10] = 0x00; + xpad->odata[11] = 0x00; + xpad->irq_out->transfer_buffer_length = 12; + break; + + case XTYPE_XBOXONE: + xpad->odata[0] = 0x09; /* activate rumble */ + xpad->odata[1] = 0x08; + xpad->odata[2] = 0x00; + xpad->odata[3] = 0x08; /* continuous effect */ + xpad->odata[4] = 0x00; /* simple rumble mode */ + xpad->odata[5] = 0x03; /* L and R actuator only */ + xpad->odata[6] = 0x00; /* TODO: LT actuator */ + xpad->odata[7] = 0x00; /* TODO: RT actuator */ + xpad->odata[8] = strong / 256; /* left actuator */ + xpad->odata[9] = weak / 256; /* right actuator */ + xpad->odata[10] = 0x80; /* length of pulse */ + xpad->odata[11] = 0x00; /* stop period of pulse */ + xpad->irq_out->transfer_buffer_length = 12; + break; + + default: + dev_dbg(&xpad->dev->dev, + "%s - rumble command sent to unsupported xpad type: %d\n", + __func__, xpad->xtype); + return -EINVAL; } - return 0; + return usb_submit_urb(xpad->irq_out, GFP_ATOMIC); } static int xpad_init_ff(struct usb_xpad *xpad) @@ -874,6 +889,9 @@ static int xpad_init_ff(struct usb_xpad *xpad) { return 0; } #if defined(CONFIG_JOYSTICK_XPAD_LEDS) #include <linux/leds.h> +#include <linux/idr.h> + +static DEFINE_IDA(xpad_pad_seq); struct xpad_led { char name[16]; @@ -881,17 +899,67 @@ struct xpad_led { struct usb_xpad *xpad; }; +/** + * set the LEDs on Xbox360 / Wireless Controllers + * @param command + * 0: off + * 1: all blink, then previous setting + * 2: 1/top-left blink, then on + * 3: 2/top-right blink, then on + * 4: 3/bottom-left blink, then on + * 5: 4/bottom-right blink, then on + * 6: 1/top-left on + * 7: 2/top-right on + * 8: 3/bottom-left on + * 9: 4/bottom-right on + * 10: rotate + * 11: blink, based on previous setting + * 12: slow blink, based on previous setting + * 13: rotate with two lights + * 14: persistent slow all blink + * 15: blink once, then previous setting + */ static void xpad_send_led_command(struct usb_xpad *xpad, int command) { - if (command >= 0 && command < 14) { - mutex_lock(&xpad->odata_mutex); + command %= 16; + + mutex_lock(&xpad->odata_mutex); + + switch (xpad->xtype) { + case XTYPE_XBOX360: xpad->odata[0] = 0x01; xpad->odata[1] = 0x03; xpad->odata[2] = command; xpad->irq_out->transfer_buffer_length = 3; - usb_submit_urb(xpad->irq_out, GFP_KERNEL); - mutex_unlock(&xpad->odata_mutex); + break; + case XTYPE_XBOX360W: + xpad->odata[0] = 0x00; + xpad->odata[1] = 0x00; + xpad->odata[2] = 0x08; + xpad->odata[3] = 0x40 + command; + xpad->odata[4] = 0x00; + xpad->odata[5] = 0x00; + xpad->odata[6] = 0x00; + xpad->odata[7] = 0x00; + xpad->odata[8] = 0x00; + xpad->odata[9] = 0x00; + xpad->odata[10] = 0x00; + xpad->odata[11] = 0x00; + xpad->irq_out->transfer_buffer_length = 12; + break; } + + usb_submit_urb(xpad->irq_out, GFP_KERNEL); + mutex_unlock(&xpad->odata_mutex); +} + +/* + * Light up the segment corresponding to the pad number on + * Xbox 360 Controllers. + */ +static void xpad_identify_controller(struct usb_xpad *xpad) +{ + xpad_send_led_command(xpad, (xpad->pad_nr % 4) + 2); } static void xpad_led_set(struct led_classdev *led_cdev, @@ -905,22 +973,24 @@ static void xpad_led_set(struct led_classdev *led_cdev, static int xpad_led_probe(struct usb_xpad *xpad) { - static atomic_t led_seq = ATOMIC_INIT(-1); - unsigned long led_no; struct xpad_led *led; struct led_classdev *led_cdev; int error; - if (xpad->xtype != XTYPE_XBOX360) + if (xpad->xtype != XTYPE_XBOX360 && xpad->xtype != XTYPE_XBOX360W) return 0; xpad->led = led = kzalloc(sizeof(struct xpad_led), GFP_KERNEL); if (!led) return -ENOMEM; - led_no = atomic_inc_return(&led_seq); + xpad->pad_nr = ida_simple_get(&xpad_pad_seq, 0, 0, GFP_KERNEL); + if (xpad->pad_nr < 0) { + error = xpad->pad_nr; + goto err_free_mem; + } - snprintf(led->name, sizeof(led->name), "xpad%lu", led_no); + snprintf(led->name, sizeof(led->name), "xpad%d", xpad->pad_nr); led->xpad = xpad; led_cdev = &led->led_cdev; @@ -928,18 +998,26 @@ static int xpad_led_probe(struct usb_xpad *xpad) led_cdev->brightness_set = xpad_led_set; error = led_classdev_register(&xpad->udev->dev, led_cdev); - if (error) { - kfree(led); - xpad->led = NULL; - return error; - } + if (error) + goto err_free_id; - /* - * Light up the segment corresponding to controller number - */ - xpad_send_led_command(xpad, (led_no % 4) + 2); + if (xpad->xtype == XTYPE_XBOX360) { + /* + * Light up the segment corresponding to controller + * number on wired devices. On wireless we'll do that + * when they respond to "presence" packet. + */ + xpad_identify_controller(xpad); + } return 0; + +err_free_id: + ida_simple_remove(&xpad_pad_seq, xpad->pad_nr); +err_free_mem: + kfree(led); + xpad->led = NULL; + return error; } static void xpad_led_disconnect(struct usb_xpad *xpad) @@ -948,15 +1026,16 @@ static void xpad_led_disconnect(struct usb_xpad *xpad) if (xpad_led) { led_classdev_unregister(&xpad_led->led_cdev); + ida_simple_remove(&xpad_pad_seq, xpad->pad_nr); kfree(xpad_led); } } #else static int xpad_led_probe(struct usb_xpad *xpad) { return 0; } static void xpad_led_disconnect(struct usb_xpad *xpad) { } +static void xpad_identify_controller(struct usb_xpad *xpad) { } #endif - static int xpad_open(struct input_dev *dev) { struct usb_xpad *xpad = input_get_drvdata(dev); @@ -1016,11 +1095,107 @@ static void xpad_set_up_abs(struct input_dev *input_dev, signed short abs) } } +static void xpad_deinit_input(struct usb_xpad *xpad) +{ + xpad_led_disconnect(xpad); + input_unregister_device(xpad->dev); +} + +static int xpad_init_input(struct usb_xpad *xpad) +{ + struct input_dev *input_dev; + int i, error; + + input_dev = input_allocate_device(); + if (!input_dev) + return -ENOMEM; + + xpad->dev = input_dev; + input_dev->name = xpad->name; + input_dev->phys = xpad->phys; + usb_to_input_id(xpad->udev, &input_dev->id); + input_dev->dev.parent = &xpad->intf->dev; + + input_set_drvdata(input_dev, xpad); + + input_dev->open = xpad_open; + input_dev->close = xpad_close; + + __set_bit(EV_KEY, input_dev->evbit); + + if (!(xpad->mapping & MAP_STICKS_TO_NULL)) { + __set_bit(EV_ABS, input_dev->evbit); + /* set up axes */ + for (i = 0; xpad_abs[i] >= 0; i++) + xpad_set_up_abs(input_dev, xpad_abs[i]); + } + + /* set up standard buttons */ + for (i = 0; xpad_common_btn[i] >= 0; i++) + __set_bit(xpad_common_btn[i], input_dev->keybit); + + /* set up model-specific ones */ + if (xpad->xtype == XTYPE_XBOX360 || xpad->xtype == XTYPE_XBOX360W || + xpad->xtype == XTYPE_XBOXONE) { + for (i = 0; xpad360_btn[i] >= 0; i++) + __set_bit(xpad360_btn[i], input_dev->keybit); + } else { + for (i = 0; xpad_btn[i] >= 0; i++) + __set_bit(xpad_btn[i], input_dev->keybit); + } + + if (xpad->mapping & MAP_DPAD_TO_BUTTONS) { + for (i = 0; xpad_btn_pad[i] >= 0; i++) + __set_bit(xpad_btn_pad[i], input_dev->keybit); + } + + /* + * This should be a simple else block. However historically + * xbox360w has mapped DPAD to buttons while xbox360 did not. This + * made no sense, but now we can not just switch back and have to + * support both behaviors. + */ + if (!(xpad->mapping & MAP_DPAD_TO_BUTTONS) || + xpad->xtype == XTYPE_XBOX360W) { + for (i = 0; xpad_abs_pad[i] >= 0; i++) + xpad_set_up_abs(input_dev, xpad_abs_pad[i]); + } + + if (xpad->mapping & MAP_TRIGGERS_TO_BUTTONS) { + for (i = 0; xpad_btn_triggers[i] >= 0; i++) + __set_bit(xpad_btn_triggers[i], input_dev->keybit); + } else { + for (i = 0; xpad_abs_triggers[i] >= 0; i++) + xpad_set_up_abs(input_dev, xpad_abs_triggers[i]); + } + + error = xpad_init_ff(xpad); + if (error) + goto err_free_input; + + error = xpad_led_probe(xpad); + if (error) + goto err_destroy_ff; + + error = input_register_device(xpad->dev); + if (error) + goto err_disconnect_led; + + return 0; + +err_disconnect_led: + xpad_led_disconnect(xpad); +err_destroy_ff: + input_ff_destroy(input_dev); +err_free_input: + input_free_device(input_dev); + return error; +} + static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); struct usb_xpad *xpad; - struct input_dev *input_dev; struct usb_endpoint_descriptor *ep_irq_in; int ep_irq_in_idx; int i, error; @@ -1042,29 +1217,30 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id } xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL); - input_dev = input_allocate_device(); - if (!xpad || !input_dev) { - error = -ENOMEM; - goto fail1; - } + if (!xpad) + return -ENOMEM; + + usb_make_path(udev, xpad->phys, sizeof(xpad->phys)); + strlcat(xpad->phys, "/input0", sizeof(xpad->phys)); xpad->idata = usb_alloc_coherent(udev, XPAD_PKT_LEN, GFP_KERNEL, &xpad->idata_dma); if (!xpad->idata) { error = -ENOMEM; - goto fail1; + goto err_free_mem; } xpad->irq_in = usb_alloc_urb(0, GFP_KERNEL); if (!xpad->irq_in) { error = -ENOMEM; - goto fail2; + goto err_free_idata; } xpad->udev = udev; xpad->intf = intf; xpad->mapping = xpad_device[i].mapping; xpad->xtype = xpad_device[i].xtype; + xpad->name = xpad_device[i].name; if (xpad->xtype == XTYPE_UNKNOWN) { if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) { @@ -1072,8 +1248,9 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id xpad->xtype = XTYPE_XBOX360W; else xpad->xtype = XTYPE_XBOX360; - } else + } else { xpad->xtype = XTYPE_XBOX; + } if (dpad_to_buttons) xpad->mapping |= MAP_DPAD_TO_BUTTONS; @@ -1083,70 +1260,9 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id xpad->mapping |= MAP_STICKS_TO_NULL; } - xpad->dev = input_dev; - usb_make_path(udev, xpad->phys, sizeof(xpad->phys)); - strlcat(xpad->phys, "/input0", sizeof(xpad->phys)); - - input_dev->name = xpad_device[i].name; - input_dev->phys = xpad->phys; - usb_to_input_id(udev, &input_dev->id); - input_dev->dev.parent = &intf->dev; - - input_set_drvdata(input_dev, xpad); - - input_dev->open = xpad_open; - input_dev->close = xpad_close; - - input_dev->evbit[0] = BIT_MASK(EV_KEY); - - if (!(xpad->mapping & MAP_STICKS_TO_NULL)) { - input_dev->evbit[0] |= BIT_MASK(EV_ABS); - /* set up axes */ - for (i = 0; xpad_abs[i] >= 0; i++) - xpad_set_up_abs(input_dev, xpad_abs[i]); - } - - /* set up standard buttons */ - for (i = 0; xpad_common_btn[i] >= 0; i++) - __set_bit(xpad_common_btn[i], input_dev->keybit); - - /* set up model-specific ones */ - if (xpad->xtype == XTYPE_XBOX360 || xpad->xtype == XTYPE_XBOX360W || - xpad->xtype == XTYPE_XBOXONE) { - for (i = 0; xpad360_btn[i] >= 0; i++) - __set_bit(xpad360_btn[i], input_dev->keybit); - } else { - for (i = 0; xpad_btn[i] >= 0; i++) - __set_bit(xpad_btn[i], input_dev->keybit); - } - - if (xpad->mapping & MAP_DPAD_TO_BUTTONS) { - for (i = 0; xpad_btn_pad[i] >= 0; i++) - __set_bit(xpad_btn_pad[i], input_dev->keybit); - } else { - for (i = 0; xpad_abs_pad[i] >= 0; i++) - xpad_set_up_abs(input_dev, xpad_abs_pad[i]); - } - - if (xpad->mapping & MAP_TRIGGERS_TO_BUTTONS) { - for (i = 0; xpad_btn_triggers[i] >= 0; i++) - __set_bit(xpad_btn_triggers[i], input_dev->keybit); - } else { - for (i = 0; xpad_abs_triggers[i] >= 0; i++) - xpad_set_up_abs(input_dev, xpad_abs_triggers[i]); - } - error = xpad_init_output(intf, xpad); if (error) - goto fail3; - - error = xpad_init_ff(xpad); - if (error) - goto fail4; - - error = xpad_led_probe(xpad); - if (error) - goto fail5; + goto err_free_in_urb; /* Xbox One controller has in/out endpoints swapped. */ ep_irq_in_idx = xpad->xtype == XTYPE_XBOXONE ? 1 : 0; @@ -1159,59 +1275,13 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id xpad->irq_in->transfer_dma = xpad->idata_dma; xpad->irq_in->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - error = input_register_device(xpad->dev); - if (error) - goto fail6; - usb_set_intfdata(intf, xpad); - if (xpad->xtype == XTYPE_XBOX360W) { - /* - * Setup the message to set the LEDs on the - * controller when it shows up - */ - xpad->bulk_out = usb_alloc_urb(0, GFP_KERNEL); - if (!xpad->bulk_out) { - error = -ENOMEM; - goto fail7; - } - - xpad->bdata = kzalloc(XPAD_PKT_LEN, GFP_KERNEL); - if (!xpad->bdata) { - error = -ENOMEM; - goto fail8; - } - - xpad->bdata[2] = 0x08; - switch (intf->cur_altsetting->desc.bInterfaceNumber) { - case 0: - xpad->bdata[3] = 0x42; - break; - case 2: - xpad->bdata[3] = 0x43; - break; - case 4: - xpad->bdata[3] = 0x44; - break; - case 6: - xpad->bdata[3] = 0x45; - } - - ep_irq_in = &intf->cur_altsetting->endpoint[1].desc; - if (usb_endpoint_is_bulk_out(ep_irq_in)) { - usb_fill_bulk_urb(xpad->bulk_out, udev, - usb_sndbulkpipe(udev, - ep_irq_in->bEndpointAddress), - xpad->bdata, XPAD_PKT_LEN, - xpad_bulk_out, xpad); - } else { - usb_fill_int_urb(xpad->bulk_out, udev, - usb_sndintpipe(udev, - ep_irq_in->bEndpointAddress), - xpad->bdata, XPAD_PKT_LEN, - xpad_bulk_out, xpad, 0); - } + error = xpad_init_input(xpad); + if (error) + goto err_deinit_output; + if (xpad->xtype == XTYPE_XBOX360W) { /* * Submit the int URB immediately rather than waiting for open * because we get status messages from the device whether @@ -1222,22 +1292,32 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id xpad->irq_in->dev = xpad->udev; error = usb_submit_urb(xpad->irq_in, GFP_KERNEL); if (error) - goto fail9; - } + goto err_deinit_input; + /* + * Send presence packet. + * This will force the controller to resend connection packets. + * This is useful in the case we activate the module after the + * adapter has been plugged in, as it won't automatically + * send us info about the controllers. + */ + error = xpad_inquiry_pad_presence(xpad); + if (error) + goto err_kill_in_urb; + } return 0; - fail9: kfree(xpad->bdata); - fail8: usb_free_urb(xpad->bulk_out); - fail7: input_unregister_device(input_dev); - input_dev = NULL; - fail6: xpad_led_disconnect(xpad); - fail5: if (input_dev) - input_ff_destroy(input_dev); - fail4: xpad_deinit_output(xpad); - fail3: usb_free_urb(xpad->irq_in); - fail2: