From 74facffeca3795ffb5cf8898f5859fbb822e4c5d Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 2 Jun 2011 11:16:22 +0100 Subject: ARM: Allow SoCs to enable scatterlist chaining Allow SoCs to enable the scatterlist chaining support, which allows scatterlist tables to be broken up into smaller allocations. As support for this feature depends on the implementation details of the users of the scatterlists, we can't enable this globally without auditing all the users, which is a very big task. Instead, let SoCs progressively switch over to using this. SoC drivers using scatterlists and SoC DMA implementations need auditing before this option can be enabled for the SoC. Signed-off-by: Russell King --- arch/arm/Kconfig | 3 +++ arch/arm/include/asm/scatterlist.h | 4 ++++ 2 files changed, 7 insertions(+) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9adc278a22ab..cc0dcbf1f6b5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -37,6 +37,9 @@ config ARM Europe. There is an ARM Linux project with a web page at . +config ARM_HAS_SG_CHAIN + bool + config HAVE_PWM bool diff --git a/arch/arm/include/asm/scatterlist.h b/arch/arm/include/asm/scatterlist.h index 2f87870d9347..cefdb8f898a1 100644 --- a/arch/arm/include/asm/scatterlist.h +++ b/arch/arm/include/asm/scatterlist.h @@ -1,6 +1,10 @@ #ifndef _ASMARM_SCATTERLIST_H #define _ASMARM_SCATTERLIST_H +#ifdef CONFIG_ARM_HAS_SG_CHAIN +#define ARCH_HAS_SG_CHAIN +#endif + #include #include #include -- cgit v1.2.3 From 37b8304642c7f91df54888955c373ae89b577fcc Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Sun, 19 Jun 2011 23:36:03 -0400 Subject: ARM: kuser: move interface documentation out of the source code Digging into some assembly file in order to get information about the kuser helpers is not that convivial. Let's move that information to a better formatted file in Documentation/arm/ and improve on it a bit. Thanks to Dave Martin for the initial cleanup and clarifications. Signed-off-by: Nicolas Pitre Acked-by: Dave Martin --- Documentation/arm/kernel_user_helpers.txt | 203 ++++++++++++++++++++++++++++++ arch/arm/kernel/entry-armv.S | 153 +--------------------- 2 files changed, 204 insertions(+), 152 deletions(-) create mode 100644 Documentation/arm/kernel_user_helpers.txt diff --git a/Documentation/arm/kernel_user_helpers.txt b/Documentation/arm/kernel_user_helpers.txt new file mode 100644 index 000000000000..0c33f72d1873 --- /dev/null +++ b/Documentation/arm/kernel_user_helpers.txt @@ -0,0 +1,203 @@ +Kernel-provided 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, or whether it is a 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 as documented here are +guaranteed to be stable. + +This is different from (but doesn't preclude) a full blown VDSO +implementation, however a VDSO would prevent some assembly tricks with +constants that allows for efficient branching to those code segments. And +since those code segments only use a few cycles before returning to user +code, the overhead of a VDSO indirect far call would add a measurable +overhead to such minimalistic operations. + +User space is expected to bypass those helpers and implement those things +inline (either in the code emitted directly by the compiler, or part of +the implementation of a library call) when optimizing for a recent enough +processor that has the necessary native support, but only if resulting +binaries are already to be incompatible with earlier ARM processors due to +useage of similar native instructions for other things. 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 new instructions for other purpose. + +New helpers may be added over time, so an older kernel may be missing some +helpers present in a newer kernel. For this reason, programs must check +the value of __kuser_helper_version (see below) before assuming that it is +safe to call any particular helper. This check should ideally be +performed only once at process startup time, and execution aborted early +if the required helpers are not provided by the kernel version that +process is running on. + +kuser_helper_version +-------------------- + +Location: 0xffff0ffc + +Reference declaration: + + extern int32_t __kuser_helper_version; + +Definition: + + This field contains the number of helpers being implemented by the + running kernel. User space may read this to determine the availability + of a particular helper. + +Usage example: + +#define __kuser_helper_version (*(int32_t *)0xffff0ffc) + +void check_kuser_version(void) +{ + if (__kuser_helper_version < 2) { + fprintf(stderr, "can't do atomic operations, kernel too old\n"); + abort(); + } +} + +Notes: + + User space may assume that the value of this field never changes + during the lifetime of any single process. This means that this + field can be read once during the initialisation of a library or + startup phase of a program. + +kuser_get_tls +------------- + +Location: 0xffff0fe0 + +Reference prototype: + + void * __kuser_get_tls(void); + +Input: + + lr = return address + +Output: + + r0 = TLS value + +Clobbered registers: + + none + +Definition: + + Get the TLS value as previously set via the __ARM_NR_set_tls syscall. + +Usage example: + +typedef void * (__kuser_get_tls_t)(void); +#define __kuser_get_tls (*(__kuser_get_tls_t *)0xffff0fe0) + +void foo() +{ + void *tls = __kuser_get_tls(); + printf("TLS = %p\n", tls); +} + +Notes: + + - Valid only if __kuser_helper_version >= 1 (from kernel version 2.6.12). + +kuser_cmpxchg +------------- + +Location: 0xffff0fc0 + +Reference prototype: + + int __kuser_cmpxchg(int32_t oldval, int32_t newval, volatile int32_t *ptr); + +Input: + + r0 = oldval + r1 = newval + r2 = ptr + lr = return address + +Output: + + r0 = success code (zero or non-zero) + C flag = set if r0 == 0, clear if r0 != 0 + +Clobbered registers: + + r3, ip, flags + +Definition: + + Atomically store newval in *ptr only if *ptr is equal to oldval. + 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. + +Usage example: + +typedef int (__kuser_cmpxchg_t)(int oldval, int newval, volatile int *ptr); +#define __kuser_cmpxchg (*(__kuser_cmpxchg_t *)0xffff0fc0) + +int atomic_add(volatile int *ptr, int val) +{ + int old, new; + + do { + old = *ptr; + new = old + val; + } while(__kuser_cmpxchg(old, new, ptr)); + + return new; +} + +Notes: + + - This routine already includes memory barriers as needed. + + - Valid only if __kuser_helper_version >= 2 (from kernel version 2.6.12). + +kuser_memory_barrier +-------------------- + +Location: 0xffff0fa0 + +Reference prototype: + + void __kuser_memory_barrier(void); + +Input: + + lr = return address + +Output: + + none + +Clobbered registers: + + none + +Definition: + + Apply any needed memory barrier to preserve consistency with data modified + manually and __kuser_cmpxchg usage. + +Usage example: + +typedef void (__kuser_dmb_t)(void); +#define __kuser_dmb (*(__kuser_dmb_t *)0xffff0fa0) + +Notes: + + - Valid only if __kuser_helper_version >= 3 (from kernel version 2.6.15). diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index e8d885676807..63f7907c4c3c 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -754,31 +754,12 @@ 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 ) @@ -794,98 +775,12 @@ ENDPROC(__switch_to) .globl __kuser_helper_start __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" ) - */ - __kuser_memory_barrier: @ 0xffff0fa0 smp_dmb arm usr_ret lr .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_cmpxchg: @ 0xffff0fc0 #if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) @@ -959,39 +854,6 @@ 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 @@ -1000,19 +862,6 @@ __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) -- cgit v1.2.3 From b69874e4f530b0103e507f695c010d00cb85a4df Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 18:57:31 +0100 Subject: ARM: pm: arrange for cpu_proc_init() to be called on resume cpu_proc_init() does processor specific initialization, which we do at boot time. We have been omitting to do this on resume, which causes some of this initialization to be skipped. We've also been skipping this on SMP initialization too. Ensure that cpu_proc_init() is always called appropriately by moving it into cpu_init(), and move cpu_init() to a more appropriate point in the boot initialization. Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/setup.c | 99 ++++++++++++++++++++++++----------------------- arch/arm/mm/proc-sa1100.S | 4 +- 2 files changed, 51 insertions(+), 52 deletions(-) diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ed11fb08b05a..edcab02be64c 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -342,54 +342,6 @@ static void __init feat_v6_fixup(void) elf_hwcap &= ~HWCAP_TLS; } -static void __init setup_processor(void) -{ - struct proc_info_list *list; - - /* - * locate processor in the list of supported processor - * types. The linker builds this table for us from the - * entries in arch/arm/mm/proc-*.S - */ - list = lookup_processor_type(read_cpuid_id()); - if (!list) { - printk("CPU configuration botched (ID %08x), unable " - "to continue.\n", read_cpuid_id()); - while (1); - } - - cpu_name = list->cpu_name; - -#ifdef MULTI_CPU - processor = *list->proc; -#endif -#ifdef MULTI_TLB - cpu_tlb = *list->tlb; -#endif -#ifdef MULTI_USER - cpu_user = *list->user; -#endif -#ifdef MULTI_CACHE - cpu_cache = *list->cache; -#endif - - printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", - cpu_name, read_cpuid_id(), read_cpuid_id() & 15, - proc_arch[cpu_architecture()], cr_alignment); - - sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS); - sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS); - elf_hwcap = list->elf_hwcap; -#ifndef CONFIG_ARM_THUMB - elf_hwcap &= ~HWCAP_THUMB; -#endif - - feat_v6_fixup(); - - cacheid_init(); - cpu_proc_init(); -} - /* * cpu_init - initialise one CPU. * @@ -405,6 +357,8 @@ void cpu_init(void) BUG(); } + cpu_proc_init(); + /* * Define the placement constraint for the inline asm directive below. * In Thumb-2, msr with an immediate value is not allowed. @@ -441,6 +395,54 @@ void cpu_init(void) : "r14"); } +static void __init setup_processor(void) +{ + struct proc_info_list *list; + + /* + * locate processor in the list of supported processor + * types. The linker builds this table for us from the + * entries in arch/arm/mm/proc-*.S + */ + list = lookup_processor_type(read_cpuid_id()); + if (!list) { + printk("CPU configuration botched (ID %08x), unable " + "to continue.\n", read_cpuid_id()); + while (1); + } + + cpu_name = list->cpu_name; + +#ifdef MULTI_CPU + processor = *list->proc; +#endif +#ifdef MULTI_TLB + cpu_tlb = *list->tlb; +#endif +#ifdef MULTI_USER + cpu_user = *list->user; +#endif +#ifdef MULTI_CACHE + cpu_cache = *list->cache; +#endif + + printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", + cpu_name, read_cpuid_id(), read_cpuid_id() & 15, + proc_arch[cpu_architecture()], cr_alignment); + + sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS); + sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS); + elf_hwcap = list->elf_hwcap; +#ifndef CONFIG_ARM_THUMB + elf_hwcap &= ~HWCAP_THUMB; +#endif + + feat_v6_fixup(); + + cacheid_init(); + cpu_init(); +} + void __init dump_machine_table(void) { struct machine_desc *p; @@ -913,7 +915,6 @@ void __init setup_arch(char **cmdline_p) #endif reserve_crashkernel(); - cpu_init(); tcm_init(); #ifdef CONFIG_MULTI_IRQ_HANDLER diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 184a9c997e36..e9c47271732d 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -34,7 +34,7 @@ */ #define DCACHELINESIZE 32 - __INIT + .section .text /* * cpu_sa1100_proc_init() @@ -45,8 +45,6 @@ ENTRY(cpu_sa1100_proc_init) mcr p15, 0, r0, c9, c0, 5 @ Allow read-buffer operations from userland mov pc, lr - .section .text - /* * cpu_sa1100_proc_fin() * -- cgit v1.2.3 From 3125af241cdb5a2421aad9f710b2744228a79084 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 18:59:33 +0100 Subject: ARM: pm: sa1100: no need to re-enable clock switching This is now taken care of by calling cpu_proc_init() in the resume path, so eliminate this unnecessary call. Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/mach-sa1100/sleep.S | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S index 04f2a618d4ef..122ab3c66923 100644 --- a/arch/arm/mach-sa1100/sleep.S +++ b/arch/arm/mach-sa1100/sleep.S @@ -147,5 +147,4 @@ sa1110_sdram_controller_fix: */ .align 5 sa1100_cpu_resume: - mcr p15, 0, r1, c15, c1, 2 @ enable clock switching ldmfd sp!, {r4 - r12, pc} @ return to caller -- cgit v1.2.3 From 6b5f6ab0e1c33beaed828271f13c03ed02ee3c15 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 13:39:44 +0100 Subject: ARM: pm: make MULTI_CPU and !MULTI_CPU resume paths the same Eliminate the differences between MULTI_CPU and non-MULTI_CPU resume paths, making the saved structure identical irrespective of the way the kernel was configured. