diff options
author | Russell King <rmk+kernel@arm.linux.org.uk> | 2011-06-28 21:23:00 +0100 |
---|---|---|
committer | Russell King <rmk+kernel@arm.linux.org.uk> | 2011-06-28 21:23:00 +0100 |
commit | 2ff0720933f9a5e502a46fb6ea14ceeaad65131f (patch) | |
tree | 7d337086a6bd803df21e4df396886015ab872326 /arch/arm/kernel/entry-armv.S | |
parent | b0af8dfdd67699e25083478c63eedef2e72ebd85 (diff) | |
parent | 40fb79c8a88625504857d44de1bc89dc0341e618 (diff) |
Merge branch 'cmpxchg64' of git://git.linaro.org/people/nico/linux into devel-stable
Diffstat (limited to 'arch/arm/kernel/entry-armv.S')
-rw-r--r-- | arch/arm/kernel/entry-armv.S | 246 |
1 files changed, 94 insertions, 152 deletions
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 90c62cd51ca..8f9ab5c9015 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -383,7 +383,7 @@ ENDPROC(__pabt_svc) .endm .macro kuser_cmpxchg_check -#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) +#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) #ifndef CONFIG_MMU #warning "NPTL on non MMU needs fixing" #else @@ -392,7 +392,7 @@ ENDPROC(__pabt_svc) @ perform a quick test inline since it should be false @ 99.9999% of the time. The rest is done out of line. cmp r2, #TASK_SIZE - blhs kuser_cmpxchg_fixup + blhs kuser_cmpxchg64_fixup #endif #endif .endm @@ -758,31 +758,12 @@ ENDPROC(__switch_to) /* * User helpers. * - * These are segment of kernel provided user code reachable from user space - * at a fixed address in kernel memory. This is used to provide user space - * with some operations which require kernel help because of unimplemented - * native feature and/or instructions in many ARM CPUs. The idea is for - * this code to be executed directly in user mode for best efficiency but - * which is too intimate with the kernel counter part to be left to user - * libraries. In fact this code might even differ from one CPU to another - * depending on the available instruction set and restrictions like on - * SMP systems. In other words, the kernel reserves the right to change - * this code as needed without warning. Only the entry points and their - * results are guaranteed to be stable. - * * Each segment is 32-byte aligned and will be moved to the top of the high * vector page. New segments (if ever needed) must be added in front of * existing ones. This mechanism should be used only for things that are * really small and justified, and not be abused freely. * - * User space is expected to implement those things inline when optimizing - * for a processor that has the necessary native support, but only if such - * resulting binaries are already to be incompatible with earlier ARM - * processors due to the use of unsupported instructions other than what - * is provided here. In other words don't make binaries unable to run on - * earlier processors just for the sake of not using these kernel helpers - * if your compiled code is not going to use the new instructions for other - * purpose. + * See Documentation/arm/kernel_user_helpers.txt for formal definitions. */ THUMB( .arm ) @@ -799,96 +780,103 @@ ENDPROC(__switch_to) __kuser_helper_start: /* - * Reference prototype: - * - * void __kernel_memory_barrier(void) - * - * Input: - * - * lr = return address - * - * Output: - * - * none - * - * Clobbered: - * - * none - * - * Definition and user space usage example: - * - * typedef void (__kernel_dmb_t)(void); - * #define __kernel_dmb (*(__kernel_dmb_t *)0xffff0fa0) - * - * Apply any needed memory barrier to preserve consistency with data modified - * manually and __kuser_cmpxchg usage. - * - * This could be used as follows: - * - * #define __kernel_dmb() \ - * asm volatile ( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #95" \ - * : : : "r0", "lr","cc" ) + * Due to the length of some sequences, __kuser_cmpxchg64 spans 2 regular + * kuser "slots", therefore 0xffff0f80 is not used as a valid entry point. */ -__kuser_memory_barrier: @ 0xffff0fa0 +__kuser_cmpxchg64: @ 0xffff0f60 + +#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) + + /* + * Poor you. No fast solution possible... + * The kernel itself must perform the operation. + * A special ghost syscall is used for that (see traps.c). + */ + stmfd sp!, {r7, lr} + ldr r7, 1f @ it's 20 bits + swi __ARM_NR_cmpxchg64 + ldmfd sp!, {r7, pc} +1: .word __ARM_NR_cmpxchg64 + +#elif defined(CONFIG_CPU_32v6K) + + stmfd sp!, {r4, r5, r6, r7} + ldrd r4, r5, [r0] @ load old val + ldrd r6, r7, [r1] @ load new val + smp_dmb arm +1: ldrexd r0, r1, [r2] @ load current val + eors r3, r0, r4 @ compare with oldval (1) + eoreqs r3, r1, r5 @ compare with oldval (2) + strexdeq r3, r6, r7, [r2] @ store newval if eq + teqeq r3, #1 @ success? + beq 1b @ if no then retry