usb_free_coherent(udev, XPAD_PKT_LEN, xpad->idata, xpad->idata_dma); - fail1: input_free_device(input_dev); +err_kill_in_urb: + usb_kill_urb(xpad->irq_in); +err_deinit_input: + xpad_deinit_input(xpad); +err_deinit_output: + xpad_deinit_output(xpad); +err_free_in_urb: + usb_free_urb(xpad->irq_in); +err_free_idata: + usb_free_coherent(udev, XPAD_PKT_LEN, xpad->idata, xpad->idata_dma); +err_free_mem: kfree(xpad); return error; @@ -1247,13 +1327,10 @@ static void xpad_disconnect(struct usb_interface *intf) { struct usb_xpad *xpad = usb_get_intfdata (intf); - xpad_led_disconnect(xpad); - input_unregister_device(xpad->dev); + xpad_deinit_input(xpad); xpad_deinit_output(xpad); if (xpad->xtype == XTYPE_XBOX360W) { - usb_kill_urb(xpad->bulk_out); - usb_free_urb(xpad->bulk_out); usb_kill_urb(xpad->irq_in); } @@ -1261,7 +1338,6 @@ static void xpad_disconnect(struct usb_interface *intf) usb_free_coherent(xpad->udev, XPAD_PKT_LEN, xpad->idata, xpad->idata_dma); - kfree(xpad->bdata); kfree(xpad); usb_set_intfdata(intf, NULL); diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index edcf4ab66e00..38d7ad509c1a 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -445,6 +445,18 @@ config DM_VERITY If unsure, say N. +config DM_VERITY_FEC + bool "Verity forward error correction support" + depends on DM_VERITY + select REED_SOLOMON + select REED_SOLOMON_DEC8 + ---help--- + Add forward error correction support to dm-verity. This option + makes it possible to use pre-generated error correction data to + recover from corrupted blocks. + + If unsure, say N. + config DM_SWITCH tristate "Switch target support (EXPERIMENTAL)" depends on BLK_DEV_DM @@ -475,4 +487,20 @@ config DM_LOG_WRITES If unsure, say N. +config DM_ANDROID_VERITY + bool "Android verity target support" + depends on DM_VERITY + depends on X509_CERTIFICATE_PARSER + depends on SYSTEM_TRUSTED_KEYRING + depends on PUBLIC_KEY_ALGO_RSA + depends on KEYS + depends on ASYMMETRIC_KEY_TYPE + depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE + ---help--- + This device-mapper target is virtually a VERITY target. This + target is setup by reading the metadata contents piggybacked + to the actual data blocks in the block device. The signature + of the metadata contents are verified against the key included + in the system keyring. Upon success, the underlying verity + target is setup. endif # MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index dba4db5985fb..29a776c54cf1 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -15,6 +15,7 @@ dm-cache-y += dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o dm-cache-mq-y += dm-cache-policy-mq.o dm-cache-cleaner-y += dm-cache-policy-cleaner.o dm-era-y += dm-era-target.o +dm-verity-y += dm-verity-target.o md-mod-y += md.o bitmap.o raid456-y += raid5.o @@ -61,3 +62,11 @@ obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o endif + +ifeq ($(CONFIG_DM_VERITY_FEC),y) +dm-verity-objs += dm-verity-fec.o +endif + +ifeq ($(CONFIG_DM_ANDROID_VERITY),y) +dm-verity-objs += dm-android-verity.o +endif diff --git a/drivers/md/dm-android-verity.c b/drivers/md/dm-android-verity.c new file mode 100644 index 000000000000..aeb5045830d9 --- /dev/null +++ b/drivers/md/dm-android-verity.c @@ -0,0 +1,771 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#include <linux/buffer_head.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/device-mapper.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/fcntl.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/module.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/of.h> +#include <linux/reboot.h> +#include <linux/string.h> +#include <linux/vmalloc.h> + +#include <asm/setup.h> +#include <crypto/hash.h> +#include <crypto/public_key.h> +#include <crypto/sha.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> + +#include "dm-verity.h" +#include "dm-android-verity.h" + +static char verifiedbootstate[VERITY_COMMANDLINE_PARAM_LENGTH]; +static char veritymode[VERITY_COMMANDLINE_PARAM_LENGTH]; + +static int __init verified_boot_state_param(char *line) +{ + strlcpy(verifiedbootstate, line, sizeof(verifiedbootstate)); + return 1; +} + +__setup("androidboot.verifiedbootstate=", verified_boot_state_param); + +static int __init verity_mode_param(char *line) +{ + strlcpy(veritymode, line, sizeof(veritymode)); + return 1; +} + +__setup("androidboot.veritymode=", verity_mode_param); + +static int table_extract_mpi_array(struct public_key_signature *pks, + const void *data, size_t len) +{ + MPI mpi = mpi_read_raw_data(data, len); + + if (!mpi) { + DMERR("Error while allocating mpi array"); + return -ENOMEM; + } + + pks->mpi[0] = mpi; + pks->nr_mpi = 1; + return 0; +} + +static struct public_key_signature *table_make_digest( + enum hash_algo hash, + const void *table, + unsigned long table_len) +{ + struct public_key_signature *pks = NULL; + struct crypto_shash *tfm; + struct shash_desc *desc; + size_t digest_size, desc_size; + int ret; + + /* Allocate the hashing algorithm we're going to need and find out how + * big the hash operational data will be. + */ + tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0); + if (IS_ERR(tfm)) + return ERR_CAST(tfm); + + desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); + digest_size = crypto_shash_digestsize(tfm); + + /* We allocate the hash operational data storage on the end of out + * context data and the digest output buffer on the end of that. + */ + ret = -ENOMEM; + pks = kzalloc(digest_size + sizeof(*pks) + desc_size, GFP_KERNEL); + if (!pks) + goto error; + + pks->pkey_hash_algo = hash; + pks->digest = (u8 *)pks + sizeof(*pks) + desc_size; + pks->digest_size = digest_size; + + desc = (struct shash_desc *)(pks + 1); + desc->tfm = tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + ret = crypto_shash_init(desc); + if (ret < 0) + goto error; + + ret = crypto_shash_finup(desc, table, table_len, pks->digest); + if (ret < 0) + goto error; + + crypto_free_shash(tfm); + return pks; + +error: + kfree(pks); + crypto_free_shash(tfm); + return ERR_PTR(ret); +} + +static int read_block_dev(struct bio_read *payload, struct block_device *bdev, + sector_t offset, int length) +{ + struct bio *bio; + int err = 0, i; + + payload->number_of_pages = DIV_ROUND_UP(length, PAGE_SIZE); + + bio = bio_alloc(GFP_KERNEL, payload->number_of_pages); + if (!bio) { + DMERR("Error while allocating bio"); + return -ENOMEM; + } + + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = offset; + + payload->page_io = kzalloc(sizeof(struct page *) * + payload->number_of_pages, GFP_KERNEL); + if (!payload->page_io) { + DMERR("page_io array alloc failed"); + err = -ENOMEM; + goto free_bio; + } + + for (i = 0; i < payload->number_of_pages; i++) { + payload->page_io[i] = alloc_page(GFP_KERNEL); + if (!payload->page_io[i]) { + DMERR("alloc_page failed"); + err = -ENOMEM; + goto free_pages; + } + if (!bio_add_page(bio, payload->page_io[i], PAGE_SIZE, 0)) { + DMERR("bio_add_page error"); + err = -EIO; + goto free_pages; + } + } + + if (!submit_bio_wait(READ, bio)) + /* success */ + goto free_bio; + DMERR("bio read failed"); + err = -EIO; + +free_pages: + for (i = 0; i < payload->number_of_pages; i++) + if (payload->page_io[i]) + __free_page(payload->page_io[i]); + kfree(payload->page_io); +free_bio: + bio_put(bio); + return err; +} + +static inline u64 fec_div_round_up(u64 x, u64 y) +{ + u64 remainder; + + return div64_u64_rem(x, y, &remainder) + + (remainder > 0 ? 1 : 0); +} + +static inline void populate_fec_metadata(struct fec_header *header, + struct fec_ecc_metadata *ecc) +{ + ecc->blocks = fec_div_round_up(le64_to_cpu(header->inp_size), + FEC_BLOCK_SIZE); + ecc->roots = le32_to_cpu(header->roots); + ecc->start = le64_to_cpu(header->inp_size); +} + +static inline int validate_fec_header(struct fec_header *header, u64 offset) +{ + /* move offset to make the sanity check work for backup header + * as well. */ + offset -= offset % FEC_BLOCK_SIZE; + if (le32_to_cpu(header->magic) != FEC_MAGIC || + le32_to_cpu(header->version) != FEC_VERSION || + le32_to_cpu(header->size) != sizeof(struct fec_header) || + le32_to_cpu(header->roots) == 0 || + le32_to_cpu(header->roots) >= FEC_RSM || + offset < le32_to_cpu(header->fec_size) || + offset - le32_to_cpu(header->fec_size) != + le64_to_cpu(header->inp_size)) + return -EINVAL; + + return 0; +} + +static int extract_fec_header(dev_t dev, struct fec_header *fec, + struct fec_ecc_metadata *ecc) +{ + u64 device_size; + struct bio_read payload; + int i, err = 0; + struct block_device *bdev; + + bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + + if (IS_ERR(bdev)) { + DMERR("bdev get error"); + return PTR_ERR(bdev); + } + + device_size = i_size_read(bdev->bd_inode); + + /* fec metadata size is a power of 2 and PAGE_SIZE + * is a power of 2 as well. + */ + BUG_ON(FEC_BLOCK_SIZE > PAGE_SIZE); + /* 512 byte sector alignment */ + BUG_ON(((device_size - FEC_BLOCK_SIZE) % (1 << SECTOR_SHIFT)) != 0); + + err = read_block_dev(&payload, bdev, (device_size - + FEC_BLOCK_SIZE) / (1 << SECTOR_SHIFT), FEC_BLOCK_SIZE); + if (err) { + DMERR("Error while reading verity metadata"); + goto error; + } + + BUG_ON(sizeof(struct fec_header) > PAGE_SIZE); + memcpy(fec, page_address(payload.page_io[0]), + sizeof(*fec)); + + ecc->valid = true; + if (validate_fec_header(fec, device_size - FEC_BLOCK_SIZE)) { + /* Try the backup header */ + memcpy(fec, page_address(payload.page_io[0]) + FEC_BLOCK_SIZE + - sizeof(*fec) , + sizeof(*fec)); + if (validate_fec_header(fec, device_size - + sizeof(struct fec_header))) + ecc->valid = false; + } + + if (ecc->valid) + populate_fec_metadata(fec, ecc); + + for (i = 0; i < payload.number_of_pages; i++) + __free_page(payload.page_io[i]); + kfree(payload.page_io); + +error: + blkdev_put(bdev, FMODE_READ); + return err; +} +static void find_metadata_offset(struct fec_header *fec, + struct block_device *bdev, u64 *metadata_offset) +{ + u64 device_size; + + device_size = i_size_read(bdev->bd_inode); + + if (le32_to_cpu(fec->magic) == FEC_MAGIC) + *metadata_offset = le64_to_cpu(fec->inp_size) - + VERITY_METADATA_SIZE; + else + *metadata_offset = device_size - VERITY_METADATA_SIZE; +} + +static struct android_metadata *extract_metadata(dev_t dev, + struct fec_header *fec) +{ + struct block_device *bdev; + struct android_metadata_header *header; + struct android_metadata *uninitialized_var(metadata); + int i; + u32 table_length, copy_length, offset; + u64 metadata_offset; + struct bio_read payload; + int err = 0; + + bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + + if (IS_ERR(bdev)) { + DMERR("blkdev_get_by_dev failed"); + return ERR_CAST(bdev); + } + + find_metadata_offset(fec, bdev, &metadata_offset); + + /* Verity metadata size is a power of 2 and PAGE_SIZE + * is a power of 2 as well. + * PAGE_SIZE is also a multiple of 512 bytes. + */ + if (VERITY_METADATA_SIZE > PAGE_SIZE) + BUG_ON(VERITY_METADATA_SIZE % PAGE_SIZE != 0); + /* 512 byte sector alignment */ + BUG_ON(metadata_offset % (1 << SECTOR_SHIFT) != 0); + + err = read_block_dev(&payload, bdev, metadata_offset / + (1 << SECTOR_SHIFT), VERITY_METADATA_SIZE); + if (err) { + DMERR("Error while reading verity metadata"); + metadata = ERR_PTR(err); + goto blkdev_release; + } + + header = kzalloc(sizeof(*header), GFP_KERNEL); + if (!header) { + DMERR("kzalloc failed for header"); + err = -ENOMEM; + goto free_payload; + } + + memcpy(header, page_address(payload.page_io[0]), + sizeof(*header)); + + DMINFO("bio magic_number:%u protocol_version:%d table_length:%u", + le32_to_cpu(header->magic_number), + le32_to_cpu(header->protocol_version), + le32_to_cpu(header->table_length)); + + metadata = kzalloc(sizeof(*metadata), GFP_KERNEL); + if (!metadata) { + DMERR("kzalloc for metadata failed"); + err = -ENOMEM; + goto free_header; + } + + metadata->header = header; + table_length = le32_to_cpu(header->table_length); + + if (table_length == 0 || + table_length > (VERITY_METADATA_SIZE - + sizeof(struct android_metadata_header))) + goto free_metadata; + + metadata->verity_table = kzalloc(table_length + 1, GFP_KERNEL); + + if (!metadata->verity_table) { + DMERR("kzalloc verity_table failed"); + err = -ENOMEM; + goto free_metadata; + } + + if (sizeof(struct android_metadata_header) + + table_length <= PAGE_SIZE) { + memcpy(metadata->verity_table, page_address(payload.page_io[0]) + + sizeof(struct android_metadata_header), + table_length); + } else { + copy_length = PAGE_SIZE - + sizeof(struct android_metadata_header); + memcpy(metadata->verity_table, page_address(payload.page_io[0]) + + sizeof(struct android_metadata_header), + copy_length); + table_length -= copy_length; + offset = copy_length; + i = 1; + while (table_length != 0) { + if (table_length > PAGE_SIZE) { + memcpy(metadata->verity_table + offset, + page_address(payload.page_io[i]), + PAGE_SIZE); + offset += PAGE_SIZE; + table_length -= PAGE_SIZE; + } else { + memcpy(metadata->verity_table + offset, + page_address(payload.page_io[i]), + table_length); + table_length = 0; + } + i++; + } + } + metadata->verity_table[table_length] = '\0'; + + goto free_payload; + +free_metadata: + kfree(metadata); +free_header: + kfree(header); + metadata = ERR_PTR(err); +free_payload: + for (i = 0; i < payload.number_of_pages; i++) + if (payload.page_io[i]) + __free_page(payload.page_io[i]); + kfree(payload.page_io); + + DMINFO("verity_table: %s", metadata->verity_table); +blkdev_release: + blkdev_put(bdev, FMODE_READ); + return metadata; +} + +/* helper functions to extract properties from dts */ +const char *find_dt_value(const char *name) +{ + struct device_node *firmware; + const char *value; + + firmware = of_find_node_by_path("/firmware/android"); + if (!firmware) + return NULL; + value = of_get_property(firmware, name, NULL); + of_node_put(firmware); + + return value; +} + +static bool is_unlocked(void) +{ + static const char unlocked[] = "orange"; + static const char verified_boot_prop[] = "verifiedbootstate"; + const char *value; + + value = find_dt_value(verified_boot_prop); + if (!value) + value = verifiedbootstate; + + return !strncmp(value, unlocked, sizeof(unlocked) - 1); +} + +static int verity_mode(void) +{ + static const char enforcing[] = "enforcing"; + static const char verified_mode_prop[] = "veritymode"; + const char *value; + + value = find_dt_value(verified_mode_prop); + if (!value) + value = veritymode; + if (!strncmp(value, enforcing, sizeof(enforcing) - 1)) + return DM_VERITY_MODE_RESTART; + + return DM_VERITY_MODE_EIO; +} + +static int verify_header(struct android_metadata_header *header) +{ + int retval = -EINVAL; + + if (is_unlocked() && le32_to_cpu(header->magic_number) == + VERITY_METADATA_MAGIC_DISABLE) { + retval = VERITY_STATE_DISABLE; + return retval; + } + + if (!