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 6398ead9d1c0..97a6577aa61e 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -40,9 +40,11 @@ ENTRY(cpu_suspend) #else mov r2, sp @ current virtual SP ldr r0, =cpu_suspend_size + ldr ip, =cpu_do_resume sub sp, sp, r0 @ allocate CPU state on stack mov r0, sp @ save pointer - stmfd sp!, {r1, r2, r3} @ save v:p, virt SP, return fn + add ip, ip, r1 @ convert resume fn to phys + stmfd sp!, {r1, r2, r3, ip} @ save v:p, virt SP, retfn, phys resume fn ldr r3, =sleep_save_sp add r2, sp, r1 @ convert SP to phys #ifdef CONFIG_SMP @@ -120,20 +122,12 @@ ENTRY(cpu_resume) ldr r0, sleep_save_sp @ stack phys addr #endif setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1 @ set SVC, irqs off -#ifdef MULTI_CPU @ load v:p, stack, return fn, resume fn ARM( ldmia r0!, {r1, sp, lr, pc} ) THUMB( ldmia r0!, {r1, r2, r3, r4} ) THUMB( mov sp, r2 ) THUMB( mov lr, r3 ) THUMB( bx r4 ) -#else - @ load v:p, stack, return fn - ARM( ldmia r0!, {r1, sp, lr} ) -THUMB( ldmia r0!, {r1, r2, lr} ) -THUMB( mov sp, r2 ) - b cpu_do_resume -#endif ENDPROC(cpu_resume) sleep_save_sp: -- cgit v1.2.3 From 2fefbcd58590cf33189c6178098e12b31b994b5f Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 13:45:34 +0100 Subject: ARM: pm: move return address (for cpu_resume) to top of stack Move the return address for cpu_resume to the top of stack so that cpu_resume looks more like a normal function. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 97a6577aa61e..f8e92513c1bd 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -15,6 +15,7 @@ * r0-r3,r9,r10,lr corrupted */ ENTRY(cpu_suspend) + stmfd sp!, {r3} mov r9, lr #ifdef MULTI_CPU ldr r10, =processor @@ -24,7 +25,7 @@ ENTRY(cpu_suspend) sub sp, sp, r0 @ allocate CPU state on stack mov r0, sp @ save pointer add ip, ip, r1 @ convert resume fn to phys - stmfd sp!, {r1, r2, r3, ip} @ save v:p, virt SP, retfn, phys resume fn + stmfd sp!, {r1, r2, ip} @ save v:p, virt SP, phys resume fn ldr r3, =sleep_save_sp add r2, sp, r1 @ convert SP to phys #ifdef CONFIG_SMP @@ -44,7 +45,7 @@ ENTRY(cpu_suspend) sub sp, sp, r0 @ allocate CPU state on stack mov r0, sp @ save pointer add ip, ip, r1 @ convert resume fn to phys - stmfd sp!, {r1, r2, r3, ip} @ save v:p, virt SP, retfn, phys resume fn + stmfd sp!, {r1, r2, ip} @ save v:p, virt SP, phys resume fn ldr r3, =sleep_save_sp add r2, sp, r1 @ convert SP to phys #ifdef CONFIG_SMP @@ -99,7 +100,7 @@ ENDPROC(cpu_resume_turn_mmu_on) cpu_resume_after_mmu: str r5, [r2, r4, lsl #2] @ restore old mapping mcr p15, 0, r0, c1, c0, 0 @ turn on D-cache - mov pc, lr + ldmfd sp!, {pc} ENDPROC(cpu_resume_after_mmu) /* @@ -122,12 +123,11 @@ ENTRY(cpu_resume) ldr r0, sleep_save_sp @ stack phys addr #endif setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1 @ set SVC, irqs off - @ load v:p, stack, return fn, resume fn - ARM( ldmia r0!, {r1, sp, lr, pc} ) -THUMB( ldmia r0!, {r1, r2, r3, r4} ) + @ load v:p, stack, resume fn + ARM( ldmia r0!, {r1, sp, pc} ) +THUMB( ldmia r0!, {r1, r2, r3} ) THUMB( mov sp, r2 ) -THUMB( mov lr, r3 ) -THUMB( bx r4 ) +THUMB( bx r3 ) ENDPROC(cpu_resume) sleep_save_sp: -- cgit v1.2.3 From 3fd431bd0cbc75a506b90b42619de3b04fe813a7 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 13:53:06 +0100 Subject: ARM: pm: extract common code from MULTI_CPU/!MULTI_CPU paths Very little code is different between these two paths now, so extract the common code. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index f8e92513c1bd..0a778c30859b 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -19,29 +19,13 @@ ENTRY(cpu_suspend) mov r9, lr #ifdef MULTI_CPU ldr r10, =processor - mov r2, sp @ current virtual SP ldr r0, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state ldr ip, [r10, #CPU_DO_RESUME] @ virtual resume function - sub sp, sp, r0 @ allocate CPU state on stack - mov r0, sp @ save pointer - add ip, ip, r1 @ convert resume fn to phys - stmfd sp!, {r1, r2, ip} @ save v:p, virt SP, phys resume fn - ldr r3, =sleep_save_sp - add r2, sp, r1 @ convert SP to phys -#ifdef CONFIG_SMP - ALT_SMP(mrc p15, 0, lr, c0, c0, 5) - ALT_UP(mov lr, #0) - and lr, lr, #15 - str r2, [r3, lr, lsl #2] @ save phys SP #else - str r2, [r3] @ save phys SP -#endif - mov lr, pc - ldr pc, [r10, #CPU_DO_SUSPEND] @ save CPU state -#else - mov r2, sp @ current virtual SP ldr r0, =cpu_suspend_size ldr ip, =cpu_do_resume +#endif + mov r2, sp @ current virtual SP sub sp, sp, r0 @ allocate CPU state on stack mov r0, sp @ save pointer add ip, ip, r1 @ convert resume fn to phys @@ -56,6 +40,10 @@ ENTRY(cpu_suspend) #else str r2, [r3] @ save phys SP #endif +#ifdef MULTI_CPU + mov lr, pc + ldr pc, [r10, #CPU_DO_SUSPEND] @ save CPU state +#else bl cpu_do_suspend #endif -- cgit v1.2.3 From 5fa94c812c0001ac7c3d8868e956ec514734a352 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 15:04:14 +0100 Subject: ARM: pm: preserve r4 - r11 across a suspend Make cpu_suspend()..return function preserve r4 to r11 across a suspend cycle. This is in preparation of relieving platform support code from this task. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 0a778c30859b..8dbca93417ff 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -12,10 +12,11 @@ * r1 = v:p offset * r3 = virtual return function * Note: sp is decremented to allocate space for CPU state on stack - * r0-r3,r9,r10,lr corrupted + * r0-r3,ip,lr corrupted */ ENTRY(cpu_suspend) stmfd sp!, {r3} + stmfd sp!, {r4 - r11} mov r9, lr #ifdef MULTI_CPU ldr r10, =processor @@ -88,7 +89,7 @@ ENDPROC(cpu_resume_turn_mmu_on) cpu_resume_after_mmu: str r5, [r2, r4, lsl #2] @ restore old mapping mcr p15, 0, r0, c1, c0, 0 @ turn on D-cache - ldmfd sp!, {pc} + ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_resume_after_mmu) /* -- cgit v1.2.3 From 8111eaa6d424ab3ba8a4d7a3148d4681ae5c6ae3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 15:25:11 +0100 Subject: ARM: pm: reallocate registers to avoid r2, r3 Avoid using r2 and r3 in the suspend code, allowing these to be passed further into the function as arguments. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 8dbca93417ff..358be13499da 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -20,26 +20,26 @@ ENTRY(cpu_suspend) mov r9, lr #ifdef MULTI_CPU ldr r10, =processor - ldr r0, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state + ldr r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state ldr ip, [r10, #CPU_DO_RESUME] @ virtual resume function #else - ldr r0, =cpu_suspend_size + ldr r5, =cpu_suspend_size ldr ip, =cpu_do_resume #endif - mov r2, sp @ current virtual SP - sub sp, sp, r0 @ allocate CPU state on stack + mov r6, sp @ current virtual SP + sub sp, sp, r5 @ allocate CPU state on stack mov r0, sp @ save pointer add ip, ip, r1 @ convert resume fn to phys - stmfd sp!, {r1, r2, ip} @ save v:p, virt SP, phys resume fn - ldr r3, =sleep_save_sp - add r2, sp, r1 @ convert SP to phys + stmfd sp!, {r1, r6, ip} @ save v:p, virt SP, phys resume fn + ldr r5, =sleep_save_sp + add r6, sp, r1 @ convert SP to phys #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, lr, c0, c0, 5) ALT_UP(mov lr, #0) and lr, lr, #15 - str r2, [r3, lr, lsl #2] @ save phys SP + str r6, [r5, lr, lsl #2] @ save phys SP #else - str r2, [r3] @ save phys SP + str r6, [r5] @ save phys SP #endif #ifdef MULTI_CPU mov lr, pc -- cgit v1.2.3 From 3799bbe57843d279008c9ec3406838966cad5f15 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 15:28:40 +0100 Subject: ARM: pm: rejig suspend follow-on function calling convention Save the suspend function pointer onto the stack for use when returning. Allocate r2 to pass an argument to the suspend function. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 358be13499da..b924bcc32dcd 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -10,6 +10,7 @@ /* * Save CPU state for a suspend * r1 = v:p offset + * r2 = suspend function arg0 * r3 = virtual return function * Note: sp is decremented to allocate space for CPU state on stack * r0-r3,ip,lr corrupted @@ -17,7 +18,6 @@ ENTRY(cpu_suspend) stmfd sp!, {r3} stmfd sp!, {r4 - r11} - mov r9, lr #ifdef MULTI_CPU ldr r10, =processor ldr r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state @@ -33,6 +33,7 @@ ENTRY(cpu_suspend) stmfd sp!, {r1, r6, ip} @ save v:p, virt SP, phys resume fn ldr r5, =sleep_save_sp add r6, sp, r1 @ convert SP to phys + stmfd sp!, {r2, lr} @ save suspend func arg and pointer #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, lr, c0, c0, 5) ALT_UP(mov lr, #0) @@ -51,12 +52,12 @@ ENTRY(cpu_suspend) @ flush data cache #ifdef MULTI_CACHE ldr r10, =cpu_cache - mov lr, r9 + mov lr, pc ldr pc, [r10, #CACHE_FLUSH_KERN_ALL] #else - mov lr, r9 - b __cpuc_flush_kern_all + bl __cpuc_flush_kern_all #endif + ldmfd sp!, {r0, pc} @ call suspend fn ENDPROC(cpu_suspend) .ltorg -- cgit v1.2.3 From dbc125168fd7dda4ffb24a29548746c7bd3b3d87 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 15:52:47 +0100 Subject: ARM: pm: move sa1100 to use proper suspend func arg0 In the previous commit, we introduced an official way to supply an argument to the suspend function. Convert the sa1100 suspend code to use this method. Signed-off-by: Russell King --- arch/arm/mach-pxa/sleep.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S index 6f5368899d84..613ddfa2c295 100644 --- a/arch/arm/mach-pxa/sleep.S +++ b/arch/arm/mach-pxa/sleep.S @@ -59,7 +59,7 @@ ENTRY(pxa27x_cpu_suspend) mra r2, r3, acc0 #endif stmfd sp!, {r2 - r12, lr} @ save registers on stack - mov r4, r0 @ save sleep mode + mov r2, r0 @ save sleep mode ldr r3, =pxa_cpu_resume @ resume function bl cpu_suspend @@ -67,7 +67,7 @@ ENTRY(pxa27x_cpu_suspend) @ (also workaround for sighting 28071) @ prepare value for sleep mode - mov r1, r4 @ sleep mode + mov r1, r0 @ sleep mode @ prepare pointer to physical address 0 (virtual mapping in generic.c) mov r2, #UNCACHED_PHYS_0 @@ -109,11 +109,11 @@ ENTRY(pxa27x_cpu_suspend) ENTRY(pxa25x_cpu_suspend) stmfd sp!, {r2 - r12, lr} @ save registers on stack - mov r4, r0 @ save sleep mode + mov r2, r0 @ save sleep mode ldr r3, =pxa_cpu_resume @ resume function bl cpu_suspend @ prepare value for sleep mode - mov r1, r4 @ sleep mode + mov r1, r0 @ sleep mode @ prepare pointer to physical address 0 (virtual mapping in generic.c) mov r2, #UNCACHED_PHYS_0 -- cgit v1.2.3 From e8856a8797e76e6883ae81f8f9ecbb231cc535df Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 15:58:34 +0100 Subject: ARM: pm: convert cpu_suspend() to a normal function cpu_suspend() has a weird calling method which makes it only possible to call from assembly code: it returns with a modified stack pointer to finish the suspend, but on resume, it 'returns' via a provided pointer. We can make cpu_suspend() appear to be a normal function merely by swapping the resume pointer argument and the link register. Do so, and update all callers to take account of this more traditional behaviour. Acked-by: Frank Hofmann Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/include/asm/system.h | 2 ++ arch/arm/kernel/sleep.S | 10 ++++------ arch/arm/mach-exynos4/sleep.S | 7 +++---- arch/arm/mach-pxa/sleep.S | 13 ++++++++++--- arch/arm/mach-s3c64xx/sleep.S | 9 +++------ arch/arm/mach-s5pv210/sleep.S | 7 +++---- arch/arm/mach-sa1100/sleep.S | 13 +++---------- arch/arm/plat-s3c24xx/sleep.S | 10 +++------- 8 files changed, 31 insertions(+), 40 deletions(-) diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 832888d0c20c..50be6055df89 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -106,6 +106,8 @@ extern void __show_regs(struct pt_regs *); extern int cpu_architecture(void); extern void cpu_init(void); +extern void cpu_suspend(int, long, unsigned long, void (*)(unsigned long)); +extern void cpu_resume(void); void arm_machine_restart(char mode, const char *cmd); extern void (*arm_pm_restart)(char str, const char *cmd); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index b924bcc32dcd..e0626779fe92 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -11,13 +11,11 @@ * Save CPU state for a suspend * r1 = v:p offset * r2 = suspend function arg0 - * r3 = virtual return function - * Note: sp is decremented to allocate space for CPU state on stack - * r0-r3,ip,lr corrupted + * r3 = suspend function + * Note: does not return until system resumes */ ENTRY(cpu_suspend) - stmfd sp!, {r3} - stmfd sp!, {r4 - r11} + stmfd sp!, {r4 - r11, lr} #ifdef MULTI_CPU ldr r10, =processor ldr r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state @@ -33,7 +31,7 @@ ENTRY(cpu_suspend) stmfd sp!, {r1, r6, ip} @ save v:p, virt SP, phys resume fn ldr r5, =sleep_save_sp add r6, sp, r1 @ convert SP to phys - stmfd sp!, {r2, lr} @ save suspend func arg and pointer + stmfd sp!, {r2, r3} @ save suspend func arg and pointer #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, lr, c0, c0, 5) ALT_UP(mov lr, #0) diff --git a/arch/arm/mach-exynos4/sleep.S b/arch/arm/mach-exynos4/sleep.S index 6b62425417a6..d9a2287b4641 100644 --- a/arch/arm/mach-exynos4/sleep.S +++ b/arch/arm/mach-exynos4/sleep.S @@ -42,16 +42,15 @@ ENTRY(s3c_cpu_save) stmfd