smp_dmb arm + rsbs r0, r3, #0 @ set returned val and C flag + ldmfd sp!, {r4, r5, r6, r7} + bx lr + +#elif !defined(CONFIG_SMP) + +#ifdef CONFIG_MMU + + /* + * The only thing that can break atomicity in this cmpxchg64 + * implementation is either an IRQ or a data abort exception + * causing another process/thread to be scheduled in the middle of + * the critical sequence. The same strategy as for cmpxchg is used. + */ + stmfd sp!, {r4, r5, r6, lr} + ldmia r0, {r4, r5} @ load old val + ldmia r1, {r6, lr} @ load new val +1: ldmia r2, {r0, r1} @ load current val + eors r3, r0, r4 @ compare with oldval (1) + eoreqs r3, r1, r5 @ compare with oldval (2) +2: stmeqia r2, {r6, lr} @ store newval if eq + rsbs r0, r3, #0 @ set return val and C flag + ldmfd sp!, {r4, r5, r6, pc} + + .text +kuser_cmpxchg64_fixup: + @ Called from kuser_cmpxchg_fixup. + @ r2 = address of interrupted insn (must be preserved). + @ sp = saved regs. r7 and r8 are clobbered. + @ 1b = first critical insn, 2b = last critical insn. + @ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b. + mov r7, #0xffff0fff + sub r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64))) + subs r8, r2, r7 + rsbcss r8, r8, #(2b - 1b) + strcs r7, [sp, #S_PC] +#if __LINUX_ARM_ARCH__ < 6 + bcc kuser_cmpxchg32_fixup +#endif + mov pc, lr + .previous + +#else +#warning "NPTL on non MMU needs fixing" + mov r0, #-1 + adds r0, r0, #0 usr_ret lr +#endif + +#else +#error "incoherent kernel configuration" +#endif + + /* pad to next slot */ + .rept (16 - (. - __kuser_cmpxchg64)/4) + .word 0 + .endr .align 5 -/* - * Reference prototype: - * - * int __kernel_cmpxchg(int oldval, int newval, int *ptr) - * - * Input: - * - * r0 = oldval - * r1 = newval - * r2 = ptr - * lr = return address - * - * Output: - * - * r0 = returned value (zero or non-zero) - * C flag = set if r0 == 0, clear if r0 != 0 - * - * Clobbered: - * - * r3, ip, flags - * - * Definition and user space usage example: - * - * typedef int (__kernel_cmpxchg_t)(int oldval, int newval, int *ptr); - * #define __kernel_cmpxchg (*(__kernel_cmpxchg_t *)0xffff0fc0) - * - * Atomically store newval in *ptr if *ptr is equal to oldval for user space. - * Return zero if *ptr was changed or non-zero if no exchange happened. - * The C flag is also set if *ptr was changed to allow for assembly - * optimization in the calling code. - * - * Notes: - * - * - This routine already includes memory barriers as needed. - * - * For example, a user space atomic_add implementation could look like this: - * - * #define atomic_add(ptr, val) \ - * ({ register unsigned int *__ptr asm("r2") = (ptr); \ - * register unsigned int __result asm("r1"); \ - * asm volatile ( \ - * "1: @ atomic_add\n\t" \ - * "ldr r0, [r2]\n\t" \ - * "mov r3, #0xffff0fff\n\t" \ - * "add lr, pc, #4\n\t" \ - * "add r1, r0, %2\n\t" \ - * "add pc, r3, #(0xffff0fc0 - 0xffff0fff)\n\t" \ - * "bcc 1b" \ - * : "=&r" (__result) \ - * : "r" (__ptr), "rIL" (val) \ - * : "r0","r3","ip","lr","cc","memory" ); \ - * __result; }) - */ +__kuser_memory_barrier: @ 0xffff0fa0 + smp_dmb arm + usr_ret lr + + .align 5 __kuser_cmpxchg: @ 0xffff0fc0 @@ -925,7 +913,7 @@ __kuser_cmpxchg: @ 0xffff0fc0 usr_ret lr .text -kuser_cmpxchg_fixup: +kuser_cmpxchg32_fixup: @ Called from kuser_cmpxchg_check macro. @ r2 = address of interrupted insn (must be preserved). @ sp = saved regs. r7 and r8 are clobbered. @@ -963,39 +951,6 @@ kuser_cmpxchg_fixup: .align 5 -/* - * Reference prototype: - * - * int __kernel_get_tls(void) - * - * Input: - * - * lr = return address - * - * Output: - * - * r0 = TLS value - * - * Clobbered: - * - * none - * - * Definition and user space usage example: - * - * typedef int (__kernel_get_tls_t)(void); - * #define __kernel_get_tls (*(__kernel_get_tls_t *)0xffff0fe0) - * - * Get the TLS value as previously set via the __ARM_NR_set_tls syscall. - * - * This could be used as follows: - * - * #define __kernel_get_tls() \ - * ({ register unsigned int __val asm("r0"); \ - * asm( "mov r0, #0xffff0fff; mov lr, pc; sub pc, r0, #31" \ - * : "=r" (__val) : : "lr","cc" ); \ - * __val; }) - */ - __kuser_get_tls: @ 0xffff0fe0 ldr r0, [pc, #(16 - 8)] @ read TLS, set in kuser_get_tls_init usr_ret lr @@ -1004,19 +959,6 @@ __kuser_get_tls: @ 0xffff0fe0 .word 0 @ 0xffff0ff0 software TLS value, then .endr @ pad up to __kuser_helper_version -/* - * Reference declaration: - * - * extern unsigned int __kernel_helper_version; - * - * Definition and user space usage example: - * - * #define __kernel_helper_version (*(unsigned int *)0xffff0ffc) - * - * User space may read this to determine the curent number of helpers - * available. - */ - __kuser_helper_version: @ 0xffff0ffc .word ((__kuser_helper_end - __kuser_helper_start) >> 5) |