(le32_to_cpu(header->magic_number) == + VERITY_METADATA_MAGIC_NUMBER) || + (le32_to_cpu(header->magic_number) == + VERITY_METADATA_MAGIC_DISABLE)) { + DMERR("Incorrect magic number"); + return retval; + } + + if (le32_to_cpu(header->protocol_version) != + VERITY_METADATA_VERSION) { + DMERR("Unsupported version %u", + le32_to_cpu(header->protocol_version)); + return retval; + } + + return 0; +} + +static int verify_verity_signature(char *key_id, + struct android_metadata *metadata) +{ + key_ref_t key_ref; + struct key *key; + struct public_key_signature *pks = NULL; + int retval = -EINVAL; + + key_ref = keyring_search(make_key_ref(system_trusted_keyring, 1), + &key_type_asymmetric, key_id); + + if (IS_ERR(key_ref)) { + DMERR("keyring: key not found"); + return -ENOKEY; + } + + key = key_ref_to_ptr(key_ref); + + pks = table_make_digest(HASH_ALGO_SHA256, + (const void *)metadata->verity_table, + le32_to_cpu(metadata->header->table_length)); + + if (IS_ERR(pks)) { + DMERR("hashing failed"); + goto error; + } + + retval = table_extract_mpi_array(pks, &metadata->header->signature[0], + RSANUMBYTES); + if (retval < 0) { + DMERR("Error extracting mpi %d", retval); + goto error; + } + + retval = verify_signature(key, pks); + mpi_free(pks->rsa.s); +error: + kfree(pks); + key_put(key); + + return retval; +} + +static void handle_error(void) +{ + int mode = verity_mode(); + if (mode == DM_VERITY_MODE_RESTART) { + DMERR("triggering restart"); + kernel_restart("dm-verity device corrupted"); + } else { + DMERR("Mounting verity root failed"); + } +} + +static inline bool test_mult_overflow(sector_t a, u32 b) +{ + sector_t r = (sector_t)~0ULL; + + sector_div(r, b); + return a > r; +} + +/* + * Target parameters: + * <key id> Key id of the public key in the system keyring. + * Verity metadata's signature would be verified against + * this. If the key id contains spaces, replace them + * with '#'. + * <block device> The block device for which dm-verity is being setup. + */ +static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv) +{ + dev_t uninitialized_var(dev); + struct android_metadata *uninitialized_var(metadata); + int err = 0, i, mode; + char *key_id, *table_ptr, dummy, + *verity_table_args[VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS]; + /* One for specifying number of opt args and one for mode */ + sector_t data_sectors; + u32 data_block_size; + unsigned int major, minor, + no_of_args = VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS; + struct fec_header uninitialized_var(fec); + struct fec_ecc_metadata uninitialized_var(ecc); + char buf[FEC_ARG_LENGTH], *buf_ptr; + unsigned long long tmpll; + + if (argc != 2) { + DMERR("Incorrect number of arguments"); + handle_error(); + return -EINVAL; + } + + /* should come as one of the arguments for the verity target */ + key_id = argv[0]; + strreplace(argv[0], '#', ' '); + + if (sscanf(argv[1], "%u:%u%c", &major, &minor, &dummy) == 2) { + dev = MKDEV(major, minor); + if (MAJOR(dev) != major || MINOR(dev) != minor) { + DMERR("Incorrect bdev major minor number"); + handle_error(); + return -EOVERFLOW; + } + } + + DMINFO("key:%s dev:%s", argv[0], argv[1]); + + if (extract_fec_header(dev, &fec, &ecc)) { + DMERR("Error while extracting fec header"); + handle_error(); + return -EINVAL; + } + + metadata = extract_metadata(dev, &fec); + + if (IS_ERR(metadata)) { + DMERR("Error while extracting metadata"); + handle_error(); + return -EINVAL; + } + + err = verify_header(metadata->header); + + if (err == VERITY_STATE_DISABLE) { + DMERR("Mounting root with verity disabled"); + return -EINVAL; + } else if (err) { + DMERR("Verity header handle error"); + handle_error(); + goto free_metadata; + } + + err = verify_verity_signature(key_id, metadata); + + if (err) { + DMERR("Signature verification failed"); + handle_error(); + goto free_metadata; + } else + DMINFO("Signature verification success"); + + table_ptr = metadata->verity_table; + + for (i = 0; i < VERITY_TABLE_ARGS; i++) { + verity_table_args[i] = strsep(&table_ptr, " "); + if (verity_table_args[i] == NULL) + break; + } + + if (i != VERITY_TABLE_ARGS) { + DMERR("Verity table not in the expected format"); + err = -EINVAL; + handle_error(); + goto free_metadata; + } + + if (sscanf(verity_table_args[5], "%llu%c", &tmpll, &dummy) + != 1) { + DMERR("Verity table not in the expected format"); + handle_error(); + err = -EINVAL; + goto free_metadata; + } + + if (tmpll > ULONG_MAX) { + DMERR("<num_data_blocks> too large. Forgot to turn on CONFIG_LBDAF?"); + handle_error(); + err = -EINVAL; + goto free_metadata; + } + + data_sectors = tmpll; + + if (sscanf(verity_table_args[3], "%u%c", &data_block_size, &dummy) + != 1) { + DMERR("Verity table not in the expected format"); + handle_error(); + err = -EINVAL; + goto free_metadata; + } + + if (test_mult_overflow(data_sectors, data_block_size >> + SECTOR_SHIFT)) { + DMERR("data_sectors too large"); + handle_error(); + err = -EOVERFLOW; + goto free_metadata; + } + + data_sectors *= data_block_size >> SECTOR_SHIFT; + DMINFO("Data sectors %llu", (unsigned long long)data_sectors); + + /* update target length */ + ti->len = data_sectors; + + /*substitute data_dev and hash_dev*/ + verity_table_args[1] = argv[1]; + verity_table_args[2] = argv[1]; + + mode = verity_mode(); + + if (ecc.valid && IS_BUILTIN(CONFIG_DM_VERITY_FEC)) { + if (mode) { + err = snprintf(buf, FEC_ARG_LENGTH, + "%u %s " VERITY_TABLE_OPT_FEC_FORMAT, + 1 + VERITY_TABLE_OPT_FEC_ARGS, + mode == DM_VERITY_MODE_RESTART ? + VERITY_TABLE_OPT_RESTART : VERITY_TABLE_OPT_LOGGING, + argv[1], ecc.start / FEC_BLOCK_SIZE, ecc.blocks, + ecc.roots); + } else { + err = snprintf(buf, FEC_ARG_LENGTH, + "%u " VERITY_TABLE_OPT_FEC_FORMAT, + VERITY_TABLE_OPT_FEC_ARGS, argv[1], + ecc.start / FEC_BLOCK_SIZE, ecc.blocks, ecc.roots); + } + } else if (mode) { + err = snprintf(buf, FEC_ARG_LENGTH, + "2 " VERITY_TABLE_OPT_IGNZERO " %s", + mode == DM_VERITY_MODE_RESTART ? + VERITY_TABLE_OPT_RESTART : VERITY_TABLE_OPT_LOGGING); + } else { + err = snprintf(buf, FEC_ARG_LENGTH, "1 %s", + "ignore_zero_blocks"); + } + + if (err < 0 || err >= FEC_ARG_LENGTH) + goto free_metadata; + + buf_ptr = buf; + + for (i = VERITY_TABLE_ARGS; i < (VERITY_TABLE_ARGS + + VERITY_TABLE_OPT_FEC_ARGS + 2); i++) { + verity_table_args[i] = strsep(&buf_ptr, " "); + if (verity_table_args[i] == NULL) { + no_of_args = i; + break; + } + } + + err = verity_ctr(ti, no_of_args, verity_table_args); + +free_metadata: + kfree(metadata->header); + kfree(metadata->verity_table); + kfree(metadata); + return err; +} + +static struct target_type android_verity_target = { + .name = "android-verity", + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = android_verity_ctr, + .dtr = verity_dtr, + .map = verity_map, + .status = verity_status, + .ioctl = verity_ioctl, + .merge = verity_merge, + .iterate_devices = verity_iterate_devices, + .io_hints = verity_io_hints, +}; + +static int __init dm_android_verity_init(void) +{ + int r; + + r = dm_register_target(&android_verity_target); + if (r < 0) + DMERR("register failed %d", r); + + return r; +} + +static void __exit dm_android_verity_exit(void) +{ + dm_unregister_target(&android_verity_target); +} + +module_init(dm_android_verity_init); +module_exit(dm_android_verity_exit); diff --git a/drivers/md/dm-android-verity.h b/drivers/md/dm-android-verity.h new file mode 100644 index 000000000000..11477ffd2243 --- /dev/null +++ b/drivers/md/dm-android-verity.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#ifndef DM_ANDROID_VERITY_H +#define DM_ANDROID_VERITY_H + +#include <crypto/sha.h> + +#define RSANUMBYTES 256 +#define VERITY_METADATA_MAGIC_NUMBER 0xb001b001 +#define VERITY_METADATA_MAGIC_DISABLE 0x46464f56 +#define VERITY_METADATA_VERSION 0 +#define VERITY_STATE_DISABLE 1 +#define DATA_BLOCK_SIZE (4 * 1024) +#define VERITY_METADATA_SIZE (8 * DATA_BLOCK_SIZE) +#define VERITY_TABLE_ARGS 10 +#define VERITY_COMMANDLINE_PARAM_LENGTH 20 + +#define FEC_MAGIC 0xFECFECFE +#define FEC_BLOCK_SIZE (4 * 1024) +#define FEC_VERSION 0 +#define FEC_RSM 255 +#define FEC_ARG_LENGTH 300 + +#define VERITY_TABLE_OPT_RESTART "restart_on_corruption" +#define VERITY_TABLE_OPT_LOGGING "ignore_corruption" +#define VERITY_TABLE_OPT_IGNZERO "ignore_zero_blocks" + +#define VERITY_TABLE_OPT_FEC_FORMAT \ + "use_fec_from_device %s fec_start %llu fec_blocks %llu fec_roots %u ignore_zero_blocks" +#define VERITY_TABLE_OPT_FEC_ARGS 9 + +#define VERITY_DEBUG 0 + +#define DM_MSG_PREFIX "android-verity" +/* + * There can be two formats. + * if fec is present + * <data_blocks> <verity_tree> <verity_metdata_32K><fec_data><fec_data_4K> + * if fec is not present + * <data_blocks> <verity_tree> <verity_metdata_32K> + */ +/* TODO: rearrange structure to reduce memory holes + * depends on userspace change. + */ +struct fec_header { + __le32 magic; + __le32 version; + __le32 size; + __le32 roots; + __le32 fec_size; + __le64 inp_size; + u8 hash[SHA256_DIGEST_SIZE]; +}; + +struct android_metadata_header { + __le32 magic_number; + __le32 protocol_version; + char signature[RSANUMBYTES]; + __le32 table_length; +}; + +struct android_metadata { + struct android_metadata_header *header; + char *verity_table; +}; + +struct fec_ecc_metadata { + bool valid; + u32 roots; + u64 blocks; + u64 rounds; + u64 start; +}; + +struct bio_read { + struct page **page_io; + int number_of_pages; +}; + +#endif /* DM_ANDROID_VERITY_H */ diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 720ceeb7fa9b..5407a53631b5 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1925,6 +1925,45 @@ void dm_interface_exit(void) dm_hash_exit(); } + +/** + * dm_ioctl_export - Permanently export a mapped device via the ioctl interface + * @md: Pointer to mapped_device + * @name: Buffer (size DM_NAME_LEN) for name + * @uuid: Buffer (size DM_UUID_LEN) for uuid or NULL if not desired + */ +int dm_ioctl_export(struct mapped_device *md, const char *name, + const char *uuid) +{ + int r = 0; + struct hash_cell *hc; + + if (!md) { + r = -ENXIO; + goto out; + } + + /* The name and uuid can only be set once. */ + mutex_lock(&dm_hash_cells_mutex); + hc = dm_get_mdptr(md); + mutex_unlock(&dm_hash_cells_mutex); + if (hc) { + DMERR("%s: already exported", dm_device_name(md)); + r = -ENXIO; + goto out; + } + + r = dm_hash_insert(name, uuid, md); + if (r) { + DMERR("%s: could not bind to '%s'", dm_device_name(md), name); + goto out; + } + + /* Let udev know we've changed. */ + dm_kobject_uevent(md, KOBJ_CHANGE, dm_get_event_nr(md)); +out: + return r; +} /** * dm_copy_name_and_uuid - Copy mapped device name & uuid into supplied buffers * @md: Pointer to mapped_device diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 16ba55ad7089..e39e3e3f4037 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -11,6 +11,7 @@ #include <linux/vmalloc.h> #include <linux/blkdev.h> #include <linux/namei.h> +#include <linux/mount.h> #include <linux/ctype.h> #include <linux/string.h> #include <linux/slab.h> diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c new file mode 100644 index 000000000000..1cc10c4de701 --- /dev/null +++ b/drivers/md/dm-verity-fec.c @@ -0,0 +1,818 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen <samitolvanen@google.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; either version 2 of the License, or (at your option) + * any later version. + */ + +#include "dm-verity-fec.h" +#include <linux/math64.h> + +#define DM_MSG_PREFIX "verity-fec" + +/* + * If error correction has been configured, returns true. + */ +bool verity_fec_is_enabled(struct dm_verity *v) +{ + return v->fec && v->fec->dev; +} + +/* + * Return a pointer to dm_verity_fec_io after dm_verity_io and its variable + * length fields. + */ +static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io) +{ + return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io); +} + +/* + * Return an interleaved offset for a byte in RS block. + */ +static inline u64 fec_interleave(struct dm_verity *v, u64 offset) +{ + u32 mod; + + mod = do_div(offset, v->fec->rsn); + return offset + mod * (v->fec->rounds << v->data_dev_block_bits); +} + +/* + * Decode an RS block using Reed-Solomon. + */ +static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, + u8 *data, u8 *fec, int neras) +{ + int i; + uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; + + for (i = 0; i < v->fec->roots; i++) + par[i] = fec[i]; + + return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, + fio->erasures, 0, NULL); +} + +/* + * Read error-correcting codes for the requested RS block. Returns a pointer + * to the data block. Caller is responsible for releasing buf. + */ +static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, + unsigned *offset, struct dm_buffer **buf) +{ + u64 position, block; + u8 *res; + + position = (index + rsb) * v->fec->roots; + block = position >> v->data_dev_block_bits; + *offset = (unsigned)(position - (block << v->data_dev_block_bits)); + + res = dm_bufio_read(v->fec->bufio, v->fec->start + block, buf); + if (unlikely(IS_ERR(res))) { + DMERR("%s: FEC %llu: parity read failed (block %llu): %ld", + v->data_dev->name, (unsigned long long)rsb, + (unsigned long long)(v->fec->start + block), + PTR_ERR(res)); + *buf = NULL; + } + + return res; +} + +/* Loop over each preallocated buffer slot. */ +#define fec_for_each_prealloc_buffer(__i) \ + for (__i = 0; __i < DM_VERITY_FEC_BUF_PREALLOC; __i++) + +/* Loop over each extra buffer slot. */ +#define fec_for_each_extra_buffer(io, __i) \ + for (__i = DM_VERITY_FEC_BUF_PREALLOC; __i < DM_VERITY_FEC_BUF_MAX; __i++) + +/* Loop over each allocated buffer. */ +#define fec_for_each_buffer(io, __i) \ + for (__i = 0; __i < (io)->nbufs; __i++) + +/* Loop over each RS block in each allocated buffer. */ +#define fec_for_each_buffer_rs_block(io, __i, __j) \ + fec_for_each_buffer(io, __i) \ + for (__j = 0; __j < 1 << DM_VERITY_FEC_BUF_RS_BITS; __j++) + +/* + * Return a pointer to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline u8 *fec_buffer_rs_block(struct dm_verity *v, + struct dm_verity_fec_io *fio, + unsigned i, unsigned j) +{ + return &fio->bufs[i][j * v->fec->rsn]; +} + +/* + * Return an index to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j) +{ + return (i << DM_VERITY_FEC_BUF_RS_BITS) + j; +} + +/* + * Decode all RS blocks from buffers and copy corrected bytes into fio->output + * starting from block_offset. + */ +static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, + u64 rsb, int byte_index, unsigned block_offset, + int neras) +{ + int r, corrected = 0, res; + struct dm_buffer *buf; + unsigned n, i, offset; + u8 *par, *block; + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (IS_ERR(par)) + return PTR_ERR(par); + + /* + * Decode the RS blocks we have in bufs. Each RS block results in + * one corrected target byte and consumes fec->roots parity bytes. + */ + fec_for_each_buffer_rs_block(fio, n, i) { + block = fec_buffer_rs_block(v, fio, n, i); + res = fec_decode_rs8(v, fio, block, &par[offset], neras); + if (res < 0) { + dm_bufio_release(buf); + + r = res; + goto error; + } + + corrected += res; + fio->output[block_offset] = block[byte_index]; + + block_offset++; + if (block_offset >= 1 << v->data_dev_block_bits) + goto done; + + /* read the next block when we run out of parity bytes */ + offset += v->fec->roots; + if (offset >= 1 << v->data_dev_block_bits) { + dm_bufio_release(buf); + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (unlikely(IS_ERR(par))) + return PTR_ERR(par); + } + } +done: + r = corrected; +error: + if (r < 0 && neras) + DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", + v->data_dev->name, (unsigned long long)rsb, r); + else if (r > 0) + DMWARN_LIMIT("%s: FEC %llu: corrected %d errors", + v->data_dev->name, (unsigned long long)rsb, r); + + return r; +} + +/* + * Locate data block erasures using verity hashes. + */ +static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, + u8 *want_digest, u8 *data) +{ + if (unlikely(verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)))) + return 0; + + return memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) != 0; +} + +/* + * Read data blocks that are part of the RS block and deinterleave as much as + * fits into buffers. Check for erasure locations if @neras is non-NULL. + */ +static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, + u64 rsb, u64 target, unsigned block_offset, + int *neras) +{ + bool is_zero; + int i, j, target_index = -1; + struct dm_buffer *buf; + struct dm_bufio_client *bufio; + struct dm_verity_fec_io *fio = fec_io(io); + u64 block, ileaved; + u8 *bbuf, *rs_block; + u8 want_digest[v->digest_size]; + unsigned n, k; + + if (neras) + *neras = 0; + + /* + * read each of the rsn data blocks that are part of the RS block, and + * interleave contents to available bufs + */ + for (i = 0; i < v->fec->rsn; i++) { + ileaved = fec_interleave(v, rsb * v->fec->rsn + i); + + /* + * target is the data block we want to correct, target_index is + * the index of this block within the rsn RS blocks + */ + if (ileaved == target) + target_index = i; + + block = ileaved >> v->data_dev_block_bits; + bufio = v->fec->data_bufio; + + if (block >= v->data_blocks) { + block -= v->data_blocks; + + /* + * blocks outside the area were assumed to contain + * zeros when encoding data was generated + */ + if (unlikely(block >= v->fec->hash_blocks)) + continue; + + block += v->hash_start; + bufio = v->bufio; + } + + bbuf = dm_bufio_read(bufio, block, &buf); + if (unlikely(IS_ERR(bbuf))) { + DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld", + v->data_dev->name, + (unsigned long long)rsb, + (unsigned long long)block, PTR_ERR(bbuf)); + + /* assume the block is corrupted */ + if (neras && *neras <= v->fec->roots) + fio->erasures[(*neras)++] = i; + + continue; + } + + /* locate erasures if the block is on the data device */ + if (bufio == v->fec->data_bufio && + verity_hash_for_block(v, io, block, want_digest, + &is_zero) == 0) { + /* skip known zero blocks entirely */ + if (is_zero) + continue; + + /* + * skip if we have already found the theoretical + * maximum number (i.e. fec->roots) of erasures + */ + if (neras && *neras <= v->fec->roots && + fec_is_erasure(v, io, want_digest, bbuf)) + fio->erasures[(*neras)++] = i; + } + + /* + * deinterleave and copy the bytes that fit into bufs, + * starting from block_offset + */ + fec_for_each_buffer_rs_block(fio, n, j) { + k = fec_buffer_rs_index(n, j) + block_offset; + + if (k >= 1 << v->data_dev_block_bits) + goto done; + + rs_block = fec_buffer_rs_block(v, fio, n, j); + rs_block[i] = bbuf[k]; + } +done: + dm_bufio_release(buf); + } + + return target_index; +} + +/* + * Allocate RS control structure and FEC buffers from preallocated mempools, + * and attempt to allocate as many extra buffers as available. + */ +static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + if (!fio->rs) { + fio->rs = mempool_alloc(v->fec->rs_pool, 0); + if (unlikely(!fio->rs)) { + DMERR("failed to allocate RS"); + return -ENOMEM; + } + } + + fec_for_each_prealloc_buffer(n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOIO); + if (unlikely(!fio->bufs[n])) { + DMERR("failed to allocate FEC buffer"); + return -ENOMEM; + } + } + + /* try to allocate the maximum number of buffers */ + fec_for_each_extra_buffer(fio, n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOIO); + /* we can manage with even one buffer if necessary */ + if (unlikely(!fio->bufs[n])) + break; + } + fio->nbufs = n; + + if (!fio->output) { + fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO); + + if (!fio->output) { + DMERR("failed to allocate FEC page"); + return -ENOMEM; + } + } + + return 0; +} + +/* + * Initialize buffers and clear erasures. fec_read_bufs() assumes buffers are + * zeroed before deinterleaving. + */ +static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + fec_for_each_buffer(fio, n) + memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS); + + memset(fio->erasures, 0, sizeof(fio->erasures)); +} + +/* + * Decode all RS blocks in a single data block and return the target block + * (indicated by @offset) in fio->output. If @use_erasures is non-zero, uses + * hashes to locate erasures. + */ +static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, + struct dm_verity_fec_io *fio, u64 rsb, u64 offset, + bool use_erasures) +{ + int r, neras = 0; + unsigned pos; + + r = fec_alloc_bufs(v, fio); + if (unlikely(r < 0)) + return r; + + for (pos = 0; pos < 1 << v->data_dev_block_bits; ) { + fec_init_bufs(v, fio); + + r = fec_read_bufs(v, io, rsb, offset, pos, + use_erasures ? &neras : NULL); + if (unlikely(r < 0)) + return r; + + r = fec_decode_bufs(v, fio, rsb, r, pos, neras); + if (r < 0) + return r; + + pos += fio->nbufs << DM_VERITY_FEC_BUF_RS_BITS; + } + + /* Always re-validate the corrected block against the expected hash */ + r = verity_hash(v, verity_io_hash_desc(v, io), fio->output, + 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) + return r; + + if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io), + v->digest_size)) { + DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)", + v->data_dev->name, (unsigned long long)rsb, neras); + return -EILSEQ; + } + + return 0; +} + +static int fec_bv_copy(struct dm_verity *v, struct dm_verity_io *io, u8 *data, + size_t len) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + memcpy(data, &fio->output[fio->output_pos], len); + fio->output_pos += len; + + return 0; +} + +/* + * Correct errors in a block. Copies corrected block to dest if non-NULL, + * otherwise to a bio_vec starting from iter. + */ +int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + int r; + struct dm_verity_fec_io *fio = fec_io(io); + u64 offset, res, rsb; + + if (!verity_fec_is_enabled(v)) + return -EOPNOTSUPP; + + if (type == DM_VERITY_BLOCK_TYPE_METADATA) + block += v->data_blocks; + + /* + * For RS(M, N), the continuous FEC data is divided into blocks of N + * bytes. Since block size may not be divisible by N, the last block + * is zero padded when decoding. + * + * Each byte of the block is covered by a different RS(M, N) code, + * and each code is interleaved over N blocks to make it less likely + * that bursty corruption will leave us in unrecoverable state. + */ + + offset = block << v->data_dev_block_bits; + + res = offset; + div64_u64(res, v->fec->rounds << v->data_dev_block_bits); + + /* + * The base RS block we can feed to the interleaver to find out all + * blocks required for decoding. + */ + rsb = offset - res * (v->fec->rounds << v->data_dev_block_bits); + + /* + * Locating erasures is slow, so attempt to recover the block without + * them first. Do a second attempt with erasures if the corruption is + * bad enough. + */ + r = fec_decode_rsb(v, io, fio, rsb, offset, false); + if (r < 0) { + r = fec_decode_rsb(v, io, fio, rsb, offset, true); + if (r < 0) + return r; + } + + if (dest) + memcpy(dest, fio->output, 1 << v->data_dev_block_bits); + else if (iter) { + fio->output_pos = 0; + r = verity_for_bv_block(v, io, iter, fec_bv_copy); + } + + return r; +} + +/* + * Clean up per-bio data. + */ +void verity_fec_finish_io(struct dm_verity_io *io) +{ + unsigned n; + struct dm_verity_fec *f = io->v->fec; + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + mempool_free(fio->rs, f->rs_pool); + + fec_for_each_prealloc_buffer(n) + mempool_free(fio->bufs[n], f->prealloc_pool); + + fec_for_each_extra_buffer(fio, n) + mempool_free(fio->bufs[n], f->extra_pool); + + mempool_free(fio->output, f->output_pool); +} + +/* + * Initialize per-bio data. + */ +void verity_fec_init_io(struct dm_verity_io *io) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + fio->rs = NULL; + memset(fio->bufs, 0, sizeof(fio->bufs)); + fio->nbufs = 0; + fio->output = NULL; +} + +/* + * Append feature arguments and values to the status table. + */ +unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen) +{ + if (!verity_fec_is_enabled(v)) + return sz; + + DMEMIT(" " DM_VERITY_OPT_FEC_DEV " %s " + DM_VERITY_OPT_FEC_BLOCKS " %llu " + DM_VERITY_OPT_FEC_START " %llu " + DM_VERITY_OPT_FEC_ROOTS " %d", + v->fec->dev->name, + (unsigned long long)v->fec->blocks, + (unsigned long long)v->fec->start, + v->fec->roots); + + return sz; +} + +void verity_fec_dtr(struct dm_verity *v) +{ + struct dm_verity_fec *f = v->fec; + + if (!verity_fec_is_enabled(v)) + goto out; + + mempool_destroy(f->rs_pool); + mempool_destroy(f->prealloc_pool); + mempool_destroy(f->extra_pool); + kmem_cache_destroy(f->cache); + + if (f->data_bufio) + dm_bufio_client_destroy(f->data_bufio); + if (f->bufio) + dm_bufio_client_destroy(f->bufio); + + if (f->dev) + dm_put_device(v->ti, f->dev); +out: + kfree(f); + v->fec = NULL; +} + +static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data) +{ + struct dm_verity *v = (struct dm_verity *)pool_data; + + return init_rs(8, 0x11d, 0, 1, v->fec->roots); +} + +static void fec_rs_free(void *element, void *pool_data) +{ + struct rs_control *rs = (struct rs_control *)element; + + if (rs) + free_rs(rs); +} + +bool verity_is_fec_opt_arg(const char *arg_name) +{ + return (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_START) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)); +} + +int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, + unsigned *argc, const char *arg_name) +{ + int r; + struct dm_target *ti = v->ti; + const char *arg_value; + unsigned long long num_ll; + unsigned char num_c; + char dummy; + + if (!*argc) { + ti->error = "FEC feature arguments require a value"; + return -EINVAL; + } + + arg_value = dm_shift_arg(as); + (*argc)--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { + r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev); + if (r) { + ti->error = "FEC device lookup failed"; + return r; + } + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) + >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + v->fec->blocks = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) >> + (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_START; + return -EINVAL; + } + v->fec->start = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)) { + if (sscanf(arg_value, "%hhu%c", &num_c, &dummy) != 1 || !num_c || + num_c < (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MAX_RSN) || + num_c > (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + v->fec->roots = num_c; + + } else { + ti->error = "Unrecognized verity FEC feature request"; + return -EINVAL; + } + + return 0; +} + +/* + * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr. + */ +int verity_fec_ctr_alloc(struct dm_verity *v) +{ + struct dm_verity_fec *f; + + f = kzalloc(sizeof(struct dm_verity_fec), GFP_KERNEL); + if (!f) { + v->ti->error = "Cannot allocate FEC structure"; + return -ENOMEM; + } + v->fec = f; + + return 0; +} + +/* + * Validate arguments and preallocate memory. Must be called after arguments + * have been parsed using verity_fec_parse_opt_args. + */ +int verity_fec_ctr(struct dm_verity *v) +{ + struct dm_verity_fec *f = v->fec; + struct dm_target *ti = v->ti; + u64 hash_blocks; + + if (!verity_fec_is_enabled(v)) { + verity_fec_dtr(v); + return 0; + } + + /* + * FEC is computed over data blocks, possible metadata, and + * hash blocks. In other words, FEC covers total of fec_blocks + * blocks consisting of the following: + * + * data blocks | hash blocks | metadata (optional) + * + * We allow metadata after hash blocks to support a use case + * where all data is stored on the same device and FEC covers + * the entire area. + * + * If metadata is included, we require it to be available on the + * hash device after the hash blocks. + */ + + hash_blocks = v->hash_blocks - v->hash_start; + + /* + * Require matching block sizes for data and hash devices for + * simplicity. + */ + if (v->data_dev_block_bits != v->hash_dev_block_bits) { + ti->error = "Block sizes must match to use FEC"; + return -EINVAL; + } + + if (!f->roots) { + ti->error = "Missing " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + f->rsn = DM_VERITY_FEC_RSM - f->roots; + + if (!f->blocks) { + ti->error = "Missing " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + f->rounds = f->blocks; + if (sector_div(f->rounds, f->rsn)) + f->rounds++; + + /* + * Due to optional metadata, f->blocks can be larger than + * data_blocks and hash_blocks combined. + */ + if (f->blocks < v->data_blocks + hash_blocks || !f->rounds) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + /* + * Metadata is accessed through the hash device, so we require + * it to be large enough. + */ + f->hash_blocks = f->blocks - v->data_blocks; + if (dm_bufio_get_device_size(v->bufio) < f->hash_blocks) { + ti->error = "Hash device is too small for " + DM_VERITY_OPT_FEC_BLOCKS; + return -E2BIG; + } + + f->bufio = dm_bufio_client_create(f->dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->bufio)) { + ti->error = "Cannot initialize FEC bufio client"; + return PTR_ERR(f->bufio); + } + + if (dm_bufio_get_device_size(f->bufio) < + ((f->start + f->rounds * f->roots) >> v->data_dev_block_bits)) { + ti->error = "FEC device is too small"; + return -E2BIG; + } + + f->data_bufio = dm_bufio_client_create(v->data_dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->data_bufio)) { + ti->error = "Cannot initialize FEC data bufio client"; + return PTR_ERR(f->data_bufio); + } + + if (dm_bufio_get_device_size(f->data_bufio) < v->data_blocks) { + ti->error = "Data device is too small"; + return -E2BIG; + } + + /* Preallocate an rs_control structure for each worker thread */ + f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc, + fec_rs_free, (void *) v); + if (!f->rs_pool) { + ti->error = "Cannot allocate RS pool"; + return -ENOMEM; + } + + f->cache = kmem_cache_create("dm_verity_fec_buffers", + f->rsn << DM_VERITY_FEC_BUF_RS_BITS, + 0, 0, NULL); + if (!f->cache) { + ti->error = "Cannot create FEC buffer cache"; + return -ENOMEM; + } + + /* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */ + f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() * + DM_VERITY_FEC_BUF_PREALLOC, + f->cache); + if (!f->prealloc_pool) { + ti->error = "Cannot allocate FEC buffer prealloc pool"; + return -ENOMEM; + } + + f->extra_pool = mempool_create_slab_pool(0, f->cache); + if (!f->extra_pool) { + ti->error = "Cannot allocate FEC buffer extra pool"; + return -ENOMEM; + } + + /* Preallocate an output buffer for each thread */ + f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(), + 1 << v->data_dev_block_bits); + if (!f->output_pool) { + ti->error = "Cannot allocate FEC output pool"; + return -ENOMEM; + } + + /* Reserve space for our per-bio data */ + ti->per_bio_data_size += sizeof(struct dm_verity_fec_io); + + return 0; +} diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h new file mode 100644 index 000000000000..7fa0298b995e --- /dev/null +++ b/drivers/md/dm-verity-fec.h @@ -0,0 +1,152 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen <samitolvanen@google.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; either version 2 of the License, or (at your option) + * any later version. + */ + +#ifndef DM_VERITY_FEC_H +#define DM_VERITY_FEC_H + +#include "dm-verity.h" +#include <linux/rslib.h> + +/* Reed-Solomon(M, N) parameters */ +#define DM_VERITY_FEC_RSM 255 +#define DM_VERITY_FEC_MAX_RSN 253 +#define DM_VERITY_FEC_MIN_RSN 231 /* ~10% space overhead */ + +/* buffers for deinterleaving and decoding */ +#define DM_VERITY_FEC_BUF_PREALLOC 1 /* buffers to preallocate */ +#define DM_VERITY_FEC_BUF_RS_BITS 4 /* 1 << RS blocks per buffer */ +/* we need buffers for at most 1 << block size RS blocks */ +#define DM_VERITY_FEC_BUF_MAX \ + (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) + +#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" +#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" +#define DM_VERITY_OPT_FEC_START "fec_start" +#define DM_VERITY_OPT_FEC_ROOTS "fec_roots" + +/* configuration */ +struct dm_verity_fec { + struct dm_dev *dev; /* parity data device */ + struct dm_bufio_client *data_bufio; /* for data dev access */ + struct dm_bufio_client *bufio; /* for parity data access */ + sector_t start; /* parity data start in blocks */ + sector_t blocks; /* number of blocks covered */ + sector_t rounds; /* number of interleaving rounds */ + sector_t hash_blocks; /* blocks covered after v->hash_start */ + unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */ + unsigned char rsn; /* N of RS(M, N) */ + mempool_t *rs_pool; /* mempool for fio->rs */ + mempool_t *prealloc_pool; /* mempool for preallocated buffers */ + mempool_t *extra_pool; /* mempool for extra buffers */ + mempool_t *output_pool; /* mempool for output */ + struct kmem_cache *cache; /* cache for buffers */ +}; + +/* per-bio data */ +struct dm_verity_fec_io { + struct rs_control *rs; /* Reed-Solomon state */ + int erasures[DM_VERITY_FEC_MAX_RSN]; /* erasures for decode_rs8 */ + u8 *bufs[DM_VERITY_FEC_BUF_MAX]; /* bufs for deinterleaving */ + unsigned nbufs; /* number of buffers allocated */ + u8 *output; /* buffer for corrected output */ + size_t output_pos; +}; + +#ifdef CONFIG_DM_VERITY_FEC + +/* each feature parameter requires a value */ +#define DM_VERITY_OPTS_FEC 8 + +extern bool verity_fec_is_enabled(struct dm_verity *v); + +extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, + u8 *dest, struct bvec_iter *iter); + +extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen); + +extern void verity_fec_finish_io(struct dm_verity_io *io); +extern void verity_fec_init_io(struct dm_verity_io *io); + +extern bool verity_is_fec_opt_arg(const char *arg_name); +extern int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, unsigned *argc, + const char *arg_name); + +extern void verity_fec_dtr(struct dm_verity *v); + +extern int verity_fec_ctr_alloc(struct dm_verity *v); +extern int verity_fec_ctr(struct dm_verity *v); + +#else /* !CONFIG_DM_VERITY_FEC */ + +#define DM_VERITY_OPTS_FEC 0 + +static inline bool verity_fec_is_enabled(struct dm_verity *v) +{ + return false; +} + +static inline int verity_fec_decode(struct dm_verity *v, + struct dm_verity_io *io, + enum verity_block_type type, + sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + return -EOPNOTSUPP; +} + +static inline unsigned verity_fec_status_table(struct dm_verity *v, + unsigned sz, char *result, + unsigned maxlen) +{ + return sz; +} + +static inline void verity_fec_finish_io(struct dm_verity_io *io) +{ +} + +static inline void verity_fec_init_io(struct dm_verity_io *io) +{ +} + +static inline bool verity_is_fec_opt_arg(const char *arg_name) +{ + return false; +} + +static inline int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, + unsigned *argc, + const char *arg_name) +{ + return -EINVAL; +} + +static inline void verity_fec_dtr(struct dm_verity *v) +{ +} + +static inline int verity_fec_ctr_alloc(struct dm_verity *v) +{ + return 0; +} + +static inline int verity_fec_ctr(struct dm_verity *v) +{ + return 0; +} + +#endif /* CONFIG_DM_VERITY_FEC */ + +#endif /* DM_VERITY_FEC_H */ diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity-target.c index 66616db33e6f..713bdb2726f9 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity-target.c @@ -14,12 +14,11 @@ * access behavior. */ -#include "dm-bufio.h" +#include "dm-verity.h" +#include "dm-verity-fec.h" #include <linux/module.h> -#include <linux/device-mapper.h> #include <linux/reboot.h> -#include <crypto/hash.h> #define DM_MSG_PREFIX "verity" @@ -30,85 +29,18 @@ #define DM_VERITY_MEMPOOL_SIZE 4 #define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144 -#define DM_VERITY_MAX_LEVELS 63 #define DM_VERITY_MAX_CORRUPTED_ERRS 100 #define DM_VERITY_OPT_LOGGING "ignore_corruption" #define DM_VERITY_OPT_RESTART "restart_on_corruption" +#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" + +#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC) static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR); -enum verity_mode { - DM_VERITY_MODE_EIO, - DM_VERITY_MODE_LOGGING, - DM_VERITY_MODE_RESTART -}; - -enum verity_block_type { - DM_VERITY_BLOCK_TYPE_DATA, - DM_VERITY_BLOCK_TYPE_METADATA -}; - -struct dm_verity { - struct dm_dev *data_dev; - struct dm_dev *hash_dev; - struct dm_target *ti; - struct dm_bufio_client *bufio; - char *alg_name; - struct crypto_shash *tfm; - u8 *root_digest; /* digest of the root block */ - u8 *salt; /* salt: its size is salt_size */ - unsigned salt_size; - sector_t data_start; /* data offset in 512-byte sectors */ - sector_t hash_start; /* hash start in blocks */ - sector_t data_blocks; /* the number of data blocks */ - sector_t hash_blocks; /* the number of hash blocks */ - unsigned char data_dev_block_bits; /* log2(data blocksize) */ - unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ - unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ - unsigned char levels; /* the number of tree levels */ - unsigned char version; - unsigned digest_size; /* digest size for the current hash algorithm */ - unsigned shash_descsize;/* the size of temporary space for crypto */ - int hash_failed; /* set to 1 if hash of any block failed */ - enum verity_mode mode; /* mode for handling verification errors */ - unsigned corrupted_errs;/* Number of errors for corrupted blocks */ - - mempool_t *vec_mempool; /* mempool of bio vector */ - - struct workqueue_struct *verify_wq; - - /* starting blocks for each tree level. 0 is the lowest level. */ - sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; -}; - -struct dm_verity_io { - struct dm_verity *v; - - /* original values of bio->bi_end_io and bio->bi_private */ - bio_end_io_t *orig_bi_end_io; - void *orig_bi_private; - - sector_t block; - unsigned n_blocks; - - struct bvec_iter iter; - - struct work_struct work; - - /* - * Three variably-size fields follow this struct: - * - * u8 hash_desc[v->shash_descsize]; - * u8 real_digest[v->digest_size]; - * u8 want_digest[v->digest_size]; - * - * To access them use: io_hash_desc(), io_real_digest() and io_want_digest(). - */ -}; - struct dm_verity_prefetch_work { struct work_struct work; struct dm_verity *v; @@ -116,21 +48,6 @@ struct dm_verity_prefetch_work { unsigned n_blocks; }; -static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io) -{ - return (struct shash_desc *)(io + 1); -} - -static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize; -} - -static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; -} - /* * Auxiliary structure appended to each dm-bufio buffer. If the value * hash_verified is nonzero, hash of the block has been verified. @@ -177,6 +94,84 @@ static sector_t verity_position_at_level(struct dm_verity *v, sector_t block, return block >> (level * v->hash_per_block_bits); } +/* + * Wrapper for crypto_shash_init, which handles verity salting. + */ +static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc) +{ + int r; + + desc->tfm = v->tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + r = crypto_shash_init(desc); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_init failed: %d", r); + return r; + } + + if (likely(v->version >= 1)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + return 0; +} + +static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len) +{ + int r = crypto_shash_update(desc, data, len); + + if (unlikely(r < 0)) + DMERR("crypto_shash_update failed: %d", r); + + return r; +} + +static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc, + u8 *digest) +{ + int r; + + if (unlikely(!v->version)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (r < 0) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + r = crypto_shash_final(desc, digest); + + if (unlikely(r < 0)) + DMERR("crypto_shash_final failed: %d", r); + + return r; +} + +int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest) +{ + int r; + + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) + return r; + + r = verity_hash_update(v, desc, data, len); + if (unlikely(r < 0)) + return r; + + return verity_hash_final(v, desc, digest); +} + static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level, sector_t *hash_block, unsigned *offset) { @@ -250,17 +245,17 @@ out: * Verify hash of a metadata block pertaining to the specified data block * ("block" argument) at a specified level ("level" argument). * - * On successful return, io_want_digest(v, io) contains the hash value for - * a lower tree level or for the data block (if we're at the lowest leve). + * On successful return, verity_io_want_digest(v, io) contains the hash value + * for a lower tree level or for the data block (if we're at the lowest level). * * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned. * If "skip_unverified" is false, unverified buffer is hashed and verified - * against current value of io_want_digest(v, io). + * against current value of verity_io_want_digest(v, io). */ -static int verity_verify_level(struct dm_verity_io *io, sector_t block, - int level, bool skip_unverified) +static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, int level, bool skip_unverified, + u8 *want_digest) { - struct dm_verity *v = io->v; struct dm_buffer *buf; struct buffer_aux *aux; u8 *data; @@ -277,72 +272,128 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block, aux = dm_bufio_get_aux_data(buf); if (!aux->hash_verified) { - struct shash_desc *desc; - u8 *result; - if (skip_unverified) { r = 1; goto release_ret_r; } - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->hash_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) goto release_ret_r; - } - - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } - r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); + if (likely(memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) == 0)) + aux->hash_verified = 1; + else if (verity_fec_decode(v, io, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block, data, NULL) == 0) + aux->hash_verified = 1; + else if (verity_handle_err(v, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block)) { + r = -EIO; goto release_ret_r; } + } - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } + data += offset; + memcpy(want_digest, data, v->digest_size); + r = 0; - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); - goto release_ret_r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, - hash_block)) { - r = -EIO; - goto release_ret_r; - } - } else - aux->hash_verified = 1; +release_ret_r: + dm_bufio_release(buf); + return r; +} + +/* + * Find a hash for a given block, write it to digest and verify the integrity + * of the hash tree if necessary. + */ +int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero) +{ + int r = 0, i; + + if (likely(v->levels)) { + /* + * First, we try to get the requested hash for + * the current block. If the hash block itself is + * verified, zero is returned. If it isn't, this + * function returns 1 and we fall back to whole + * chain verification. + */ + r = verity_verify_level(v, io, block, 0, true, digest); + if (likely(r <= 0)) + goto out; } - data += offset; + memcpy(digest, v->root_digest, v->digest_size); + + for (i = v->levels - 1; i >= 0; i--) { + r = verity_verify_level(v, io, block, i, false, digest); + if (unlikely(r)) + goto out; + } +out: + if (!r && v->zero_digest) + *is_zero = !memcmp(v->zero_digest, digest, v->digest_size); + else + *is_zero = false; - memcpy(io_want_digest(v, io), data, v->digest_size); + return r; +} + +/* + * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec + * starting from iter. + */ +int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, u8 *data, + size_t len)) +{ + unsigned todo = 1 << v->data_dev_block_bits; + struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); + + do { + int r; + u8 *page; + unsigned len; + struct bio_vec bv = bio_iter_iovec(bio, *iter); + + page = kmap_atomic(bv.bv_page); + len = bv.bv_len; + + if (likely(len >= todo)) + len = todo; + + r = process(v, io, page + bv.bv_offset, len); + kunmap_atomic(page); + + if (r < 0) + return r; + + bio_advance_iter(bio, iter, len); + todo -= len; + } while (todo); - dm_bufio_release(buf); return 0; +} -release_ret_r: - dm_bufio_release(buf); +static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + return verity_hash_update(v, verity_io_hash_desc(v, io), data, len); +} - return r; +static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + memset(data, 0, len); + return 0; } /* @@ -350,99 +401,56 @@ release_ret_r: */ static int verity_verify_io(struct dm_verity_io *io) { + bool is_zero; struct dm_verity *v = io->v; - struct bio *bio = dm_bio_from_per_bio_data(io, - v->ti->per_bio_data_size); + struct bvec_iter start; unsigned b; - int i; for (b = 0; b < io->n_blocks; b++) { - struct shash_desc *desc; - u8 *result; int r; - unsigned todo; + struct shash_desc *desc = verity_io_hash_desc(v, io); + + r = verity_hash_for_block(v, io, io->block + b, + verity_io_want_digest(v, io), + &is_zero); + if (unlikely(r < 0)) + return r; - if (likely(v->levels)) { + if (is_zero) { /* - * First, we try to get the requested hash for - * the current block. If the hash block itself is - * verified, zero is returned. If it isn't, this - * function returns 0 and we fall back to whole - * chain verification. + * If we expect a zero block, don't validate, just + * return zeros. */ - int r = verity_verify_level(io, io->block + b, 0, true); - if (likely(!r)) - goto test_block_hash; - if (r < 0) + r = verity_for_bv_block(v, io, &io->iter, + verity_bv_zero); + if (unlikely(r < 0)) return r; - } - - memcpy(io_want_digest(v, io), v->root_digest, v->digest_size); - for (i = v->levels - 1; i >= 0; i--) { - int r = verity_verify_level(io, io->block + b, i, false); - if (unlikely(r)) - return r; + continue; } -test_block_hash: - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) return r; - } - - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } - todo = 1 << v->data_dev_block_bits; - do { - u8 *page; - unsigned len; - struct bio_vec bv = bio_iter_iovec(bio, io->iter); - - page = kmap_atomic(bv.bv_page); - len = bv.bv_len; - if (likely(len >= todo)) - len = todo; - r = crypto_shash_update(desc, page + bv.bv_offset, len); - kunmap_atomic(page); - - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - bio_advance_iter(bio, &io->iter, len); - todo -= len; - } while (todo); - - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } + start = io->iter; + r = verity_for_bv_block(v, io, &io->iter, verity_bv_hash_update); + if (unlikely(r < 0)) + return r; - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); + r = verity_hash_final(v, desc, verity_io_real_digest(v, io)); + if (unlikely(r < 0)) return r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, - io->block + b)) - return -EIO; - } + + if (likely(memcmp(verity_io_real_digest(v, io), + verity_io_want_digest(v, io), v->digest_size) == 0)) + continue; + else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b, NULL, &start) == 0) + continue; + else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b)) + return -EIO; } return 0; @@ -459,6 +467,8 @@ static void verity_finish_io(struct dm_verity_io *io, int error) bio->bi_end_io = io->orig_bi_end_io; bio->bi_private = io->orig_bi_private; + verity_fec_finish_io(io); + bio_endio_nodec(bio, error); } @@ -473,7 +483,7 @@ static void verity_end_io(struct bio *bio, int error) { struct dm_verity_io *io = bio->bi_private; - if (error) { + if (error && !verity_fec_is_enabled(io->v)) { verity_finish_io(io, error); return; } @@ -543,7 +553,7 @@ static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io) * Bio map function. It allocates dm_verity_io structure and bio vector and * fills them. Then it issues prefetches and the I/O. */ -static int verity_map(struct dm_target *ti, struct bio *bio) +int verity_map(struct dm_target *ti, struct bio *bio) { struct dm_verity *v = ti->private; struct dm_verity_io *io; @@ -577,6 +587,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio) bio->bi_private = io; io->iter = bio->bi_iter; + verity_fec_init_io(io); + verity_submit_prefetch(v, io); generic_make_request(bio); @@ -587,10 +599,11 @@ static int verity_map(struct dm_target *ti, struct bio *bio) /* * Status: V (valid) or C (corruption found) */ -static void verity_status(struct dm_target *ti, status_type_t type, +void verity_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct dm_verity *v = ti->private; + unsigned args = 0; unsigned sz = 0; unsigned x; @@ -617,8 +630,17 @@ static void verity_status(struct dm_target *ti, status_type_t type, else for (x = 0; x < v->salt_size; x++) DMEMIT("%02x", v->salt[x]); + if (v->mode != DM_VERITY_MODE_EIO) + args++; + if (verity_fec_is_enabled(v)) + args += DM_VERITY_OPTS_FEC; + if (v->zero_digest) + args++; + if (!args) + return; + DMEMIT(" %u", args); if (v->mode != DM_VERITY_MODE_EIO) { - DMEMIT(" 1 "); + DMEMIT(" "); switch (v->mode) { case DM_VERITY_MODE_LOGGING: DMEMIT(DM_VERITY_OPT_LOGGING); @@ -630,11 +652,14 @@ static void verity_status(struct dm_target *ti, status_type_t type, BUG(); } } + if (v->zero_digest) + DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES); + sz = verity_fec_status_table(v, sz, result, maxlen); break; } } -static int verity_ioctl(struct dm_target *ti, unsigned cmd, +int verity_ioctl(struct dm_target *ti, unsigned cmd, unsigned long arg) { struct dm_verity *v = ti->private; @@ -648,7 +673,7 @@ static int verity_ioctl(struct dm_target *ti, unsigned cmd, cmd, arg); } -static int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm, +int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm, struct bio_vec *biovec, int max_size) { struct dm_verity *v = ti->private; @@ -663,7 +688,7 @@ static int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm, return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); } -static int verity_iterate_devices(struct dm_target *ti, +int verity_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct dm_verity *v = ti->private; @@ -671,7 +696,7 @@ static int verity_iterate_devices(struct dm_target *ti, return fn(ti, v->data_dev, v->data_start, ti->len, data); } -static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) +void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct dm_verity *v = ti->private; @@ -684,7 +709,7 @@ static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, limits->logical_block_size); } -static void verity_dtr(struct dm_target *ti) +void verity_dtr(struct dm_target *ti) { struct dm_verity *v = ti->private; @@ -699,6 +724,7 @@ static void verity_dtr(struct dm_target *ti) kfree(v->salt); kfree(v->root_digest); + kfree(v->zero_digest); if (v->tfm) crypto_free_shash(v->tfm); @@ -711,9 +737,94 @@ static void verity_dtr(struct dm_target *ti) if (v->data_dev) dm_put_device(ti, v->data_dev); + verity_fec_dtr(v); + kfree(v); } +static int verity_alloc_zero_digest(struct dm_verity *v) +{ + int r = -ENOMEM; + struct shash_desc *desc; + u8 *zero_data; + + v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL); + + if (!v->zero_digest) + return r; + + desc = kmalloc(v->shash_descsize, GFP_KERNEL); + + if (!desc) + return r; /* verity_dtr will free zero_digest */ + + zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL); + + if (!zero_data) + goto out; + + r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits, + v->zero_digest); + +out: + kfree(desc); + kfree(zero_data); + + return r; +} + +static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) +{ + int r; + unsigned argc; + struct dm_target *ti = v->ti; + const char *arg_name; + + static struct dm_arg _args[] = { + {0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"}, + }; + + r = dm_read_arg_group(_args, as, &argc, &ti->error); + if (r) + return -EINVAL; + + if (!argc) + return 0; + + do { + arg_name = dm_shift_arg(as); + argc--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) { + v->mode = DM_VERITY_MODE_LOGGING; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) { + v->mode = DM_VERITY_MODE_RESTART; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) { + r = verity_alloc_zero_digest(v); + if (r) { + ti->error = "Cannot allocate zero digest"; + return r; + } + continue; + + } else if (verity_is_fec_opt_arg(arg_name)) { + r = verity_fec_parse_opt_args(as, v, &argc, arg_name); + if (r) + return r; + continue; + } + + ti->error = "Unrecognized verity feature request"; + return -EINVAL; + } while (argc && !r); + + return r; +} + /* * Target parameters: * <version> The current format is version 1. @@ -728,22 +839,17 @@ static void verity_dtr(struct dm_target *ti) * <digest> * <salt> Hex string or "-" if no salt. */ -static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) +int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) { struct dm_verity *v; struct dm_arg_set as; - const char *opt_string; - unsigned int num, opt_params; + unsigned int num; unsigned long long num_ll; int r; int i; sector_t hash_position; char dummy; - static struct dm_arg _args[] = { - {0, 1, "Invalid number of feature args"}, - }; - v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL); if (!v) { ti->error = "Cannot allocate verity structure"; @@ -752,6 +858,10 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->private = v; v->ti = ti; + r = verity_fec_ctr_alloc(v); + if (r) + goto bad; + if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) { ti->error = "Device must be readonly"; r = -EINVAL; @@ -888,29 +998,9 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) as.argc = argc; as.argv = argv; - r = dm_read_arg_group(_args, &as, &opt_params, &ti->error); - if (r) + r = verity_parse_opt_args(&as, v); + if (r < 0) goto bad; - - while (opt_params) { - opt_params--; - opt_string = dm_shift_arg(&as); - if (!opt_string) { - ti->error = "Not enough feature arguments"; - r = -EINVAL; - goto bad; - } - - if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING)) - v->mode = DM_VERITY_MODE_LOGGING; - else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART)) - v->mode = DM_VERITY_MODE_RESTART; - else { - ti->error = "Invalid feature arguments"; - r = -EINVAL; - goto bad; - } - } } v->hash_per_block_bits = @@ -978,6 +1068,16 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } + ti->per_bio_data_size = sizeof(struct dm_verity_io) + + v->shash_descsize + v->digest_size * 2; + + r = verity_fec_ctr(v); + if (r) + goto bad; + + ti->per_bio_data_size = roundup(ti->per_bio_data_size, + __alignof__(struct dm_verity_io)); + return 0; bad: @@ -988,7 +1088,7 @@ bad: static struct target_type verity_target = { .name = "verity", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h new file mode 100644 index 000000000000..cc2af69ffa72 --- /dev/null +++ b/drivers/md/dm-verity.h @@ -0,0 +1,144 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2015 Google, Inc. + * + * Author: Mikulas Patocka <mpatocka@redhat.com> + * + * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors + * + * This file is released under the GPLv2. + */ + +#ifndef DM_VERITY_H +#define DM_VERITY_H + +#include "dm-bufio.h" +#include <linux/device-mapper.h> +#include <crypto/hash.h> + +#define DM_VERITY_MAX_LEVELS 63 + +enum verity_mode { + DM_VERITY_MODE_EIO, + DM_VERITY_MODE_LOGGING, + DM_VERITY_MODE_RESTART +}; + +enum verity_block_type { + DM_VERITY_BLOCK_TYPE_DATA, + DM_VERITY_BLOCK_TYPE_METADATA +}; + +struct dm_verity_fec; + +struct dm_verity { + struct dm_dev *data_dev; + struct dm_dev *hash_dev; + struct dm_target *ti; + struct dm_bufio_client *bufio; + char *alg_name; + struct crypto_shash *tfm; + u8 *root_digest; /* digest of the root block */ + u8 *salt; /* salt: its size is salt_size */ + u8 *zero_digest; /* digest for a zero block */ + unsigned salt_size; + sector_t data_start; /* data offset in 512-byte sectors */ + sector_t hash_start; /* hash start in blocks */ + sector_t data_blocks; /* the number of data blocks */ + sector_t hash_blocks; /* the number of hash blocks */ + unsigned char data_dev_block_bits; /* log2(data blocksize) */ + unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ + unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ + unsigned char levels; /* the number of tree levels */ + unsigned char version; + unsigned digest_size; /* digest size for the current hash algorithm */ + unsigned shash_descsize;/* the size of temporary space for crypto */ + int hash_failed; /* set to 1 if hash of any block failed */ + enum verity_mode mode; /* mode for handling verification errors */ + unsigned corrupted_errs;/* Number of errors for corrupted blocks */ + + mempool_t *vec_mempool; /* mempool of bio vector */ + + struct workqueue_struct *verify_wq; + + /* starting blocks for each tree level. 0 is the lowest level. */ + sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; + + struct dm_verity_fec *fec; /* forward error correction */ +}; + +struct dm_verity_io { + struct dm_verity *v; + + /* original value of bio->bi_end_io */ + bio_end_io_t *orig_bi_end_io; + void *orig_bi_private; + + sector_t block; + unsigned n_blocks; + + struct bvec_iter iter; + + struct work_struct work; + + /* + * Three variably-size fields follow this struct: + * + * u8 hash_desc[v->shash_descsize]; + * u8 real_digest[v->digest_size]; + * u8 want_digest[v->digest_size]; + * + * To access them use: verity_io_hash_desc(), verity_io_real_digest() + * and verity_io_want_digest(). + */ +}; + +static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (struct shash_desc *)(io + 1); +} + +static inline u8 *verity_io_real_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize; +} + +static inline u8 *verity_io_want_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; +} + +static inline u8 *verity_io_digest_end(struct dm_verity *v, + struct dm_verity_io *io) +{ + return verity_io_want_digest(v, io) + v->digest_size; +} + +extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, + u8 *data, size_t len)); + +extern int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest); + +extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero); + +extern void verity_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen); +extern int verity_ioctl(struct dm_target *ti, unsigned cmd, + unsigned long arg); +extern int verity_merge(struct dm_target *ti, struct bvec_merge_data *bvm, + struct bio_vec *biovec, int max_size); +extern int verity_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data); +extern void verity_io_hints(struct dm_target *ti, struct queue_limits *limits); +extern void verity_dtr(struct dm_target *ti); +extern int verity_ctr(struct dm_target *ti, unsigned argc, char **argv); +extern int verity_map(struct dm_target *ti, struct bio *bio); +#endif /* DM_VERITY_H */ diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 8efa3684aef8..ccee8ebc55d8 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -19,6 +19,7 @@ #include <linux/mmc/card.h> #include <linux/mmc/host.h> +#include <linux/sched/rt.h> #include "queue.h" #define MMC_QUEUE_BOUNCESZ 65536 @@ -50,6 +51,11 @@ static int mmc_queue_thread(void *d) { struct mmc_queue *mq = d; struct request_queue *q = mq->queue; + struct sched_param scheduler_params = {0}; + + scheduler_params.sched_priority = 1; + + sched_setscheduler(current, SCHED_FIFO, &scheduler_params); current->flags |= PF_MEMALLOC; diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index b304d2bcd895..18fa59d5c902 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -29,7 +29,6 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/of.h> -#include <linux/wakelock.h> #include <trace/events/mmc.h> @@ -59,7 +58,6 @@ #define MMC_BKOPS_MAX_TIMEOUT (4 * 60 * 1000) /* max time to wait in ms */ static struct workqueue_struct *workqueue; -static struct wake_lock mmc_delayed_work_wake_lock; static const unsigned freqs[] = { 400000, 300000, 200000, 100000 }; /* @@ -76,7 +74,6 @@ module_param(use_spi_crc, bool, 0); static int mmc_schedule_delayed_work(struct delayed_work *work, unsigned long delay) { - wake_lock(&mmc_delayed_work_wake_lock); return queue_delayed_work(workqueue, work, delay); } @@ -2504,7 +2501,6 @@ void mmc_rescan(struct work_struct *work) struct mmc_host *host = container_of(work, struct mmc_host, detect.work); int i; - bool extend_wakelock = false; if (host->trigger_card_event && host->ops->card_event) { host->ops->card_event(host); @@ -2531,12 +2527,6 @@ void mmc_rescan(struct work_struct *work) host->detect_change = 0; - /* If the card was removed the bus will be marked - * as dead - extend the wakelock so userspace - * can respond */ - if (host->bus_dead) - extend_wakelock = 1; - /* * Let mmc_bus_put() free the bus/bus_ops if we've found that * the card is no longer present. @@ -2566,20 +2556,14 @@ void mmc_rescan(struct work_struct *work) mmc_claim_host(host); for (i = 0; i < ARRAY_SIZE(freqs); i++) { - if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min))) { - extend_wakelock = true; + if (!mmc_rescan_try_freq(host, max(freqs[i], host->f_min))) break; - } if (freqs[i] <= host->f_min) break; } mmc_release_host(host); out: - if (extend_wakelock) - wake_lock_timeout(&mmc_delayed_work_wake_lock, HZ / 2); - else - wake_unlock(&mmc_delayed_work_wake_lock); if (host->caps & MMC_CAP_NEEDS_POLL) mmc_schedule_delayed_work(&host->detect, HZ); } @@ -2801,9 +2785,6 @@ static int __init mmc_init(void) if (!workqueue) return -ENOMEM; - wake_lock_init(&mmc_delayed_work_wake_lock, WAKE_LOCK_SUSPEND, - "mmc_delayed_work"); - ret = mmc_register_bus(); if (ret) goto destroy_workqueue; @@ -2824,7 +2805,6 @@ unregister_bus: mmc_unregister_bus(); destroy_workqueue: destroy_workqueue(workqueue); - wake_lock_destroy(&mmc_delayed_work_wake_lock); return ret; } @@ -2835,7 +2815,6 @@ static void __exit mmc_exit(void) mmc_unregister_host_class(); mmc_unregister_bus(); destroy_workqueue(workqueue); - wake_lock_destroy(&mmc_delayed_work_wake_lock); } subsys_initcall(mmc_init); diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig index 710733f034fa..16604bdf5197 100644 --- a/drivers/net/wireless/Kconfig +++ b/drivers/net/wireless/Kconfig @@ -265,11 +265,6 @@ config MWL8K To compile this driver as a module, choose M here: the module will be called mwl8k. If unsure, say N. -config WIFI_CONTROL_FUNC - bool "Enable WiFi control function abstraction" - help - Enables Power/Reset/Carddetect function abstraction - source "drivers/net/wireless/ath/Kconfig" source "drivers/net/wireless/b43/Kconfig" source "drivers/net/wireless/b43legacy/Kconfig" diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index 1f9feb7480b2..9adfd6de8f8c 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -83,7 +83,7 @@ static void free_buffer_page(struct ion_system_heap *heap, unsigned int order = compound_order(page); bool cached = ion_buffer_cached(buffer); - if (!cached && !(buffer->private_flags & ION_PRIV_FLAG_SHRINKER_FREE)) { + if (!cached) { struct ion_page_pool *pool = heap->pools[order_to_index(order)]; if (buffer->private_flags & ION_PRIV_FLAG_SHRINKER_FREE) ion_page_pool_free_immediate(pool, page); diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 710c687d265e..c5341524c02a 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -845,7 +845,7 @@ done: } EXPORT_SYMBOL_GPL(usb_add_config); -static void unbind_config(struct usb_composite_dev *cdev, +static void remove_config(struct usb_composite_dev *cdev, struct usb_configuration *config) { while (!list_empty(&config->functions)) { @@ -860,6 +860,7 @@ static void unbind_config(struct usb_composite_dev *cdev, /* may free memory for "f" */ } } + list_del(&config->list); if (config->unbind) { DBG(cdev, "unbind config '%s'/%p\n", config->label, config); config->unbind(config); @@ -886,11 +887,9 @@ void usb_remove_config(struct usb_composite_dev *cdev, if (cdev->config == config) reset_config(cdev); - list_del(&config->list); - spin_unlock_irqrestore(&cdev->lock, flags); - unbind_config(cdev, config); + remove_config(cdev, config); } /*-------------------------------------------------------------------------*/ @@ -1882,8 +1881,7 @@ static void __composite_unbind(struct usb_gadget *gadget, bool unbind_driver) struct usb_configuration *c; c = list_first_entry(&cdev->configs, struct usb_configuration, list); - list_del(&c->list); - unbind_config(cdev, c); + remove_config(cdev, c); } if (cdev->driver->unbind && unbind_driver) cdev->driver->unbind(cdev); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 51cc1deb7af3..65b696e8a8d9 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -385,6 +385,12 @@ void dm_set_mdptr(struct mapped_device *md, void *ptr); void *dm_get_mdptr(struct mapped_device *md); /* + * Export the device via the ioctl interface (uses mdptr). + */ +int dm_ioctl_export(struct mapped_device *md, const char *name, + const char *uuid); + +/* * A device can still be used while suspended, but I/O is deferred. */ int dm_suspend(struct mapped_device *md, unsigned suspend_flags); diff --git a/include/linux/string.h b/include/linux/string.h index e40099e585c9..a8d90db9c4b0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -111,6 +111,7 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif void *memchr_inv(const void *s, int c, size_t n); +char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); diff --git a/init/Makefile b/init/Makefile index 692b91f1c1d4..243f61de2cba 100644 --- a/init/Makefile +++ b/init/Makefile @@ -15,6 +15,7 @@ mounts-y := do_mounts.o mounts-$(CONFIG_BLK_DEV_RAM) += do_mounts_rd.o mounts-$(CONFIG_BLK_DEV_INITRD) += do_mounts_initrd.o mounts-$(CONFIG_BLK_DEV_MD) += do_mounts_md.o +mounts-$(CONFIG_BLK_DEV_DM) += do_mounts_dm.o # dependencies on generated files need to be listed explicitly $(obj)/version.o: include/generated/compile.h diff --git a/init/do_mounts.c b/init/do_mounts.c index a95bbdb2a502..842274efcb47 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -561,6 +561,7 @@ void __init prepare_namespace(void) wait_for_device_probe(); md_run_setup(); + dm_run_setup(); if (saved_root_name[0]) { root_device_name = saved_root_name; diff --git a/init/do_mounts.h b/init/do_mounts.h index f5b978a9bb92..09d22862e8c3 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -74,3 +74,13 @@ void md_run_setup(void); static inline void md_run_setup(void) {} #endif + +#ifdef CONFIG_BLK_DEV_DM + +void dm_run_setup(void); + +#else + +static inline void dm_run_setup(void) {} + +#endif diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c new file mode 100644 index 000000000000..f521bc5ae248 --- /dev/null +++ b/init/do_mounts_dm.c @@ -0,0 +1,425 @@ +/* do_mounts_dm.c + * Copyright (C) 2010 The Chromium OS Authors <chromium-os-dev@chromium.org> + * All Rights Reserved. + * Based on do_mounts_md.c + * + * This file is released under the GPL. + */ +#include <linux/device-mapper.h> +#include <linux/fs.h> +#include <linux/string.h> + +#include "do_mounts.h" +#include "../drivers/md/dm.h" + +#define DM_MAX_NAME 32 +#define DM_MAX_UUID 129 +#define DM_NO_UUID "none" + +#define DM_MSG_PREFIX "init" + +/* Separators used for parsing the dm= argument. */ +#define DM_FIELD_SEP ' ' +#define DM_LINE_SEP ',' + +/* + * When the device-mapper and any targets are compiled into the kernel + * (not a module), one target may be created and used as the root device at + * boot time with the parameters given with the boot line dm=... + * The code for that is here. + */ + +struct dm_setup_target { + sector_t begin; + sector_t length; + char *type; + char *params; + /* simple singly linked list */ + struct dm_setup_target *next; +}; + +static struct { + int minor; + int ro; + char name[DM_MAX_NAME]; + char uuid[DM_MAX_UUID]; + char *targets; + struct dm_setup_target *target; + int target_count; +} dm_setup_args __initdata; + +static __initdata int dm_early_setup; + +static size_t __init get_dm_option(char *str, char **next, char sep) +{ + size_t len = 0; + char *endp = NULL; + + if (!str) + return 0; + + endp = strchr(str, sep); + if (!endp) { /* act like strchrnul */ + len = strlen(str); + endp = str + len; + } else { + len = endp - str; + } + + if (endp == str) + return 0; + + if (!next) + return len; + + if (*endp == 0) { + /* Don't advance past the nul. */ + *next = endp; + } else { + *next = endp + 1; + } + return len; +} + +static int __init dm_setup_args_init(void) +{ + dm_setup_args.minor = 0; + dm_setup_args.ro = 0; + dm_setup_args.target = NULL; + dm_setup_args.target_count = 0; + return 0; +} + +static int __init dm_setup_cleanup(void) +{ + struct dm_setup_target *target = dm_setup_args.target; + struct dm_setup_target *old_target = NULL; + while (target) { + kfree(target->type); + kfree(target->params); + old_target = target; + target = target->next; + kfree(old_target); + dm_setup_args.target_count--; + } + BUG_ON(dm_setup_args.target_count); + return 0; +} + +static char * __init dm_setup_parse_device_args(char *str) +{ + char *next = NULL; + size_t len = 0; + + /* Grab the logical name of the device to be exported to udev */ + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len) { + DMERR("failed to parse device name"); + goto parse_fail; + } + len = min(len + 1, sizeof(dm_setup_args.name)); + strlcpy(dm_setup_args.name, str, len); /* includes nul */ + str = skip_spaces(next); + + /* Grab the UUID value or "none" */ + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len) { + DMERR("failed to parse device uuid"); + goto parse_fail; + } + len = min(len + 1, sizeof(dm_setup_args.uuid)); + strlcpy(dm_setup_args.uuid, str, len); + str = skip_spaces(next); + + /* Determine if the table/device will be read only or read-write */ + if (!strncmp("ro,", str, 3)) { + dm_setup_args.ro = 1; + } else if (!strncmp("rw,", str, 3)) { + dm_setup_args.ro = 0; + } else { + DMERR("failed to parse table mode"); + goto parse_fail; + } + str = skip_spaces(str + 3); + + return str; + +parse_fail: + return NULL; +} + +static void __init dm_substitute_devices(char *str, size_t str_len) +{ + char *candidate = str; + char *candidate_end = str; + char old_char; + size_t len = 0; + dev_t dev; + + if (str_len < 3) + return; + + while (str && *str) { + candidate = strchr(str, '/'); + if (!candidate) + break; + + /* Avoid embedded slashes */ + if (candidate != str && *(candidate - 1) != DM_FIELD_SEP) { + str = strchr(candidate, DM_FIELD_SEP); + continue; + } + + len = get_dm_option(candidate, &candidate_end, DM_FIELD_SEP); + str = skip_spaces(candidate_end); + if (len < 3 || len > 37) /* name_to_dev_t max; maj:mix min */ + continue; + + /* Temporarily terminate with a nul */ + candidate_end--; + old_char = *candidate_end; + *candidate_end = '\0'; + + DMDEBUG("converting candidate device '%s' to dev_t", candidate); + /* Use the boot-time specific device naming */ + dev = name_to_dev_t(candidate); + *candidate_end = old_char; + + DMDEBUG(" -> %u", dev); + /* No suitable replacement found */ + if (!dev) + continue; + + /* Rewrite the /dev/path as a major:minor */ + len = snprintf(candidate, len, "%u:%u", MAJOR(dev), MINOR(dev)); + if (!len) { + DMERR("error substituting device major/minor."); + break; + } + candidate += len; + /* Pad out with spaces (fixing our nul) */ + while (candidate < candidate_end) + *(candidate++) = DM_FIELD_SEP; + } +} + +static int __init dm_setup_parse_targets(char *str) +{ + char *next = NULL; + size_t len = 0; + struct dm_setup_target **target = NULL; + + /* Targets are defined as per the table format but with a + * comma as a newline separator. */ + target = &dm_setup_args.target; + while (str && *str) { + *target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL); + if (!*target) { + DMERR("failed to allocate memory for target %d", + dm_setup_args.target_count); + goto parse_fail; + } + dm_setup_args.target_count++; + + (*target)->begin = simple_strtoull(str, &next, 10); + if (!next || *next != DM_FIELD_SEP) { + DMERR("failed to parse starting sector for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next + 1); + + (*target)->length = simple_strtoull(str, &next, 10); + if (!next || *next != DM_FIELD_SEP) { + DMERR("failed to parse length for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next + 1); + + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len || + !((*target)->type = kstrndup(str, len, GFP_KERNEL))) { + DMERR("failed to parse type for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next); + + len = get_dm_option(str, &next, DM_LINE_SEP); + if (!len || + !((*target)->params = kstrndup(str, len, GFP_KERNEL))) { + DMERR("failed to parse params for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next); + + /* Before moving on, walk through the copied target and + * attempt to replace all /dev/xxx with the major:minor number. + * It may not be possible to resolve them traditionally at + * boot-time. */ + dm_substitute_devices((*target)->params, len); + + target = &((*target)->next); + } + DMDEBUG("parsed %d targets", dm_setup_args.target_count); + + return 0; + +parse_fail: + return 1; +} + +/* + * Parse the command-line parameters given our kernel, but do not + * actually try to invoke the DM device now; that is handled by + * dm_setup_drive after the low-level disk drivers have initialised. + * dm format is as follows: + * dm="name uuid fmode,[table line 1],[table line 2],..." + * May be used with root=/dev/dm-0 as it always uses the first dm minor. + */ + +static int __init dm_setup(char *str) +{ + dm_setup_args_init(); + + str = dm_setup_parse_device_args(str); + if (!str) { + DMDEBUG("str is NULL"); + goto parse_fail; + } + + /* Target parsing is delayed until we have dynamic memory */ + dm_setup_args.targets = str; + + printk(KERN_INFO "dm: will configure '%s' on dm-%d\n", + dm_setup_args.name, dm_setup_args.minor); + + dm_early_setup = 1; + return 1; + +parse_fail: + printk(KERN_WARNING "dm: Invalid arguments supplied to dm=.\n"); + return 0; +} + + +static void __init dm_setup_drive(void) +{ + struct mapped_device *md = NULL; + struct dm_table *table = NULL; + struct dm_setup_target *target; + char *uuid = dm_setup_args.uuid; + fmode_t fmode = FMODE_READ; + + /* Finish parsing the targets. */ + if (dm_setup_parse_targets(dm_setup_args.targets)) + goto parse_fail; + + if (dm_create(dm_setup_args.minor, &md)) { + DMDEBUG("failed to create the device"); + goto dm_create_fail; + } + DMDEBUG("created device '%s'", dm_device_name(md)); + + /* In addition to flagging the table below, the disk must be + * set explicitly ro/rw. */ + set_disk_ro(dm_disk(md), dm_setup_args.ro); + + if (!dm_setup_args.ro) + fmode |= FMODE_WRITE; + if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) { + DMDEBUG("failed to create the table"); + goto dm_table_create_fail; + } + + dm_lock_md_type(md); + target = dm_setup_args.target; + while (target) { + DMINFO("adding target '%llu %llu %s %s'", + (unsigned long long) target->begin, + (unsigned long long) target->length, target->type, + target->params); + if (dm_table_add_target(table, target->type, target->begin, + target->length, target->params)) { + DMDEBUG("failed to add the target to the table"); + goto add_target_fail; + } + target = target->next; + } + + if (dm_table_complete(table)) { + DMDEBUG("failed to complete the table"); + goto table_complete_fail; + } + + if (dm_get_md_type(md) == DM_TYPE_NONE) { + dm_set_md_type(md, dm_table_get_type(table)); + if (dm_setup_md_queue(md)) { + DMWARN("unable to set up device queue for new table."); + goto setup_md_queue_fail; + } + } else if (dm_get_md_type(md) != dm_table_get_type(table)) { + DMWARN("can't change device type after initial table load."); + goto setup_md_queue_fail; + } + + /* Suspend the device so that we can bind it to the table. */ + if (dm_suspend(md, 0)) { + DMDEBUG("failed to suspend the device pre-bind"); + goto suspend_fail; + } + + /* Bind the table to the device. This is the only way to associate + * md->map with the table and set the disk capacity directly. */ + if (dm_swap_table(md, table)) { /* should return NULL. */ + DMDEBUG("failed to bind the device to the table"); + goto table_bind_fail; + } + + /* Finally, resume and the device should be ready. */ + if (dm_resume(md)) { + DMDEBUG("failed to resume the device"); + goto resume_fail; + } + + /* Export the dm device via the ioctl interface */ + if (!strcmp(DM_NO_UUID, dm_setup_args.uuid)) + uuid = NULL; + if (dm_ioctl_export(md, dm_setup_args.name, uuid)) { + DMDEBUG("failed to export device with given name and uuid"); + goto export_fail; + } + printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor); + + dm_unlock_md_type(md); + dm_setup_cleanup(); + return; + +export_fail: +resume_fail: +table_bind_fail: +suspend_fail: +setup_md_queue_fail: +table_complete_fail: +add_target_fail: + dm_unlock_md_type(md); +dm_table_create_fail: + dm_put(md); +dm_create_fail: + dm_setup_cleanup(); +parse_fail: + printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n", + dm_setup_args.minor, dm_setup_args.name); +} + +__setup("dm=", dm_setup); + +void __init dm_run_setup(void) +{ + if (!dm_early_setup) + return; + printk(KERN_INFO "dm: attempting early device configuration.\n"); + dm_setup_drive(); +} diff --git a/lib/string.c b/lib/string.c index bb3d4b6993c4..13d1e84ddb80 100644 --- a/lib/string.c +++ b/lib/string.c @@ -849,3 +849,20 @@ void *memchr_inv(const void *start, int c, size_t bytes) return check_bytes8(start, value, bytes % 8); } EXPORT_SYMBOL(memchr_inv); + +/** + * strreplace - Replace all occurrences of character in string. + * @s: The string to operate on. + * @old: The character being replaced. + * @new: The character @old is replaced with. + * + * Returns pointer to the nul byte at the end of @s. + */ +char *strreplace(char *s, char old, char new) +{ + for (; *s; ++s) + if (*s == old) + *s = new; + return s; +} +EXPORT_SYMBOL(strreplace); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 99b50153e985..83973fec0d6e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3824,16 +3824,17 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, swap_buffers: /* Swap primary and spare array */ thresholds->spare = thresholds->primary; - /* If all events are unregistered, free the spare array */ - if (!new) { - kfree(thresholds->spare); - thresholds->spare = NULL; - } rcu_assign_pointer(thresholds->primary, new); /* To be sure that nobody uses thresholds */ synchronize_rcu(); + + /* If all events are unregistered, free the spare array */ + if (!new) { + kfree(thresholds->spare); + thresholds->spare = NULL; + } unlock: mutex_unlock(&memcg->thresholds_lock); } diff --git a/net/netfilter/xt_qtaguid.c b/net/netfilter/xt_qtaguid.c index 90b2c6aac7d8..c9b5ff123a8d 100644 --- a/net/netfilter/xt_qtaguid.c +++ b/net/netfilter/xt_qtaguid.c @@ -1291,11 +1291,12 @@ static void if_tag_stat_update(const char *ifname, uid_t uid, "uid=%u sk=%p dir=%d proto=%d bytes=%d)\n", ifname, uid, sk, direction, proto, bytes); - + spin_lock_bh(&iface_stat_list_lock); iface_entry = get_iface_entry(ifname); if (!iface_entry) { pr_err_ratelimited("qtaguid: iface_stat: stat_update() " "%s not found\n", ifname); + spin_unlock_bh(&iface_stat_list_lock); return; } /* It is ok to process data when an iface_entry is inactive */ @@ -1331,8 +1332,7 @@ static void if_tag_stat_update(const char *ifname, uid_t uid, * {0, uid_tag} will also get updated. */ tag_stat_update(tag_stat_entry, direction, proto, bytes); - spin_unlock_bh(&iface_entry->tag_stat_list_lock); - return; + goto unlock; } /* Loop over tag list under this interface for {0,uid_tag} */ @@ -1372,6 +1372,7 @@ static void if_tag_stat_update(const char *ifname, uid_t uid, tag_stat_update(new_tag_stat, direction, proto, bytes); unlock: spin_unlock_bh(&iface_entry->tag_stat_list_lock); + spin_unlock_bh(&iface_stat_list_lock); } static int iface_netdev_event_handler(struct notifier_block *nb, diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index bd536cb221e2..db91639c81e3 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -794,6 +794,7 @@ long join_session_keyring(const char *name) ret = PTR_ERR(keyring); goto error2; } else if (keyring == new->session_keyring) { + key_put(keyring); ret = 0; goto error2; } diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 18643bf9894d..456e1a9bcfde 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -638,7 +638,7 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, { struct avtab_node *node; - if (!ctab || !key || !avd || !xperms) + if (!ctab || !key || !avd) return; for (node = avtab_search_node(ctab, key); node; @@ -657,7 +657,7 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, if ((u16)(AVTAB_AUDITALLOW|AVTAB_ENABLED) == (node->key.specified & (AVTAB_AUDITALLOW|AVTAB_ENABLED))) avd->auditallow |= node->datum.u.data; - if ((node->key.specified & AVTAB_ENABLED) && + if (xperms && (node->key.specified & AVTAB_ENABLED) && (node->key.specified & AVTAB_XPERMS)) services_compute_xperms_drivers(xperms, node); } |