sp!, { r3 - r12, lr } - ldr r3, =resume_with_mmu + adr r3, BSYM(exynos4_finish_suspend) bl cpu_suspend + ldmfd sp!, { r3 - r12, pc } +exynos4_finish_suspend: ldr r0, =pm_cpu_sleep ldr r0, [ r0 ] mov pc, r0 -resume_with_mmu: - ldmfd sp!, { r3 - r12, pc } - .ltorg /* diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S index 613ddfa2c295..3a67887e6dbd 100644 --- a/arch/arm/mach-pxa/sleep.S +++ b/arch/arm/mach-pxa/sleep.S @@ -35,9 +35,11 @@ ENTRY(pxa3xx_cpu_suspend) #endif stmfd sp!, {r2 - r12, lr} @ save registers on stack mov r1, r0 - ldr r3, =pxa_cpu_resume @ resume function + adr r3, BSYM(pxa3xx_finish_suspend) bl cpu_suspend + b pxa_cpu_resume +pxa3xx_finish_suspend: mov r0, #0x06 @ S2D3C4 mode mcr p14, 0, r0, c7, c0, 0 @ enter sleep @@ -60,9 +62,11 @@ ENTRY(pxa27x_cpu_suspend) #endif stmfd sp!, {r2 - r12, lr} @ save registers on stack mov r2, r0 @ save sleep mode - ldr r3, =pxa_cpu_resume @ resume function + adr r3, BSYM(pxa27x_finish_suspend) bl cpu_suspend + b pxa_cpu_resume +pxa27x_finish_suspend: @ Put the processor to sleep @ (also workaround for sighting 28071) @@ -110,8 +114,11 @@ ENTRY(pxa27x_cpu_suspend) ENTRY(pxa25x_cpu_suspend) stmfd sp!, {r2 - r12, lr} @ save registers on stack mov r2, r0 @ save sleep mode - ldr r3, =pxa_cpu_resume @ resume function + adr r3, BSYM(pxa25x_finish_suspend) bl cpu_suspend + b pxa_cpu_resume + +pxa25x_finish_suspend: @ prepare value for sleep mode mov r1, r0 @ sleep mode diff --git a/arch/arm/mach-s3c64xx/sleep.S b/arch/arm/mach-s3c64xx/sleep.S index 1f87732b2320..dc4f58202101 100644 --- a/arch/arm/mach-s3c64xx/sleep.S +++ b/arch/arm/mach-s3c64xx/sleep.S @@ -36,18 +36,15 @@ ENTRY(s3c_cpu_save) stmfd sp!, { r4 - r12, lr } - ldr r3, =resume_with_mmu + adr r3, BSYM(s3c64xx_finish_suspend) bl cpu_suspend + ldmfd sp!, { r4 - r12, pc } +s3c64xx_finish_suspend: @@ call final suspend code ldr r0, =pm_cpu_sleep ldr pc, [r0] - @@ return to the caller, after the MMU is turned on. - @@ restore the last bits of the stack and return. -resume_with_mmu: - ldmfd sp!, { r4 - r12, pc } @ return, from sp from s3c_cpu_save - /* Sleep magic, the word before the resume entry point so that the * bootloader can check for a resumeable image. */ diff --git a/arch/arm/mach-s5pv210/sleep.S b/arch/arm/mach-s5pv210/sleep.S index a3d649466fb1..1182fc848a79 100644 --- a/arch/arm/mach-s5pv210/sleep.S +++ b/arch/arm/mach-s5pv210/sleep.S @@ -41,16 +41,15 @@ ENTRY(s3c_cpu_save) stmfd sp!, { r3 - r12, lr } - ldr r3, =resume_with_mmu + adr r3, BSYM(s5pv210_finish_suspend) bl cpu_suspend + ldmfd sp!, { r3 - r12, pc } +s5pv210_finish_suspend: ldr r0, =pm_cpu_sleep ldr r0, [ r0 ] mov pc, r0 -resume_with_mmu: - ldmfd sp!, { r3 - r12, pc } - .ltorg /* sleep magic, to allow the bootloader to check for an valid diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S index 122ab3c66923..f3fe39773f8b 100644 --- a/arch/arm/mach-sa1100/sleep.S +++ b/arch/arm/mach-sa1100/sleep.S @@ -31,9 +31,11 @@ ENTRY(sa1100_cpu_suspend) stmfd sp!, {r4 - r12, lr} @ save registers on stack mov r1, r0 - ldr r3, =sa1100_cpu_resume @ return function + adr r3, BSYM(sa1100_finish_suspend) bl cpu_suspend + ldmfd sp!, {r4 - r12, pc} @ return to caller +sa1100_finish_suspend: @ disable clock switching mcr p15, 0, r1, c15, c2, 2 @@ -139,12 +141,3 @@ sa1110_sdram_controller_fix: str r13, [r12] 20: b 20b @ loop waiting for sleep - -/* - * cpu_sa1100_resume() - * - * entry point from bootloader into kernel during resume - */ - .align 5 -sa1100_cpu_resume: - ldmfd sp!, {r4 - r12, pc} @ return to caller diff --git a/arch/arm/plat-s3c24xx/sleep.S b/arch/arm/plat-s3c24xx/sleep.S index fd7032f84ae7..f822e6282dd4 100644 --- a/arch/arm/plat-s3c24xx/sleep.S +++ b/arch/arm/plat-s3c24xx/sleep.S @@ -49,21 +49,17 @@ ENTRY(s3c_cpu_save) stmfd sp!, { r4 - r12, lr } - ldr r3, =resume_with_mmu + adr r3, BSYM(s3c24xx_finish_suspend) bl cpu_suspend + ldmfd sp!, { r4 - r12, pc } +s3c24xx_finish_suspend: @@ jump to final code to send system to sleep ldr r0, =pm_cpu_sleep @@ldr pc, [ r0 ] ldr r0, [ r0 ] mov pc, r0 - @@ return to the caller, after having the MMU - @@ turned on, this restores the last bits from the - @@ stack -resume_with_mmu: - ldmfd sp!, { r4 - r12, pc } - .ltorg /* sleep magic, to allow the bootloader to check for an valid -- cgit v1.2.3 From 14cd8fd574bce1cfbe510ccb1f73c7c1024d770f Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 16:32:58 +0100 Subject: ARM: pm: move cpu_init() call into core code As we have core code dealing with CPU suspend/resume, we can re-initialize the CPUs exception banked registers via that code rather than having platforms deal with that level of detail. So, move the call to cpu_init() out of platform code into core code. Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/kernel/sleep.S | 1 + arch/arm/mach-pxa/pm.c | 1 - arch/arm/mach-sa1100/pm.c | 2 -- arch/arm/plat-samsung/pm.c | 4 ---- 4 files changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index e0626779fe92..53922748d101 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -88,6 +88,7 @@ ENDPROC(cpu_resume_turn_mmu_on) cpu_resume_after_mmu: str r5, [r2, r4, lsl #2] @ restore old mapping mcr p15, 0, r0, c1, c0, 0 @ turn on D-cache + bl cpu_init @ restore the und/abt/irq banked regs ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_resume_after_mmu) diff --git a/arch/arm/mach-pxa/pm.c b/arch/arm/mach-pxa/pm.c index 51e1583265b2..37178a8559b1 100644 --- a/arch/arm/mach-pxa/pm.c +++ b/arch/arm/mach-pxa/pm.c @@ -42,7 +42,6 @@ int pxa_pm_enter(suspend_state_t state) /* *** go zzz *** */ pxa_cpu_pm_fns->enter(state); - cpu_init(); if (state != PM_SUSPEND_STANDBY && pxa_cpu_pm_fns->restore) { /* after sleeping, validate the checksum */ diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index c4661aab22fb..d35885ca97a1 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -77,8 +77,6 @@ static int sa11x0_pm_enter(suspend_state_t state) /* go zzz */ sa1100_cpu_suspend(PLAT_PHYS_OFFSET - PAGE_OFFSET); - cpu_init(); - /* * Ensure not to come back here if it wasn't intended */ diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c index 5c0a440d6e16..3828191416b5 100644 --- a/arch/arm/plat-samsung/pm.c +++ b/arch/arm/plat-samsung/pm.c @@ -300,10 +300,6 @@ static int s3c_pm_enter(suspend_state_t state) s3c_cpu_save(0, PLAT_PHYS_OFFSET - PAGE_OFFSET); - /* restore the cpu state using the kernel's cpu init code. */ - - cpu_init(); - /* restore the system state */ s3c_pm_restore_core(); -- cgit v1.2.3 From 34c79de6b2ea5bc5734d970851fb966b49d55a17 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 16:26:29 +0100 Subject: ARM: pm: sa1100: move cpu_suspend into C code We don't need a veneer for cpu_suspend, it can be called directly from C code now. Move it into sa11x0_pm_enter() along with the re-enabling of clock switching. Signed-off-by: Russell King --- arch/arm/mach-sa1100/pm.c | 4 ++-- arch/arm/mach-sa1100/sleep.S | 11 ++--------- 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index d35885ca97a1..259ed3bcc3fe 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -32,7 +32,7 @@ #include #include -extern void sa1100_cpu_suspend(long); +extern void sa1100_finish_suspend(unsigned long); #define SAVE(x) sleep_save[SLEEP_SAVE_##x] = x #define RESTORE(x) x = sleep_save[SLEEP_SAVE_##x] @@ -75,7 +75,7 @@ static int sa11x0_pm_enter(suspend_state_t state) PSPR = virt_to_phys(cpu_resume); /* go zzz */ - sa1100_cpu_suspend(PLAT_PHYS_OFFSET - PAGE_OFFSET); + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, 0, sa1100_finish_suspend); /* * Ensure not to come back here if it wasn't intended diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S index f3fe39773f8b..e8223315b442 100644 --- a/arch/arm/mach-sa1100/sleep.S +++ b/arch/arm/mach-sa1100/sleep.S @@ -22,20 +22,13 @@ .text /* - * sa1100_cpu_suspend() + * sa1100_finish_suspend() * * Causes sa11x0 to enter sleep state * */ -ENTRY(sa1100_cpu_suspend) - stmfd sp!, {r4 - r12, lr} @ save registers on stack - mov r1, r0 - adr r3, BSYM(sa1100_finish_suspend) - bl cpu_suspend - ldmfd sp!, {r4 - r12, pc} @ return to caller - -sa1100_finish_suspend: +ENTRY(sa1100_finish_suspend) @ disable clock switching mcr p15, 0, r1, c15, c2, 2 -- cgit v1.2.3 From c4ac82c07dd3e4fb5d65a52ffa94e302f80b609d Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 16:03:19 +0100 Subject: ARM: pm: plat-s3c24xx: cleanup s3c_cpu_save s3c_cpu_save does not need to save any registers with the new cpu_suspend calling convention. Remove these redundant instructions. Tested-by: Kukjin Kim Signed-off-by: Russell King --- arch/arm/plat-s3c24xx/sleep.S | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/plat-s3c24xx/sleep.S b/arch/arm/plat-s3c24xx/sleep.S index f822e6282dd4..6ada459498a8 100644 --- a/arch/arm/plat-s3c24xx/sleep.S +++ b/arch/arm/plat-s3c24xx/sleep.S @@ -48,10 +48,8 @@ */ ENTRY(s3c_cpu_save) - stmfd sp!, { r4 - r12, lr } adr r3, BSYM(s3c24xx_finish_suspend) - bl cpu_suspend - ldmfd sp!, { r4 - r12, pc } + b cpu_suspend s3c24xx_finish_suspend: @@ jump to final code to send system to sleep -- cgit v1.2.3 From 3d32ead3f16f054fa7f4a85a34eb12c36fd76269 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 16:10:16 +0100 Subject: ARM: pm: mach-s5pv210: cleanup s3c_cpu_save s3c_cpu_save does not need to save any registers with the new cpu_suspend calling convention. Remove these redundant instructions. Signed-off-by: Russell King --- arch/arm/mach-s5pv210/sleep.S | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/arm/mach-s5pv210/sleep.S b/arch/arm/mach-s5pv210/sleep.S index 1182fc848a79..28dfeff342b8 100644 --- a/arch/arm/mach-s5pv210/sleep.S +++ b/arch/arm/mach-s5pv210/sleep.S @@ -39,11 +39,8 @@ */ ENTRY(s3c_cpu_save) - - stmfd sp!, { r3 - r12, lr } adr r3, BSYM(s5pv210_finish_suspend) - bl cpu_suspend - ldmfd sp!, { r3 - r12, pc } + b cpu_suspend s5pv210_finish_suspend: ldr r0, =pm_cpu_sleep -- cgit v1.2.3 From 769783a9300d47236766345cc98ce963122c2e4f Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 16:12:27 +0100 Subject: ARM: pm: mach-exynos4: cleanup s3c_cpu_save s3c_cpu_save does not need to save any registers with the new cpu_suspend calling convention. Remove these redundant instructions. Signed-off-by: Russell King --- arch/arm/mach-exynos4/sleep.S | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/arm/mach-exynos4/sleep.S b/arch/arm/mach-exynos4/sleep.S index d9a2287b4641..b56a4914985c 100644 --- a/arch/arm/mach-exynos4/sleep.S +++ b/arch/arm/mach-exynos4/sleep.S @@ -40,11 +40,8 @@ */ ENTRY(s3c_cpu_save) - - stmfd sp!, { r3 - r12, lr } adr r3, BSYM(exynos4_finish_suspend) - bl cpu_suspend - ldmfd sp!, { r3 - r12, pc } + b cpu_suspend exynos4_finish_suspend: ldr r0, =pm_cpu_sleep -- cgit v1.2.3 From 4d01446fea61a32b6755ae1e11314ffca744dcaa Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 13 Jun 2011 16:33:30 +0100 Subject: ARM: pm: mach-s3c64xx: cleanup s3c_cpu_save s3c_cpu_save does not need to save any registers with the new cpu_suspend calling convention. Remove these redundant instructions. Acked-by: Frank Hofmann Signed-off-by: Russell King --- arch/arm/mach-s3c64xx/sleep.S | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/mach-s3c64xx/sleep.S b/arch/arm/mach-s3c64xx/sleep.S index dc4f58202101..2fd343332838 100644 --- a/arch/arm/mach-s3c64xx/sleep.S +++ b/arch/arm/mach-s3c64xx/sleep.S @@ -35,10 +35,8 @@ */ ENTRY(s3c_cpu_save) - stmfd sp!, { r4 - r12, lr } adr r3, BSYM(s3c64xx_finish_suspend) - bl cpu_suspend - ldmfd sp!, { r4 - r12, pc } + b cpu_suspend s3c64xx_finish_suspend: @@ call final suspend code -- cgit v1.2.3 From e7089da9567fa8da37e35e1f81a5e3579d0d582d Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 19:29:26 +0100 Subject: ARM: pm: samsung: move cpu_suspend into C code Move the call to cpu_suspend into C code, and noticing that all the s3c_cpu_save implementations are now identical, we can move this into the common samsung code. Signed-off-by: Russell King --- arch/arm/mach-exynos4/pm.c | 2 +- arch/arm/mach-exynos4/sleep.S | 18 ------------------ arch/arm/mach-s3c2412/pm.c | 2 +- arch/arm/mach-s3c2416/pm.c | 2 +- arch/arm/mach-s3c64xx/pm.c | 2 +- arch/arm/mach-s3c64xx/sleep.S | 18 ------------------ arch/arm/mach-s5pv210/pm.c | 2 +- arch/arm/mach-s5pv210/sleep.S | 17 ----------------- arch/arm/plat-s3c24xx/sleep.S | 19 ------------------- arch/arm/plat-samsung/include/plat/pm.h | 5 ++--- arch/arm/plat-samsung/pm.c | 6 +++--- 11 files changed, 10 insertions(+), 83 deletions(-) diff --git a/arch/arm/mach-exynos4/pm.c b/arch/arm/mach-exynos4/pm.c index 8755ca8dd48d..5c01c6076645 100644 --- a/arch/arm/mach-exynos4/pm.c +++ b/arch/arm/mach-exynos4/pm.c @@ -280,7 +280,7 @@ static struct sleep_save exynos4_l2cc_save[] = { SAVE_ITEM(S5P_VA_L2CC + L2X0_AUX_CTRL), }; -void exynos4_cpu_suspend(void) +void exynos4_cpu_suspend(unsigned long arg) { unsigned long tmp; unsigned long mask = 0xFFFFFFFF; diff --git a/arch/arm/mach-exynos4/sleep.S b/arch/arm/mach-exynos4/sleep.S index b56a4914985c..0984078f1eba 100644 --- a/arch/arm/mach-exynos4/sleep.S +++ b/arch/arm/mach-exynos4/sleep.S @@ -32,24 +32,6 @@ .text - /* - * s3c_cpu_save - * - * entry: - * r1 = v:p offset - */ - -ENTRY(s3c_cpu_save) - adr r3, BSYM(exynos4_finish_suspend) - b cpu_suspend - -exynos4_finish_suspend: - ldr r0, =pm_cpu_sleep - ldr r0, [ r0 ] - mov pc, r0 - - .ltorg - /* * sleep magic, to allow the bootloader to check for an valid * image to resume to. Must be the first word before the diff --git a/arch/arm/mach-s3c2412/pm.c b/arch/arm/mach-s3c2412/pm.c index 752b13a7b3db..fecd85489e51 100644 --- a/arch/arm/mach-s3c2412/pm.c +++ b/arch/arm/mach-s3c2412/pm.c @@ -37,7 +37,7 @@ extern void s3c2412_sleep_enter(void); -static void s3c2412_cpu_suspend(void) +static void s3c2412_cpu_suspend(unsigned long arg) { unsigned long tmp; diff --git a/arch/arm/mach-s3c2416/pm.c b/arch/arm/mach-s3c2416/pm.c index 41db2b21e213..268fda744201 100644 --- a/arch/arm/mach-s3c2416/pm.c +++ b/arch/arm/mach-s3c2416/pm.c @@ -24,7 +24,7 @@ extern void s3c2412_sleep_enter(void); -static void s3c2416_cpu_suspend(void) +static void s3c2416_cpu_suspend(unsigned long arg) { flush_cache_all(); diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c index bc1c470b7de6..7cc1879af722 100644 --- a/arch/arm/mach-s3c64xx/pm.c +++ b/arch/arm/mach-s3c64xx/pm.c @@ -112,7 +112,7 @@ void s3c_pm_save_core(void) * this. */ -static void s3c64xx_cpu_suspend(void) +static void s3c64xx_cpu_suspend(unsigned long arg) { unsigned long tmp; diff --git a/arch/arm/mach-s3c64xx/sleep.S b/arch/arm/mach-s3c64xx/sleep.S index 2fd343332838..34313f9c8792 100644 --- a/arch/arm/mach-s3c64xx/sleep.S +++ b/arch/arm/mach-s3c64xx/sleep.S @@ -25,24 +25,6 @@ .text - /* s3c_cpu_save - * - * Save enough processor state to allow the restart of the pm.c - * code after resume. - * - * entry: - * r1 = v:p offset - */ - -ENTRY(s3c_cpu_save) - adr r3, BSYM(s3c64xx_finish_suspend) - b cpu_suspend - -s3c64xx_finish_suspend: - @@ call final suspend code - ldr r0, =pm_cpu_sleep - ldr pc, [r0] - /* Sleep magic, the word before the resume entry point so that the * bootloader can check for a resumeable image. */ diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c index 24febae3d4c0..309e388a8a83 100644 --- a/arch/arm/mach-s5pv210/pm.c +++ b/arch/arm/mach-s5pv210/pm.c @@ -88,7 +88,7 @@ static struct sleep_save s5pv210_core_save[] = { SAVE_ITEM(S3C2410_TCNTO(0)), }; -void s5pv210_cpu_suspend(void) +void s5pv210_cpu_suspend(unsigned long arg) { unsigned long tmp; diff --git a/arch/arm/mach-s5pv210/sleep.S b/arch/arm/mach-s5pv210/sleep.S index 28dfeff342b8..e3452ccd4b08 100644 --- a/arch/arm/mach-s5pv210/sleep.S +++ b/arch/arm/mach-s5pv210/sleep.S @@ -32,23 +32,6 @@ .text - /* s3c_cpu_save - * - * entry: - * r1 = v:p offset - */ - -ENTRY(s3c_cpu_save) - adr r3, BSYM(s5pv210_finish_suspend) - b cpu_suspend - -s5pv210_finish_suspend: - ldr r0, =pm_cpu_sleep - ldr r0, [ r0 ] - mov pc, r0 - - .ltorg - /* sleep magic, to allow the bootloader to check for an valid * image to resume to. Must be the first word before the * s3c_cpu_resume entry. diff --git a/arch/arm/plat-s3c24xx/sleep.S b/arch/arm/plat-s3c24xx/sleep.S index 6ada459498a8..c56612569b40 100644 --- a/arch/arm/plat-s3c24xx/sleep.S +++ b/arch/arm/plat-s3c24xx/sleep.S @@ -41,25 +41,6 @@ .text - /* s3c_cpu_save - * - * entry: - * r1 = v:p offset - */ - -ENTRY(s3c_cpu_save) - adr r3, BSYM(s3c24xx_finish_suspend) - b cpu_suspend - -s3c24xx_finish_suspend: - @@ jump to final code to send system to sleep - ldr r0, =pm_cpu_sleep - @@ldr pc, [ r0 ] - ldr r0, [ r0 ] - mov pc, r0 - - .ltorg - /* sleep magic, to allow the bootloader to check for an valid * image to resume to. Must be the first word before the * s3c_cpu_resume entry. diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h index 7fb6f6be8c81..0a5b7faca836 100644 --- a/arch/arm/plat-samsung/include/plat/pm.h +++ b/arch/arm/plat-samsung/include/plat/pm.h @@ -42,7 +42,7 @@ extern unsigned long s3c_irqwake_eintallow; /* per-cpu sleep functions */ extern void (*pm_cpu_prep)(void); -extern void (*pm_cpu_sleep)(void); +extern void (*pm_cpu_sleep)(unsigned long); /* Flags for PM Control */ @@ -52,10 +52,9 @@ extern unsigned char pm_uart_udivslot; /* true to save UART UDIVSLOT */ /* from sleep.S */ -extern int s3c_cpu_save(unsigned long *saveblk, long); extern void s3c_cpu_resume(void); -extern void s3c2410_cpu_suspend(void); +extern void s3c2410_cpu_suspend(unsigned long); /* sleep save info */ diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c index 3828191416b5..3a6d0768ba0c 100644 --- a/arch/arm/plat-samsung/pm.c +++ b/arch/arm/plat-samsung/pm.c @@ -231,7 +231,7 @@ static void __maybe_unused s3c_pm_show_resume_irqs(int start, void (*pm_cpu_prep)(void); -void (*pm_cpu_sleep)(void); +void (*pm_cpu_sleep)(unsigned long); #define any_allowed(mask, allow) (((mask) & (allow)) != (allow)) @@ -294,11 +294,11 @@ static int s3c_pm_enter(suspend_state_t state) s3c_pm_arch_stop_clocks(); - /* s3c_cpu_save will also act as our return point from when + /* this will also act as our return point from when * we resume as it saves its own register state and restores it * during the resume. */ - s3c_cpu_save(0, PLAT_PHYS_OFFSET - PAGE_OFFSET); + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, 0, pm_cpu_sleep); /* restore the system state */ -- cgit v1.2.3 From 372c0ac8aca7655b6a8920b10bf9563402ac19d8 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 19:34:34 +0100 Subject: ARM: pm: samsung: no need to call flush_cache_all() The core suspend code calls flush_cache_all() immediately prior to calling the suspend finisher function, so remove these needless calls from the finisher functions. Signed-off-by: Russell King --- arch/arm/mach-s3c2412/pm.c | 2 -- arch/arm/mach-s3c2416/pm.c | 2 -- 2 files changed, 4 deletions(-) diff --git a/arch/arm/mach-s3c2412/pm.c b/arch/arm/mach-s3c2412/pm.c index fecd85489e51..9a1fb898db53 100644 --- a/arch/arm/mach-s3c2412/pm.c +++ b/arch/arm/mach-s3c2412/pm.c @@ -41,8 +41,6 @@ static void s3c2412_cpu_suspend(unsigned long arg) { unsigned long tmp; - flush_cache_all(); - /* set our standby method to sleep */ tmp = __raw_readl(S3C2412_PWRCFG); diff --git a/arch/arm/mach-s3c2416/pm.c b/arch/arm/mach-s3c2416/pm.c index 268fda744201..9e67a2a07a86 100644 --- a/arch/arm/mach-s3c2416/pm.c +++ b/arch/arm/mach-s3c2416/pm.c @@ -26,8 +26,6 @@ extern void s3c2412_sleep_enter(void); static void s3c2416_cpu_suspend(unsigned long arg) { - flush_cache_all(); - /* enable wakeup sources regardless of battery state */ __raw_writel(S3C2443_PWRCFG_SLEEP, S3C2443_PWRCFG); -- cgit v1.2.3 From a9503d2185bbc28e498c435a07f24986c48b5cbe Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jun 2011 16:29:30 +0100 Subject: ARM: pm: pxa: move cpu_suspend into C code We don't need a veneer for cpu_suspend, it can be called directly from C code now. Move it into the PXA CPU suspend functions, along with the accumulator register saving/restoring. Signed-off-by: Russell King --- arch/arm/mach-pxa/include/mach/pm.h | 4 +-- arch/arm/mach-pxa/pxa25x.c | 3 +- arch/arm/mach-pxa/pxa27x.c | 11 ++++++- arch/arm/mach-pxa/pxa3xx.c | 13 +++++++-- arch/arm/mach-pxa/sleep.S | 58 ++++--------------------------------- arch/arm/mach-pxa/zeus.c | 3 +- 6 files changed, 33 insertions(+), 59 deletions(-) diff --git a/arch/arm/mach-pxa/include/mach/pm.h b/arch/arm/mach-pxa/include/mach/pm.h index f15afe012995..a566720527cf 100644 --- a/arch/arm/mach-pxa/include/mach/pm.h +++ b/arch/arm/mach-pxa/include/mach/pm.h @@ -22,8 +22,8 @@ struct pxa_cpu_pm_fns { extern struct pxa_cpu_pm_fns *pxa_cpu_pm_fns; /* sleep.S */ -extern void pxa25x_cpu_suspend(unsigned int, long); -extern void pxa27x_cpu_suspend(unsigned int, long); +extern void pxa25x_finish_suspend(unsigned long); +extern void pxa27x_finish_suspend(unsigned long); extern int pxa_pm_enter(suspend_state_t state); extern int pxa_pm_prepare(void); diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c index fed363cec9c6..fd7725cb5c01 100644 --- a/arch/arm/mach-pxa/pxa25x.c +++ b/arch/arm/mach-pxa/pxa25x.c @@ -244,7 +244,8 @@ static void pxa25x_cpu_pm_enter(suspend_state_t state) switch (state) { case PM_SUSPEND_MEM: - pxa25x_cpu_suspend(PWRMODE_SLEEP, PLAT_PHYS_OFFSET - PAGE_OFFSET); + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, PWRMODE_SLEEP, + pxa25x_finish_suspend); break; } } diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c index 2fecbec58d88..824379d43758 100644 --- a/arch/arm/mach-pxa/pxa27x.c +++ b/arch/arm/mach-pxa/pxa27x.c @@ -284,6 +284,11 @@ void pxa27x_cpu_pm_restore(unsigned long *sleep_save) void pxa27x_cpu_pm_enter(suspend_state_t state) { extern void pxa_cpu_standby(void); +#ifndef CONFIG_IWMMXT + u64 acc0; + + asm volatile("mra %Q0, %R0, acc0" : "=r" (acc0)); +#endif /* ensure voltage-change sequencer not initiated, which hangs */ PCFR &= ~PCFR_FVC; @@ -299,7 +304,11 @@ void pxa27x_cpu_pm_enter(suspend_state_t state) pxa_cpu_standby(); break; case PM_SUSPEND_MEM: - pxa27x_cpu_suspend(pwrmode, PLAT_PHYS_OFFSET - PAGE_OFFSET); + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, pwrmode, + pxa27x_finish_suspend); +#ifndef CONFIG_IWMMXT + asm volatile("mar acc0, %Q0, %R0" : "=r" (acc0)); +#endif break; } } diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c index 8521d7d6f1da..220fd8c15dab 100644 --- a/arch/arm/mach-pxa/pxa3xx.c +++ b/arch/arm/mach-pxa/pxa3xx.c @@ -141,8 +141,13 @@ static void pxa3xx_cpu_pm_suspend(void) { volatile unsigned long *p = (volatile void *)0xc0000000; unsigned long saved_data = *p; +#ifndef CONFIG_IWMMXT + u64 acc0; - extern void pxa3xx_cpu_suspend(long); + asm volatile("mra %Q0, %R0, acc0" : "=r" (acc0)); +#endif + + extern void pxa3xx_finish_suspend(unsigned long); /* resuming from D2 requires the HSIO2/BOOT/TPM clocks enabled */ CKENA |= (1 << CKEN_BOOT) | (1 << CKEN_TPM); @@ -162,11 +167,15 @@ static void pxa3xx_cpu_pm_suspend(void) /* overwrite with the resume address */ *p = virt_to_phys(cpu_resume); - pxa3xx_cpu_suspend(PLAT_PHYS_OFFSET - PAGE_OFFSET); + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, 0, pxa3xx_finish_suspend); *p = saved_data; AD3ER = 0; + +#ifndef CONFIG_IWMMXT + asm volatile("mar acc0, %Q0, %R0" : "=r" (acc0)); +#endif } static void pxa3xx_cpu_pm_enter(suspend_state_t state) diff --git a/arch/arm/mach-pxa/sleep.S b/arch/arm/mach-pxa/sleep.S index 3a67887e6dbd..1e544be9905d 100644 --- a/arch/arm/mach-pxa/sleep.S +++ b/arch/arm/mach-pxa/sleep.S @@ -24,22 +24,9 @@ #ifdef CONFIG_PXA3xx /* - * pxa3xx_cpu_suspend() - forces CPU into sleep state (S2D3C4) - * - * r0 = v:p offset + * pxa3xx_finish_suspend() - forces CPU into sleep state (S2D3C4) */ -ENTRY(pxa3xx_cpu_suspend) - -#ifndef CONFIG_IWMMXT - mra r2, r3, acc0 -#endif - stmfd sp!, {r2 - r12, lr} @ save registers on stack - mov r1, r0 - adr r3, BSYM(pxa3xx_finish_suspend) - bl cpu_suspend - b pxa_cpu_resume - -pxa3xx_finish_suspend: +ENTRY(pxa3xx_finish_suspend) mov r0, #0x06 @ S2D3C4 mode mcr p14, 0, r0, c7, c0, 0 @ enter sleep @@ -48,25 +35,13 @@ pxa3xx_finish_suspend: #ifdef CONFIG_PXA27x /* - * pxa27x_cpu_suspend() + * pxa27x_finish_suspend() * * Forces CPU into sleep state. * * r0 = value for PWRMODE M field for desired sleep state - * r1 = v:p offset */ -ENTRY(pxa27x_cpu_suspend) - -#ifndef CONFIG_IWMMXT - mra r2, r3, acc0 -#endif - stmfd sp!, {r2 - r12, lr} @ save registers on stack - mov r2, r0 @ save sleep mode - adr r3, BSYM(pxa27x_finish_suspend) - bl cpu_suspend - b pxa_cpu_resume - -pxa27x_finish_suspend: +ENTRY(pxa27x_finish_suspend) @ Put the processor to sleep @ (also workaround for sighting 28071) @@ -103,22 +78,14 @@ pxa27x_finish_suspend: #ifdef CONFIG_PXA25x /* - * pxa25x_cpu_suspend() + * pxa25x_finish_suspend() * * Forces CPU into sleep state. * * r0 = value for PWRMODE M field for desired sleep state - * r1 = v:p offset */ -ENTRY(pxa25x_cpu_suspend) - stmfd sp!, {r2 - r12, lr} @ save registers on stack - mov r2, r0 @ save sleep mode - adr r3, BSYM(pxa25x_finish_suspend) - bl cpu_suspend - b pxa_cpu_resume - -pxa25x_finish_suspend: +ENTRY(pxa25x_finish_suspend) @ prepare value for sleep mode mov r1, r0 @ sleep mode @@ -202,16 +169,3 @@ pxa_cpu_do_suspend: mcr p14, 0, r1, c7, c0, 0 @ PWRMODE 20: b 20b @ loop waiting for sleep - -/* - * pxa_cpu_resume() - * - * entry point from bootloader into kernel during resume - */ - .align 5 -pxa_cpu_resume: - ldmfd sp!, {r2, r3} -#ifndef CONFIG_IWMMXT - mar acc0, r2, r3 -#endif - ldmfd sp!, {r4 - r12, pc} @ return to caller diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index 00363c7ac182..28eb410ca779 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -676,7 +676,8 @@ static struct pxa2xx_udc_mach_info zeus_udc_info = { static void zeus_power_off(void) { local_irq_disable(); - pxa27x_cpu_suspend(PWRMODE_DEEPSLEEP, PLAT_PHYS_OFFSET - PAGE_OFFSET); + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, PWRMODE_DEEPSLEEP, + pxa27x_finish_suspend); } #else #define zeus_power_off NULL -- cgit v1.2.3 From 857c1b81f8dd2e2a97d859d7e53dd955e2ab55af Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Jun 2011 12:44:32 +0100 Subject: ARM: pm: omap34xx: no need to save all registers in sleep34xx.S The ABI allows called functions to corrupt r0-r3 and ip (r12). So its pointless saving these registers in the suspend code - the calling function will expect them to be corrupted and so won't rely on their contents after resume. Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/mach-omap2/sleep34xx.S | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 63f10669571a..9551c7dc71ef 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -133,7 +133,7 @@ ENDPROC(enable_omap3630_toggle_l2_on_restore) /* Function to call rom code to save secure ram context */ .align 3 ENTRY(save_secure_ram_context) - stmfd sp!, {r1-r12, lr} @ save registers on stack + stmfd sp!, {r4 - r11, lr} @ save registers on stack adr r3, api_params @ r3 points to parameters str r0, [r3,#0x4] @ r0 has sdram address ldr r12, high_mask @@ -152,7 +152,7 @@ ENTRY(save_secure_ram_context) nop nop nop - ldmfd sp!, {r1-r12, pc} + ldmfd sp!, {r4 - r11, pc} .align sram_phy_addr_mask: .word SRAM_BASE_P @@ -187,7 +187,7 @@ ENTRY(save_secure_ram_context_sz) */ .align 3 ENTRY(omap34xx_cpu_suspend) - stmfd sp!, {r0-r12, lr} @ save registers on stack + stmfd sp!, {r4 - r11, lr} @ save registers on stack /* * r0 contains CPU context save/restore pointer in sdram @@ -329,7 +329,7 @@ omap3_do_wfi: * == Exit point from non-OFF modes == * =================================== */ - ldmfd sp!, {r0-r12, pc} @ restore regs and return + ldmfd sp!, {r4 - r11, pc} @ restore regs and return /* @@ -572,7 +572,7 @@ usettbr0: * ============================== */ restoremmu_on: - ldmfd sp!, {r0-r12, pc} @ restore regs and return + ldmfd sp!, {r4 - r11, pc} @ restore regs and return /* -- cgit v1.2.3 From 2637ce30e145557bf89ebcf35b2d78e729e16e5a Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Jun 2011 12:54:41 +0100 Subject: ARM: pm: omap34xx: remove misleading comment and use of r9 The code alludes to r9 being used to indicate what was lost over the suspend/resume transition. However, although r9 is set, it is never actually used. Also, the comments before the code (which refer to the value of r9) and the comments against the assignment of r9 contradict each other, so just remove them to avoid confusion. Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/mach-omap2/sleep34xx.S | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 9551c7dc71ef..12e9da2f0263 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -381,18 +381,13 @@ restore_3630: restore: /* - * Check what was the reason for mpu reset and store the reason in r9: - * 0 - No context lost - * 1 - Only L1 and logic lost - * 2 - Only L2 lost - In this case, we wont be here - * 3 - Both L1 and L2 lost + * Read the pwstctrl register to check the reason for mpu reset. + * This tells us what was lost. */ ldr r1, pm_pwstctrl_mpu ldr r2, [r1] and r2, r2, #0x3 cmp r2, #0x0 @ Check if target power state was OFF or RET - moveq r9, #0x3 @ MPU OFF => L1 and L2 lost - movne r9, #0x1 @ Only L1 and L2 lost => avoid L2 invalidation bne logic_l1_restore ldr r0, l2dis_3630 -- cgit v1.2.3 From 076f2cc449188b7d3d4866730afa3ac7be3e6640 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Jun 2011 15:42:54 +0100 Subject: ARM: pm: omap34xx: convert to generic suspend/resume support Convert omap34xx to use the generic CPU suspend/resume support, rather than implementing its own version. Tested on 3430 LDP. Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/mach-omap2/pm34xx.c | 47 +++---------- arch/arm/mach-omap2/sleep34xx.S | 143 +--------------------------------------- 2 files changed, 13 insertions(+), 177 deletions(-) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index c155c9d1c82c..ae4017750bbe 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -40,8 +40,6 @@ #include #include -#include - #include "cm2xxx_3xxx.h" #include "cm-regbits-34xx.h" #include "prm-regbits-34xx.h" @@ -64,11 +62,6 @@ static inline bool is_suspending(void) } #endif -/* Scratchpad offsets */ -#define OMAP343X_TABLE_ADDRESS_OFFSET 0xc4 -#define OMAP343X_TABLE_VALUE_OFFSET 0xc0 -#define OMAP343X_CONTROL_REG_VALUE_OFFSET 0xc8 - /* pm34xx errata defined in pm.h */ u16 pm34xx_errata; @@ -312,28 +305,9 @@ static irqreturn_t prcm_interrupt_handler (int irq, void *dev_id) return IRQ_HANDLED; } -/* Function to restore the table entry that was modified for enabling MMU */ -static void restore_table_entry(void) +static void omap34xx_do_sram_idle(unsigned long save_state) { - void __iomem *scratchpad_address; - u32 previous_value, control_reg_value; - u32 *address; - - scratchpad_address = OMAP2_L4_IO_ADDRESS(OMAP343X_SCRATCHPAD); - - /* Get address of entry that was modified */ - address = (u32 *)__raw_readl(scratchpad_address + - OMAP343X_TABLE_ADDRESS_OFFSET); - /* Get the previous value which needs to be restored */ - previous_value = __raw_readl(scratchpad_address + - OMAP343X_TABLE_VALUE_OFFSET); - address = __va(address); - *address = previous_value; - flush_tlb_all(); - control_reg_value = __raw_readl(scratchpad_address - + OMAP343X_CONTROL_REG_VALUE_OFFSET); - /* This will enable caches and prediction */ - set_cr(control_reg_value); + _omap_sram_idle(omap3_arm_context, save_state); } void omap_sram_idle(void) @@ -432,12 +406,15 @@ void omap_sram_idle(void) sdrc_pwr = sdrc_read_reg(SDRC_POWER); /* - * omap3_arm_context is the location where ARM registers - * get saved. The restore path then reads from this - * location and restores them back. + * omap3_arm_context is the location where some ARM context + * get saved. The rest is placed on the stack, and restored + * from there before resuming. */ - _omap_sram_idle(omap3_arm_context, save_state); - cpu_init(); + if (save_state == 1 || save_state == 3) + cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, save_state, + omap34xx_do_sram_idle); + else + omap34xx_do_sram_idle(save_state); /* Restore normal SDRC POWER settings */ if (omap_rev() >= OMAP3430_REV_ES3_0 && @@ -445,10 +422,6 @@ void omap_sram_idle(void) core_next_state == PWRDM_POWER_OFF) sdrc_write_reg(sdrc_pwr, SDRC_POWER); - /* Restore table entry modified during MMU restoration */ - if (pwrdm_read_prev_pwrst(mpu_pwrdm) == PWRDM_POWER_OFF) - restore_table_entry(); - /* CORE */ if (core_next_state < PWRDM_POWER_ON) { core_prev_state = pwrdm_read_prev_pwrst(core_pwrdm); diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 12e9da2f0263..9a1349ea460a 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -211,37 +211,6 @@ save_context_wfi: mrc p15, 1, r5, c9, c0, 2 @ Read L2 AUX ctrl register stmia r8!, {r4-r5} @ Push parameters for restore call - /* Check what that target sleep state is from r1 */ - cmp r1, #0x2 @ Only L2 lost, no need to save context - beq clean_caches - -l1_logic_lost: - mov r4, sp @ Store sp - mrs r5, spsr @ Store spsr - mov r6, lr @ Store lr - stmia r8!, {r4-r6} - - mrc p15, 0, r4, c1, c0, 2 @ Coprocessor access control register - mrc p15, 0, r5, c2, c0, 0 @ TTBR0 - mrc p15, 0, r6, c2, c0, 1 @ TTBR1 - mrc p15, 0, r7, c2, c0, 2 @ TTBCR - stmia r8!, {r4-r7} - - mrc p15, 0, r4, c3, c0, 0 @ Domain access Control Register - mrc p15, 0, r5, c10, c2, 0 @ PRRR - mrc p15, 0, r6, c10, c2, 1 @ NMRR - stmia r8!,{r4-r6} - - mrc p15, 0, r4, c13, c0, 1 @ Context ID - mrc p15, 0, r5, c13, c0, 2 @ User r/w thread and process ID - mrc p15, 0, r6, c12, c0, 0 @ Secure or NS vector base address - mrs r7, cpsr @ Store current cpsr - stmia r8!, {r4-r7} - - mrc p15, 0, r4, c1, c0, 0 @ save control register - stmia r8!, {r4} - -clean_caches: /* * jump out to kernel flush routine * - reuse that code is better @@ -466,109 +435,11 @@ logic_l1_restore: orr r1, r1, #2 @ re-enable L2 cache mcr p15, 0, r1, c1, c0, 1 skipl2reen: - mov r1, #0 - /* - * Invalidate all instruction caches to PoU - * and flush branch target cache - */ - mcr p15, 0, r1, c7, c5, 0 - ldr r4, scratchpad_base - ldr r3, [r4,#0xBC] - adds r3, r3, #16 - - ldmia r3!, {r4-r6} - mov sp, r4 @ Restore sp - msr spsr_cxsf, r5 @ Restore spsr - mov lr, r6 @ Restore lr - - ldmia r3!, {r4-r7} - mcr p15, 0, r4, c1, c0, 2 @ Coprocessor access Control Register - mcr p15, 0, r5, c2, c0, 0 @ TTBR0 - mcr p15, 0, r6, c2, c0, 1 @ TTBR1 - mcr p15, 0, r7, c2, c0, 2 @ TTBCR - - ldmia r3!,{r4-r6} - mcr p15, 0, r4, c3, c0, 0 @ Domain access Control Register - mcr p15, 0, r5, c10, c2, 0 @ PRRR - mcr p15, 0, r6, c10, c2, 1 @ NMRR - - - ldmia r3!,{r4-r7} - mcr p15, 0, r4, c13, c0, 1 @ Context ID - mcr p15, 0, r5, c13, c0, 2 @ User r/w thread and process ID - mrc p15, 0, r6, c12, c0, 0 @ Secure or NS vector base address - msr cpsr, r7 @ store cpsr - - /* Enabling MMU here */ - mrc p15, 0, r7, c2, c0, 2 @ Read TTBRControl - /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */ - and r7, #0x7 - cmp r7, #0x0 - beq usettbr0 -ttbr_error: - /* - * More work needs to be done to support N[0:2] value other than 0 - * So looping here so that the error can be detected - */ - b ttbr_error -usettbr0: - mrc p15, 0, r2, c2, c0, 0 - ldr r5, ttbrbit_mask - and r2, r5 - mov r4, pc - ldr r5, table_index_mask - and r4, r5 @ r4 = 31 to 20 bits of pc - /* Extract the value to be written to table entry */ - ldr r1, table_entry - /* r1 has the value to be written to table entry*/ - add r1, r1, r4 - /* Getting the address of table entry to modify */ - lsr r4, #18 - /* r2 has the location which needs to be modified */ - add r2, r4 - /* Storing previous entry of location being modified */ - ldr r5, scratchpad_base - ldr r4, [r2] - str r4, [r5, #0xC0] - /* Modify the table entry */ - str r1, [r2] - /* - * Storing address of entry being modified - * - will be restored after enabling MMU - */ - ldr r5, scratchpad_base - str r2, [r5, #0xC4] - - mov r0, #0 - mcr p15, 0, r0, c7, c5, 4 @ Flush prefetch buffer - mcr p15, 0, r0, c7, c5, 6 @ Invalidate branch predictor array - mcr p15, 0, r0, c8, c5, 0 @ Invalidate instruction TLB - mcr p15, 0, r0, c8, c6, 0 @ Invalidate data TLB - /* - * Restore control register. This enables the MMU. - * The caches and prediction are not enabled here, they - * will be enabled after restoring the MMU table entry. - */ - ldmia r3!, {r4} - /* Store previous value of control register in scratchpad */ - str r4, [r5, #0xC8] - ldr r2, cache_pred_disable_mask - and r4, r2 - mcr p15, 0, r4, c1, c0, 0 - dsb - isb - ldr r0, =restoremmu_on - bx r0 - -/* - * ============================== - * == Exit point from OFF mode == - * ============================== - */ -restoremmu_on: - ldmfd sp!, {r4 - r11, pc} @ restore regs and return + /* Now branch to the common CPU resume function */ + b cpu_resume + .ltorg /* * Internal functions @@ -719,14 +590,6 @@ sram_base: .word SRAM_BASE_P + 0x8000 sdrc_power: .word SDRC_POWER_V -ttbrbit_mask: - .word 0xFFFFC000 -table_index_mask: - .word 0xFFF00000 -table_entry: - .word 0x00000C02 -cache_pred_disable_mask: - .word 0xFFFFE7FB control_stat: .word CONTROL_STAT control_mem_rta: -- cgit v1.2.3 From 14c79bbed7e06135bcbccb2b92c19df7115b4502 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Thu, 23 Jun 2011 17:16:14 -0700 Subject: ARM: pm: omap34xx: remove get_*_restore_pointer functions, directly use entry points Upon return from off-mode, the ROM code jumps to a restore function saved in the scratchpad. Based on SoC revision or errata, this restore entry point is different. Current code uses some helper functions in sleep34xx.S (get_*_restore_pointer) to get the restore function entry point. When returning from off-mode, this code is executed from SDRAM, so there's no reason to use these helper functions when using the SDRAM entry points directly would work just fine. This patch uses ENTRY/ENDPROC to create "real" entry points for these functions, and uses those values directly when writing the scratchpad. Tested all three entry points - restore_es3: 3430/n900 - restore_3630: 3630/Zoom3 - restore: 3530/Overo Suggested-by: Russell King Acked-by: Jean Pihet Acked-by: Santosh Shilimkar Signed-off-by: Kevin Hilman Signed-off-by: Russell King --- arch/arm/mach-omap2/control.c | 7 +++--- arch/arm/mach-omap2/control.h | 6 ++--- arch/arm/mach-omap2/sleep34xx.S | 55 +++++++---------------------------------- 3 files changed, 16 insertions(+), 52 deletions(-) diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c index da53ba3917ca..aab884fecc55 100644 --- a/arch/arm/mach-omap2/control.c +++ b/arch/arm/mach-omap2/control.c @@ -286,14 +286,15 @@ void omap3_save_scratchpad_contents(void) scratchpad_contents.boot_config_ptr = 0x0; if (cpu_is_omap3630()) scratchpad_contents.public_restore_ptr = - virt_to_phys(get_omap3630_restore_pointer()); + virt_to_phys(omap3_restore_3630); else if (omap_rev() != OMAP3430_REV_ES3_0 && omap_rev() != OMAP3430_REV_ES3_1) scratchpad_contents.public_restore_ptr = - virt_to_phys(get_restore_pointer()); + virt_to_phys(omap3_restore); else scratchpad_contents.public_restore_ptr = - virt_to_phys(get_es3_restore_pointer()); + virt_to_phys(omap3_restore_es3); + if (omap_type() == OMAP2_DEVICE_TYPE_GP) scratchpad_contents.secure_ram_restore_ptr = 0x0; else diff --git a/arch/arm/mach-omap2/control.h b/arch/arm/mach-omap2/control.h index a016c8b59e00..d4ef75d5a382 100644 --- a/arch/arm/mach-omap2/control.h +++ b/arch/arm/mach-omap2/control.h @@ -386,9 +386,9 @@ extern void omap4_ctrl_pad_writel(u32 val, u16 offset); extern void omap3_save_scratchpad_contents(void); extern void omap3_clear_scratchpad_contents(void); -extern u32 *get_restore_pointer(void); -extern u32 *get_es3_restore_pointer(void); -extern u32 *get_omap3630_restore_pointer(void); +extern void omap3_restore(void); +extern void omap3_restore_es3(void); +extern void omap3_restore_3630(void); extern u32 omap3_arm_context[128]; extern void omap3_control_save_context(void); extern void omap3_control_restore_context(void); diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 9a1349ea460a..d18f52e46c7c 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -74,46 +74,6 @@ * API functions */ -/* - * The "get_*restore_pointer" functions are used to provide a - * physical restore address where the ROM code jumps while waking - * up from MPU OFF/OSWR state. - * The restore pointer is stored into the scratchpad. - */ - - .text -/* Function call to get the restore pointer for resume from OFF */ -ENTRY(get_restore_pointer) - stmfd sp!, {lr} @ save registers on stack - adr r0, restore - ldmfd sp!, {pc} @ restore regs and return -ENDPROC(get_restore_pointer) - .align -ENTRY(get_restore_pointer_sz) - .word . - get_restore_pointer - - .text -/* Function call to get the restore pointer for 3630 resume from OFF */ -ENTRY(get_omap3630_restore_pointer) - stmfd sp!, {lr} @ save registers on stack - adr r0, restore_3630 - ldmfd sp!, {pc} @ restore regs and return -ENDPROC(get_omap3630_restore_pointer) - .align -ENTRY(get_omap3630_restore_pointer_sz) - .word . - get_omap3630_restore_pointer - - .text -/* Function call to get the restore pointer for ES3 to resume from OFF */ -ENTRY(get_es3_restore_pointer) - stmfd sp!, {lr} @ save registers on stack - adr r0, restore_es3 - ldmfd sp!, {pc} @ restore regs and return -ENDPROC(get_es3_restore_pointer) - .align -ENTRY(get_es3_restore_pointer_sz) - .word . - get_es3_restore_pointer - .text /* * L2 cache needs to be toggled for stable OFF mode functionality on 3630. @@ -316,12 +276,12 @@ omap3_do_wfi: * restore_3630: applies to 36xx * restore: common code for 3xxx */ -restore_es3: +ENTRY(omap3_restore_es3) ldr r5, pm_prepwstst_core_p ldr r4, [r5] and r4, r4, #0x3 cmp r4, #0x0 @ Check if previous power state of CORE is OFF - bne restore + bne omap3_restore adr r0, es3_sdrc_fix ldr r1, sram_base ldr r2, es3_sdrc_fix_sz @@ -333,22 +293,24 @@ copy_to_sram: bne copy_to_sram ldr r1, sram_base blx r1 - b restore + b omap3_restore +ENDPROC(omap3_restore_es3) -restore_3630: +ENTRY(omap3_restore_3630) ldr r1, pm_prepwstst_core_p ldr r2, [r1] and r2, r2, #0x3 cmp r2, #0x0 @ Check if previous power state of CORE is OFF - bne restore + bne omap3_restore /* Disable RTA before giving control */ ldr r1, control_mem_rta mov r2, #OMAP36XX_RTA_DISABLE str r2, [r1] +ENDPROC(omap3_restore_3630) /* Fall through to common code for the remaining logic */ -restore: +ENTRY(omap3_restore) /* * Read the pwstctrl register to check the reason for mpu reset. * This tells us what was lost. @@ -438,6 +400,7 @@ skipl2reen: /* Now branch to the common CPU resume function */ b cpu_resume +ENDPROC(omap3_restore) .ltorg -- cgit v1.2.3 From 2c74a0cefa463a7a483b07ba4d2ea8e4ec7b996c Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Jun 2011 17:41:48 +0100 Subject: ARM: pm: hide 1st and 2nd arguments to cpu_suspend from platform code The first and second arguments shouldn't concern platform code, so hide them from each platforms caller. Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/include/asm/suspend.h | 19 +++++++++++++++++++ arch/arm/include/asm/system.h | 2 -- arch/arm/kernel/sleep.S | 4 ++-- arch/arm/mach-omap2/pm34xx.c | 5 +++-- arch/arm/mach-pxa/palmz72.c | 1 + arch/arm/mach-pxa/pxa25x.c | 4 ++-- arch/arm/mach-pxa/pxa27x.c | 4 ++-- arch/arm/mach-pxa/pxa3xx.c | 3 ++- arch/arm/mach-pxa/zeus.c | 4 ++-- arch/arm/mach-sa1100/pm.c | 3 ++- arch/arm/plat-samsung/pm.c | 3 ++- 11 files changed, 37 insertions(+), 15 deletions(-) create mode 100644 arch/arm/include/asm/suspend.h diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h new file mode 100644 index 000000000000..8d5b4461c205 --- /dev/null +++ b/arch/arm/include/asm/suspend.h @@ -0,0 +1,19 @@ +#ifndef __ASM_ARM_SUSPEND_H +#define __ASM_ARM_SUSPEND_H + +#include + +extern void cpu_resume(void); + +/* + * Hide the first two arguments to __cpu_suspend - these are an implementation + * detail which platform code shouldn't have to know about. + */ +static inline void cpu_suspend(unsigned long arg, void (*fn)(unsigned long)) +{ + extern void __cpu_suspend(int, long, unsigned long, + void (*)(unsigned long)); + __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn); +} + +#endif diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 50be6055df89..832888d0c20c 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -106,8 +106,6 @@ extern void __show_regs(struct pt_regs *); extern int cpu_architecture(void); extern void cpu_init(void); -extern void cpu_suspend(int, long, unsigned long, void (*)(unsigned long)); -extern void cpu_resume(void); void arm_machine_restart(char mode, const char *cmd); extern void (*arm_pm_restart)(char str, const char *cmd); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 53922748d101..c156d0e5f455 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -14,7 +14,7 @@ * r3 = suspend function * Note: does not return until system resumes */ -ENTRY(cpu_suspend) +ENTRY(__cpu_suspend) stmfd sp!, {r4 - r11, lr} #ifdef MULTI_CPU ldr r10, =processor @@ -56,7 +56,7 @@ ENTRY(cpu_suspend) bl __cpuc_flush_kern_all #endif ldmfd sp!, {r0, pc} @ call suspend fn -ENDPROC(cpu_suspend) +ENDPROC(__cpu_suspend) .ltorg /* diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index ae4017750bbe..3e9a13e1ac57 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -31,6 +31,8 @@ #include #include +#include + #include #include "clockdomain.h" #include "powerdomain.h" @@ -411,8 +413,7 @@ void omap_sram_idle(void) * from there before resuming. */ if (save_state == 1 || save_state == 3) - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, save_state, - omap34xx_do_sram_idle); + cpu_suspend(save_state, omap34xx_do_sram_idle); else omap34xx_do_sram_idle(save_state); diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c index 65f24f0b77e8..5a5329bc33f1 100644 --- a/arch/arm/mach-pxa/palmz72.c +++ b/arch/arm/mach-pxa/palmz72.c @@ -33,6 +33,7 @@ #include #include +#include #include #include diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c index fd7725cb5c01..9c434d21a271 100644 --- a/arch/arm/mach-pxa/pxa25x.c +++ b/arch/arm/mach-pxa/pxa25x.c @@ -25,6 +25,7 @@ #include #include +#include #include #include #include @@ -244,8 +245,7 @@ static void pxa25x_cpu_pm_enter(suspend_state_t state) switch (state) { case PM_SUSPEND_MEM: - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, PWRMODE_SLEEP, - pxa25x_finish_suspend); + cpu_suspend(PWRMODE_SLEEP, pxa25x_finish_suspend); break; } } diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c index 824379d43758..9d2400b5f503 100644 --- a/arch/arm/mach-pxa/pxa27x.c +++ b/arch/arm/mach-pxa/pxa27x.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -304,8 +305,7 @@ void pxa27x_cpu_pm_enter(suspend_state_t state) pxa_cpu_standby(); break; case PM_SUSPEND_MEM: - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, pwrmode, - pxa27x_finish_suspend); + cpu_suspend(pwrmode, pxa27x_finish_suspend); #ifndef CONFIG_IWMMXT asm volatile("mar acc0, %Q0, %R0" : "=r" (acc0)); #endif diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c index 220fd8c15dab..9fe947b5d5f7 100644 --- a/arch/arm/mach-pxa/pxa3xx.c +++ b/arch/arm/mach-pxa/pxa3xx.c @@ -24,6 +24,7 @@ #include #include +#include #include #include #include @@ -167,7 +168,7 @@ static void pxa3xx_cpu_pm_suspend(void) /* overwrite with the resume address */ *p = virt_to_phys(cpu_resume); - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, 0, pxa3xx_finish_suspend); + cpu_suspend(0, pxa3xx_finish_suspend); *p = saved_data; diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index 28eb410ca779..9b99cc164de5 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -31,6 +31,7 @@ #include #include +#include #include #include @@ -676,8 +677,7 @@ static struct pxa2xx_udc_mach_info zeus_udc_info = { static void zeus_power_off(void) { local_irq_disable(); - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, PWRMODE_DEEPSLEEP, - pxa27x_finish_suspend); + cpu_suspend(PWRMODE_DEEPSLEEP, pxa27x_finish_suspend); } #else #define zeus_power_off NULL diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index 259ed3bcc3fe..cf9a1e9fb70d 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -29,6 +29,7 @@ #include #include +#include #include #include @@ -75,7 +76,7 @@ static int sa11x0_pm_enter(suspend_state_t state) PSPR = virt_to_phys(cpu_resume); /* go zzz */ - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, 0, sa1100_finish_suspend); + cpu_suspend(0, sa1100_finish_suspend); /* * Ensure not to come back here if it wasn't intended diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c index 3a6d0768ba0c..69d6b040a019 100644 --- a/arch/arm/plat-samsung/pm.c +++ b/arch/arm/plat-samsung/pm.c @@ -20,6 +20,7 @@ #include #include +#include #include #include @@ -298,7 +299,7 @@ static int s3c_pm_enter(suspend_state_t state) * we resume as it saves its own register state and restores it * during the resume. */ - cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, 0, pm_cpu_sleep); + cpu_suspend(0, pm_cpu_sleep); /* restore the system state */ -- cgit v1.2.3 From 0853f96f13e0b60f1c319bcd7f6a3a84d0d1e706 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 23 Jun 2011 14:24:09 +0100 Subject: ARM: pm: ensure our temporary page table entry is removed from the TLB Ensure that our temporary page table entry is flushed from the TLB before we resume normal operations. This ensures that userspace won't trip over the stale TLB entry. Tested-by: Kevin Hilman Acked-by: Jean Pihet Signed-off-by: Russell King --- arch/arm/include/asm/suspend.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h index 8d5b4461c205..f8db9d096bc7 100644 --- a/arch/arm/include/asm/suspend.h +++ b/arch/arm/include/asm/suspend.h @@ -2,6 +2,7 @@ #define __ASM_ARM_SUSPEND_H #include +#include extern void cpu_resume(void); @@ -14,6 +15,7 @@ static inline void cpu_suspend(unsigned long arg, void (*fn)(unsigned long)) extern void __cpu_suspend(int, long, unsigned long, void (*)(unsigned long)); __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn); + flush_tlb_all(); } #endif -- cgit v1.2.3 From b6fcd313c9db4f4c4feaf9d5d48b293d5fa27061 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 10:32:05 +0100 Subject: ARM: entry: remove unused irq_prio_table macro Platforms provide an empty irq_prio_table macro, and as nothing uses this macro, it can simply be removed. Signed-off-by: Russell King --- arch/arm/mach-bcmring/include/mach/entry-macro.S | 4 ---- arch/arm/mach-davinci/include/mach/entry-macro.S | 3 --- arch/arm/mach-h720x/include/mach/entry-macro.S | 3 --- arch/arm/mach-lpc32xx/include/mach/entry-macro.S | 4 ---- arch/arm/mach-omap2/include/mach/entry-macro.S | 3 --- arch/arm/mach-pnx4008/include/mach/entry-macro.S | 5 ----- arch/arm/plat-mxc/include/mach/entry-macro.S | 4 ---- 7 files changed, 26 deletions(-) diff --git a/arch/arm/mach-bcmring/include/mach/entry-macro.S b/arch/arm/mach-bcmring/include/mach/entry-macro.S index 7d393ca010ac..94c950d783ba 100644 --- a/arch/arm/mach-bcmring/include/mach/entry-macro.S +++ b/arch/arm/mach-bcmring/include/mach/entry-macro.S @@ -80,7 +80,3 @@ .macro arch_ret_to_user, tmp1, tmp2 .endm - - .macro irq_prio_table - .endm - diff --git a/arch/arm/mach-davinci/include/mach/entry-macro.S b/arch/arm/mach-davinci/include/mach/entry-macro.S index fbdebc7cb409..e14c0dc0e12c 100644 --- a/arch/arm/mach-davinci/include/mach/entry-macro.S +++ b/arch/arm/mach-davinci/include/mach/entry-macro.S @@ -46,6 +46,3 @@ #endif 1002: .endm - - .macro irq_prio_table - .endm diff --git a/arch/arm/mach-h720x/include/mach/entry-macro.S b/arch/arm/mach-h720x/include/mach/entry-macro.S index 6d3b917c4a18..c3948e5ba4a0 100644 --- a/arch/arm/mach-h720x/include/mach/entry-macro.S +++ b/arch/arm/mach-h720x/include/mach/entry-macro.S @@ -57,9 +57,6 @@ tst \irqstat, #1 @ bit 0 should be set .endm - .macro irq_prio_table - .endm - #else #error hynix processor selection missmatch #endif diff --git a/arch/arm/mach-lpc32xx/include/mach/entry-macro.S b/arch/arm/mach-lpc32xx/include/mach/entry-macro.S index 870227c96602..b725f6c93975 100644 --- a/arch/arm/mach-lpc32xx/include/mach/entry-macro.S +++ b/arch/arm/mach-lpc32xx/include/mach/entry-macro.S @@ -41,7 +41,3 @@ rsb \irqnr, \irqnr, #31 teq \irqstat, #0 .endm - - .macro irq_prio_table - .endm - diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S index a48690b90990..ceb8b7e593d7 100644 --- a/arch/arm/mach-omap2/include/mach/entry-macro.S +++ b/arch/arm/mach-omap2/include/mach/entry-macro.S @@ -165,6 +165,3 @@ #endif #endif /* MULTI_OMAP2 */ - - .macro irq_prio_table - .endm diff --git a/arch/arm/mach-pnx4008/include/mach/entry-macro.S b/arch/arm/mach-pnx4008/include/mach/entry-macro.S index 8003037578ed..db7eeebf30d7 100644 --- a/arch/arm/mach-pnx4008/include/mach/entry-macro.S +++ b/arch/arm/mach-pnx4008/include/mach/entry-macro.S @@ -120,8 +120,3 @@ 1003: .endm - - .macro irq_prio_table - .endm - - diff --git a/arch/arm/plat-mxc/include/mach/entry-macro.S b/arch/arm/plat-mxc/include/mach/entry-macro.S index 2e49e71b1b98..066d464d322d 100644 --- a/arch/arm/plat-mxc/include/mach/entry-macro.S +++ b/arch/arm/plat-mxc/include/mach/entry-macro.S @@ -78,7 +78,3 @@ movs \irqnr, \irqnr #endif .endm - - @ irq priority table (not used) - .macro irq_prio_table - .endm -- cgit v1.2.3 From 2342aa282b59f028cf0850b483b34587db2c22b0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 10:04:15 +0100 Subject: ARM: entry: shark: don't directly reference registers in macros Directly referencing registers in macros makes assembly code harder to change, because the macros have side effects which are non-obvious. Use the provided 'base' register rather than directly referencing r4. Signed-off-by: Russell King --- arch/arm/mach-shark/include/mach/entry-macro.S | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/mach-shark/include/mach/entry-macro.S b/arch/arm/mach-shark/include/mach/entry-macro.S index e2853c0a3333..0bb6cc626eb7 100644 --- a/arch/arm/mach-shark/include/mach/entry-macro.S +++ b/arch/arm/mach-shark/include/mach/entry-macro.S @@ -11,17 +11,17 @@ .endm .macro get_irqnr_preamble, base, tmp + mov \base, #0xe0000000 .endm .macro arch_ret_to_user, tmp1, tmp2 .endm .macro get_irqnr_and_base, irqnr, irqstat, base, tmp - mov r4, #0xe0000000 mov \irqstat, #0x0C - strb \irqstat, [r4, #0x20] @outb(0x0C, 0x20) /* Poll command */ - ldrb \irqnr, [r4, #0x20] @irq = inb(0x20) & 7 + strb \irqstat, [\base, #0x20] @outb(0x0C, 0x20) /* Poll command */ + ldrb \irqnr, [\base, #0x20] @irq = inb(0x20) & 7 and \irqstat, \irqnr, #0x80 teq \irqstat, #0 beq 43f @@ -29,8 +29,8 @@ teq \irqnr, #2 bne 44f 43: mov \irqstat, #0x0C - strb \irqstat, [r4, #0xa0] @outb(0x0C, 0xA0) /* Poll command */ - ldrb \irqnr, [r4, #0xa0] @irq = (inb(0xA0) & 7) + 8 + strb \irqstat, [\base, #0xa0] @outb(0x0C, 0xA0) /* Poll command */ + ldrb \irqnr, [\base, #0xa0] @irq = (inb(0xA0) & 7) + 8 and \irqstat, \irqnr, #0x80 teq \irqstat, #0 beq 44f -- cgit v1.2.3 From 40fb79c8a88625504857d44de1bc89dc0341e618 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Sun, 19 Jun 2011 23:36:03 -0400 Subject: ARM: add a kuser_cmpxchg64 user space helper Some user space applications are designed around the ability to perform atomic operations on 64 bit values. Since this is natively possible only with ARMv6k and above, let's provide a new kuser helper to perform the operation with kernel supervision on pre ARMv6k hardware. Signed-off-by: Nicolas Pitre Tested-by: Dave Martin --- Documentation/arm/kernel_user_helpers.txt | 64 ++++++++++++++++++++ arch/arm/kernel/entry-armv.S | 99 ++++++++++++++++++++++++++++++- 2 files changed, 160 insertions(+), 3 deletions(-) diff --git a/Documentation/arm/kernel_user_helpers.txt b/Documentation/arm/kernel_user_helpers.txt index 0c33f72d1873..a17df9f91d16 100644 --- a/Documentation/arm/kernel_user_helpers.txt +++ b/Documentation/arm/kernel_user_helpers.txt @@ -201,3 +201,67 @@ typedef void (__kuser_dmb_t)(void); Notes: - Valid only if __kuser_helper_version >= 3 (from kernel version 2.6.15). + +kuser_cmpxchg64 +--------------- + +Location: 0xffff0f60 + +Reference prototype: + + int __kuser_cmpxchg64(const int64_t *oldval, + const int64_t *newval, + volatile int64_t *ptr); + +Input: + + r0 = pointer to oldval + r1 = pointer to newval + r2 = pointer to target value + lr = return address + +Output: + + r0 = success code (zero or non-zero) + C flag = set if r0 == 0, clear if r0 != 0 + +Clobbered registers: + + r3, lr, flags + +Definition: + + Atomically store the 64-bit value pointed by *newval in *ptr only if *ptr + is equal to the 64-bit value pointed by *oldval. 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. + +Usage example: + +typedef int (__kuser_cmpxchg64_t)(const int64_t *oldval, + const int64_t *newval, + volatile int64_t *ptr); +#define __kuser_cmpxchg64 (*(__kuser_cmpxchg64_t *)0xffff0f60) + +int64_t atomic_add64(volatile int64_t *ptr, int64_t val) +{ + int64_t old, new; + + do { + old = *ptr; + new = old + val; + } while(__kuser_cmpxchg64(&old, &new, ptr)); + + return new; +} + +Notes: + + - This routine already includes memory barriers as needed. + + - Due to the length of this sequence, this spans 2 conventional kuser + "slots", therefore 0xffff0f80 is not used as a valid entry point. + + - Valid only if __kuser_helper_version >= 5 (from kernel version 3.1). diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 63f7907c4c3c..9be97deca215 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 @@ -775,6 +775,99 @@ ENDPROC(__switch_to) .globl __kuser_helper_start __kuser_helper_start: +/* + * 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_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 + __kuser_memory_barrier: @ 0xffff0fa0 smp_dmb arm usr_ret lr @@ -816,7 +909,7 @@ __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. -- cgit v1.2.3 From 090ab3ff8ebb842c0f159d34d57d6e51bd94ace1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 26 Apr 2011 06:29:53 +0100 Subject: ARM: 6886/1: mmc, Add zboot from eSD support for SuperH Mobile ARM This allows a ROM-able zImage to be written to eSD and for SuperH Mobile ARM to boot directly from the SDHI hardware block. This is achieved by the MaskROM loading the first portion of the image into MERAM and then jumping to it. This portion contains loader code which copies the entire image to SDRAM and jumps to it. From there the zImage boot code proceeds as normal, uncompressing the image into its final location and then jumping to it. Cc: Paul Mundt Acked-by: Magnus Damm Acked-by: Paul Mundt Signed-off-by: Simon Horman Signed-off-by: Russell King --- Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt | 42 ++ arch/arm/Kconfig | 33 +- arch/arm/boot/compressed/Makefile | 10 +- arch/arm/boot/compressed/head-shmobile.S | 12 +- arch/arm/boot/compressed/mmcif-sh7372.c | 2 +- arch/arm/boot/compressed/sdhi-sh7372.c | 95 +++++ arch/arm/boot/compressed/sdhi-shmobile.c | 449 ++++++++++++++++++++++ arch/arm/boot/compressed/sdhi-shmobile.h | 11 + arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h | 21 + arch/arm/mach-shmobile/include/mach/sdhi.h | 16 + 10 files changed, 674 insertions(+), 17 deletions(-) create mode 100644 Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt create mode 100644 arch/arm/boot/compressed/sdhi-sh7372.c create mode 100644 arch/arm/boot/compressed/sdhi-shmobile.c create mode 100644 arch/arm/boot/compressed/sdhi-shmobile.h create mode 100644 arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h create mode 100644 arch/arm/mach-shmobile/include/mach/sdhi.h diff --git a/Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt b/Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt new file mode 100644 index 000000000000..441959846e1a --- /dev/null +++ b/Documentation/arm/SH-Mobile/zboot-rom-sdhi.txt @@ -0,0 +1,42 @@ +ROM-able zImage boot from eSD +----------------------------- + +An ROM-able zImage compiled with ZBOOT_ROM_SDHI may be written to eSD and +SuperH Mobile ARM will to boot directly from the SDHI hardware block. + +This is achieved by the mask ROM loading the first portion of the image into +MERAM and then jumping to it. This portion contains loader code which +copies the entire image to SDRAM and jumps to it. From there the zImage +boot code proceeds as normal, uncompressing the image into its final +location and then jumping to it. + +This code has been tested on an mackerel board using the developer 1A eSD +boot mode which is configured using the following jumper settings. + + 8 7 6 5 4 3 2 1 + x|x|x|x| |x|x| +S4 -+-+-+-+-+-+-+- + | | | |x| | |x on + +The eSD card needs to be present in SDHI slot 1 (CN7). +As such S1 and S33 also need to be configured as per +the notes in arch/arm/mach-shmobile/board-mackerel.c. + +A partial zImage must be written to physical partition #1 (boot) +of the eSD at sector 0 in vrl4 format. A utility vrl4 is supplied to +accomplish this. + +e.g. + vrl4 < zImage | dd of=/dev/sdX bs=512 count=17 + +A full copy of _the same_ zImage should be written to physical partition #1 +(boot) of the eSD at sector 0. This should _not_ be in vrl4 format. + + vrl4 < zImage | dd of=/dev/sdX bs=512 + +Note: The commands above assume that the physical partition has been +switched. No such facility currently exists in the Linux Kernel. + +Physical partitions are described in the eSD specification. At the time of +writing they are not the same as partitions that are typically configured +using fdisk and visible through /proc/partitions diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index cc0dcbf1f6b5..cd8f520dd03d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1718,17 +1718,34 @@ config ZBOOT_ROM Say Y here if you intend to execute your compressed kernel image (zImage) directly from ROM or flash. If unsure, say N. +choice + prompt "Include SD/MMC loader in zImage (EXPERIMENTAL)" + depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL + default ZBOOT_ROM_NONE + help + Include experimental SD/MMC loading code in the ROM-able zImage. + With this enabled it is possible to write the the ROM-able zImage + kernel image to an MMC or SD card and boot the kernel straight + from the reset vector. At reset the processor Mask ROM will load + the first part of the the ROM-able zImage which in turn loads the + rest the kernel image to RAM. + +config ZBOOT_ROM_NONE + bool "No SD/MMC loader in zImage (EXPERIMENTAL)" + help + Do not load image from SD or MMC + config ZBOOT_ROM_MMCIF bool "Include MMCIF loader in zImage (EXPERIMENTAL)" - depends on ZBOOT_ROM && ARCH_SH7372 && EXPERIMENTAL help - Say Y here to include experimental MMCIF loading code in the - ROM-able zImage. With this enabled it is possible to write the - the ROM-able zImage kernel image to an MMC card and boot the - kernel straight from the reset vector. At reset the processor - Mask ROM will load the first part of the the ROM-able zImage - which in turn loads the rest the kernel image to RAM using the - MMCIF hardware block. + Load image from MMCIF hardware block. + +config ZBOOT_ROM_SH_MOBILE_SDHI + bool "Include SuperH Mobile SDHI loader in zImage (EXPERIMENTAL)" + help + Load image from SDHI hardware block + +endchoice config CMDLINE string "Default kernel command string" diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 23aad0722303..0c74a6fab952 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -6,13 +6,19 @@ OBJS = -# Ensure that mmcif loader code appears early in the image +# Ensure that MMCIF loader code appears early in the image # to minimise that number of bocks that have to be read in # order to load it. ifeq ($(CONFIG_ZBOOT_ROM_MMCIF),y) -ifeq ($(CONFIG_ARCH_SH7372),y) OBJS += mmcif-sh7372.o endif + +# Ensure that SDHI loader code appears early in the image +# to minimise that number of bocks that have to be read in +# order to load it. +ifeq ($(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI),y) +OBJS += sdhi-shmobile.o +OBJS += sdhi-sh7372.o endif AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET) diff --git a/arch/arm/boot/compressed/head-shmobile.S b/arch/arm/boot/compressed/head-shmobile.S index c943d2e7da9d..fe3719b516fd 100644 --- a/arch/arm/boot/compressed/head-shmobile.S +++ b/arch/arm/boot/compressed/head-shmobile.S @@ -25,14 +25,14 @@ /* load board-specific initialization code */ #include -#ifdef CONFIG_ZBOOT_ROM_MMCIF - /* Load image from MMC */ - adr sp, __tmp_stack + 128 +#if defined(CONFIG_ZBOOT_ROM_MMCIF) || defined(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI) + /* Load image from MMC/SD */ + adr sp, __tmp_stack + 256 ldr r0, __image_start ldr r1, __image_end subs r1, r1, r0 ldr r0, __load_base - bl mmcif_loader + bl mmc_loader /* Jump to loaded code */ ldr r0, __loaded @@ -51,9 +51,9 @@ __loaded: .long __continue .align __tmp_stack: - .space 128 + .space 256 __continue: -#endif /* CONFIG_ZBOOT_ROM_MMCIF */ +#endif /* CONFIG_ZBOOT_ROM_MMC || CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI */ b 1f __atags:@ tag #1 diff --git a/arch/arm/boot/compressed/mmcif-sh7372.c b/arch/arm/boot/compressed/mmcif-sh7372.c index 7453c8337b83..b6f61d9a5a1b 100644 --- a/arch/arm/boot/compressed/mmcif-sh7372.c +++ b/arch/arm/boot/compressed/mmcif-sh7372.c @@ -40,7 +40,7 @@ * to an MMC card * # dd if=vrl4.out of=/dev/sdx bs=512 seek=1 */ -asmlinkage void mmcif_loader(unsigned char *buf, unsigned long len) +asmlinkage void mmc_loader(unsigned char *buf, unsigned long len) { mmc_init_progress(); mmc_update_progress(MMC_PROGRESS_ENTER); diff --git a/arch/arm/boot/compressed/sdhi-sh7372.c b/arch/arm/boot/compressed/sdhi-sh7372.c new file mode 100644 index 000000000000..d403a8b24d7f --- /dev/null +++ b/arch/arm/boot/compressed/sdhi-sh7372.c @@ -0,0 +1,95 @@ +/* + * SuperH Mobile SDHI + * + * Copyright (C) 2010 Magnus Damm + * Copyright (C) 2010 Kuninori Morimoto + * Copyright (C) 2010 Simon Horman + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Parts inspired by u-boot + */ + +#include +#include +#include +#include + +#include "sdhi-shmobile.h" + +#define PORT179CR 0xe60520b3 +#define PORT180CR 0xe60520b4 +#define PORT181CR 0xe60520b5 +#define PORT182CR 0xe60520b6 +#define PORT183CR 0xe60520b7 +#define PORT184CR 0xe60520b8 + +#define SMSTPCR3 0xe615013c + +#define CR_INPUT_ENABLE 0x10 +#define CR_FUNCTION1 0x01 + +#define SDHI1_BASE (void __iomem *)0xe6860000 +#define SDHI_BASE SDHI1_BASE + +/* SuperH Mobile SDHI loader + * + * loads the zImage from an SD card starting from block 0 + * on physical partition 1 + * + * The image must be start with a vrl4 header and + * the zImage must start at offset 512 of the image. That is, + * at block 1 (=byte 512) of physical partition 1 + * + * Use the following line to write the vrl4 formated zImage + * to an SD card + * # dd if=vrl4.out of=/dev/sdx bs=512 + */ +asmlinkage void mmc_loader(unsigned short *buf, unsigned long len) +{ + int high_capacity; + + mmc_init_progress(); + + mmc_update_progress(MMC_PROGRESS_ENTER); + /* Initialise SDHI1 */ + /* PORT184CR: GPIO_FN_SDHICMD1 Control */ + __raw_writeb(CR_FUNCTION1, PORT184CR); + /* PORT179CR: GPIO_FN_SDHICLK1 Control */ + __raw_writeb(CR_INPUT_ENABLE|CR_FUNCTION1, PORT179CR); + /* PORT181CR: GPIO_FN_SDHID1_3 Control */ + __raw_writeb(CR_FUNCTION1, PORT183CR); + /* PORT182CR: GPIO_FN_SDHID1_2 Control */ + __raw_writeb(CR_FUNCTION1, PORT182CR); + /* PORT183CR: GPIO_FN_SDHID1_1 Control */ + __raw_writeb(CR_FUNCTION1, PORT181CR); + /* PORT180CR: GPIO_FN_SDHID1_0 Control */ + __raw_writeb(CR_FUNCTION1, PORT180CR); + + /* Enable clock to SDHI1 hardware block */ + __raw_writel(__raw_readl(SMSTPCR3) & ~(1 << 13), SMSTPCR3); + + /* setup SDHI hardware */ + mmc_update_progress(MMC_PROGRESS_INIT); + high_capacity = sdhi_boot_init(SDHI_BASE); + if (high_capacity < 0) + goto err; + + mmc_update_progress(MMC_PROGRESS_LOAD); + /* load kernel */ + if (sdhi_boot_do_read(SDHI_BASE, high_capacity, + 0, /* Kernel is at block 1 */ + (len + TMIO_BBS - 1) / TMIO_BBS, buf)) + goto err; + + /* Disable clock to SDHI1 hardware block */ + __raw_writel(__raw_readl(SMSTPCR3) & (1 << 13), SMSTPCR3); + + mmc_update_progress(MMC_PROGRESS_DONE); + + return; +err: + for(;;); +} diff --git a/arch/arm/boot/compressed/sdhi-shmobile.c b/arch/arm/boot/compressed/sdhi-shmobile.c new file mode 100644 index 000000000000..bd3d46980955 --- /dev/null +++ b/arch/arm/boot/compressed/sdhi-shmobile.c @@ -0,0 +1,449 @@ +/* + * SuperH Mobile SDHI + * + * Copyright (C) 2010 Magnus Damm + * Copyright (C) 2010 Kuninori Morimoto + * Copyright (C) 2010 Simon Horman + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Parts inspired by u-boot + */ + +#include +#include +#include +#include +#include +#include +#include + +#define OCR_FASTBOOT (1<<29) +#define OCR_HCS (1<<30) +#define OCR_BUSY (1<<31) + +#define RESP_CMD12 0x00000030 + +static inline u16 sd_ctrl_read16(void __iomem *base, int addr) +{ + return __raw_readw(base + addr); +} + +static inline u32 sd_ctrl_read32(void __iomem *base, int addr) +{ + return __raw_readw(base + addr) | + __raw_readw(base + addr + 2) << 16; +} + +static inline void sd_ctrl_write16(void __iomem *base, int addr, u16 val) +{ + __raw_writew(val, base + addr); +} + +static inline void sd_ctrl_write32(void __iomem *base, int addr, u32 val) +{ + __raw_writew(val, base + addr); + __raw_writew(val >> 16, base + addr + 2); +} + +#define ALL_ERROR (TMIO_STAT_CMD_IDX_ERR | TMIO_STAT_CRCFAIL | \ + TMIO_STAT_STOPBIT_ERR | TMIO_STAT_DATATIMEOUT | \ + TMIO_STAT_RXOVERFLOW | TMIO_STAT_TXUNDERRUN | \ + TMIO_STAT_CMDTIMEOUT | TMIO_STAT_ILL_ACCESS | \ + TMIO_STAT_ILL_FUNC) + +static int sdhi_intr(void __iomem *base) +{ + unsigned long state = sd_ctrl_read32(base, CTL_STATUS); + + if (state & ALL_ERROR) { + sd_ctrl_write32(base, CTL_STATUS, ~ALL_ERROR); + sd_ctrl_write32(base, CTL_IRQ_MASK, + ALL_ERROR | + sd_ctrl_read32(base, CTL_IRQ_MASK)); + return -EINVAL; + } + if (state & TMIO_STAT_CMDRESPEND) { + sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND); + sd_ctrl_write32(base, CTL_IRQ_MASK, + TMIO_STAT_CMDRESPEND | + sd_ctrl_read32(base, CTL_IRQ_MASK)); + return 0; + } + if (state & TMIO_STAT_RXRDY) { + sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_RXRDY); + sd_ctrl_write32(base, CTL_IRQ_MASK, + TMIO_STAT_RXRDY | TMIO_STAT_TXUNDERRUN | + sd_ctrl_read32(base, CTL_IRQ_MASK)); + return 0; + } + if (state & TMIO_STAT_DATAEND) { + sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_DATAEND); + sd_ctrl_write32(base, CTL_IRQ_MASK, + TMIO_STAT_DATAEND | + sd_ctrl_read32(base, CTL_IRQ_MASK)); + return 0; + } + + return -EAGAIN; +} + +static int sdhi_boot_wait_resp_end(void __iomem *base) +{ + int err = -EAGAIN, timeout = 10000000; + + while (timeout--) { + err = sdhi_intr(base); + if (err != -EAGAIN) + break; + udelay(1); + } + + return err; +} + +/* SDHI_CLK_CTRL */ +#define CLK_MMC_ENABLE (1 << 8) +#define CLK_MMC_INIT (1 << 6) /* clk / 256 */ + +static void sdhi_boot_mmc_clk_stop(void __iomem *base) +{ + sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, 0x0000); + msleep(10); + sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, ~CLK_MMC_ENABLE & + sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL)); + msleep(10); +} + +static void sdhi_boot_mmc_clk_start(void __iomem *base) +{ + sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, CLK_MMC_ENABLE | + sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL)); + msleep(10); + sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, CLK_MMC_ENABLE); + msleep(10); +} + +static void sdhi_boot_reset(void __iomem *base) +{ + sd_ctrl_write16(base, CTL_RESET_SD, 0x0000); + msleep(10); + sd_ctrl_write16(base, CTL_RESET_SD, 0x0001); + msleep(10); +} + +/* Set MMC clock / power. + * Note: This controller uses a simple divider scheme therefore it cannot + * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as + * MMC wont run that fast, it has to be clocked at 12MHz which is the next + * slowest setting. + */ +static int sdhi_boot_mmc_set_ios(void __iomem *base, struct mmc_ios *ios) +{ + if (sd_ctrl_read32(base, CTL_STATUS) & TMIO_STAT_CMD_BUSY) + return -EBUSY; + + if (ios->clock) + sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, + ios->clock | CLK_MMC_ENABLE); + + /* Power sequence - OFF -> ON -> UP */ + switch (ios->power_mode) { + case MMC_POWER_OFF: /* power down SD bus */ + sdhi_boot_mmc_clk_stop(base); + break; + case MMC_POWER_ON: /* power up SD bus */ + break; + case MMC_POWER_UP: /* start bus clock */ + sdhi_boot_mmc_clk_start(base); + break; + } + + switch (ios->bus_width) { + case MMC_BUS_WIDTH_1: + sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x80e0); + break; + case MMC_BUS_WIDTH_4: + sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x00e0); + break; + } + + /* Let things settle. delay taken from winCE driver */ + udelay(140); + + return 0; +} + +/* These are the bitmasks the tmio chip requires to implement the MMC response + * types. Note that R1 and R6 are the same in this scheme. */ +#define RESP_NONE 0x0300 +#define RESP_R1 0x0400 +#define RESP_R1B 0x0500 +#define RESP_R2 0x0600 +#define RESP_R3 0x0700 +#define DATA_PRESENT 0x0800 +#define TRANSFER_READ 0x1000 + +static int sdhi_boot_request(void __iomem *base, struct mmc_command *cmd) +{ + int err, c = cmd->opcode; + + switch (mmc_resp_type(cmd)) { + case MMC_RSP_NONE: c |= RESP_NONE; break; + case MMC_RSP_R1: c |= RESP_R1; break; + case MMC_RSP_R1B: c |= RESP_R1B; break; + case MMC_RSP_R2: c |= RESP_R2; break; + case MMC_RSP_R3: c |= RESP_R3; break; + default: + return -EINVAL; + } + + /* No interrupts so this may not be cleared */ + sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND); + + sd_ctrl_write32(base, CTL_IRQ_MASK, TMIO_STAT_CMDRESPEND | + sd_ctrl_read32(base, CTL_IRQ_MASK)); + sd_ctrl_write32(base, CTL_ARG_REG, cmd->arg); + sd_ctrl_write16(base, CTL_SD_CMD, c); + + + sd_ctrl_write32(base, CTL_IRQ_MASK, + ~(TMIO_STAT_CMDRESPEND | ALL_ERROR) & + sd_ctrl_read32(base, CTL_IRQ_MASK)); + + err = sdhi_boot_wait_resp_end(base); + if (err) + return err; + + cmd->resp[0] = sd_ctrl_read32(base, CTL_RESPONSE); + + return 0; +} + +static int sdhi_boot_do_read_single(void __iomem *base, int high_capacity, + unsigned long block, unsigned short *buf) +{ + int err, i; + + /* CMD17 - Read */ + { + struct mmc_command cmd; + + cmd.opcode = MMC_READ_SINGLE_BLOCK | \ + TRANSFER_READ | DATA_PRESENT; + if (high_capacity) + cmd.arg = block; + else + cmd.arg = block * TMIO_BBS; + cmd.flags = MMC_RSP_R1; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + } + + sd_ctrl_write32(base, CTL_IRQ_MASK, + ~(TMIO_STAT_DATAEND | TMIO_STAT_RXRDY | + TMIO_STAT_TXUNDERRUN) & + sd_ctrl_read32(base, CTL_IRQ_MASK)); + err = sdhi_boot_wait_resp_end(base); + if (err) + return err; + + sd_ctrl_write16(base, CTL_SD_XFER_LEN, TMIO_BBS); + for (i = 0; i < TMIO_BBS / sizeof(*buf); i++) + *buf++ = sd_ctrl_read16(base, RESP_CMD12); + + err = sdhi_boot_wait_resp_end(base); + if (err) + return err; + + return 0; +} + +int sdhi_boot_do_read(void __iomem *base, int high_capacity, + unsigned long offset, unsigned short count, + unsigned short *buf) +{ + unsigned long i; + int err = 0; + + for (i = 0; i < count; i++) { + err = sdhi_boot_do_read_single(base, high_capacity, offset + i, + buf + (i * TMIO_BBS / + sizeof(*buf))); + if (err) + return err; + } + + return 0; +} + +#define VOLTAGES (MMC_VDD_32_33 | MMC_VDD_33_34) + +int sdhi_boot_init(void __iomem *base) +{ + bool sd_v2 = false, sd_v1_0 = false; + unsigned short cid; + int err, high_capacity = 0; + + sdhi_boot_mmc_clk_stop(base); + sdhi_boot_reset(base); + + /* mmc0: clock 400000Hz busmode 1 powermode 2 cs 0 Vdd 21 width 0 timing 0 */ + { + struct mmc_ios ios; + ios.power_mode = MMC_POWER_ON; + ios.bus_width = MMC_BUS_WIDTH_1; + ios.clock = CLK_MMC_INIT; + err = sdhi_boot_mmc_set_ios(base, &ios); + if (err) + return err; + } + + /* CMD0 */ + { + struct mmc_command cmd; + msleep(1); + cmd.opcode = MMC_GO_IDLE_STATE; + cmd.arg = 0; + cmd.flags = MMC_RSP_NONE; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + msleep(2); + } + + /* CMD8 - Test for SD version 2 */ + { + struct mmc_command cmd; + cmd.opcode = SD_SEND_IF_COND; + cmd.arg = (VOLTAGES != 0) << 8 | 0xaa; + cmd.flags = MMC_RSP_R1; + err = sdhi_boot_request(base, &cmd); /* Ignore error */ + if ((cmd.resp[0] & 0xff) == 0xaa) + sd_v2 = true; + } + + /* CMD55 - Get OCR (SD) */ + { + int timeout = 1000; + struct mmc_command cmd; + + cmd.arg = 0; + + do { + cmd.opcode = MMC_APP_CMD; + cmd.flags = MMC_RSP_R1; + cmd.arg = 0; + err = sdhi_boot_request(base, &cmd); + if (err) + break; + + cmd.opcode = SD_APP_OP_COND; + cmd.flags = MMC_RSP_R3; + cmd.arg = (VOLTAGES & 0xff8000); + if (sd_v2) + cmd.arg |= OCR_HCS; + cmd.arg |= OCR_FASTBOOT; + err = sdhi_boot_request(base, &cmd); + if (err) + break; + + msleep(1); + } while((!(cmd.resp[0] & OCR_BUSY)) && --timeout); + + if (!err && timeout) { + if (!sd_v2) + sd_v1_0 = true; + high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS; + } + } + + /* CMD1 - Get OCR (MMC) */ + if (!sd_v2 && !sd_v1_0) { + int timeout = 1000; + struct mmc_command cmd; + + do { + cmd.opcode = MMC_SEND_OP_COND; + cmd.arg = VOLTAGES | OCR_HCS; + cmd.flags = MMC_RSP_R3; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + + msleep(1); + } while((!(cmd.resp[0] & OCR_BUSY)) && --timeout); + + if (!timeout) + return -EAGAIN; + + high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS; + } + + /* CMD2 - Get CID */ + { + struct mmc_command cmd; + cmd.opcode = MMC_ALL_SEND_CID; + cmd.arg = 0; + cmd.flags = MMC_RSP_R2; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + } + + /* CMD3 + * MMC: Set the relative address + * SD: Get the relative address + * Also puts the card into the standby state + */ + { + struct mmc_command cmd; + cmd.opcode = MMC_SET_RELATIVE_ADDR; + cmd.arg = 0; + cmd.flags = MMC_RSP_R1; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + cid = cmd.resp[0] >> 16; + } + + /* CMD9 - Get CSD */ + { + struct mmc_command cmd; + cmd.opcode = MMC_SEND_CSD; + cmd.arg = cid << 16; + cmd.flags = MMC_RSP_R2; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + } + + /* CMD7 - Select the card */ + { + struct mmc_command cmd; + cmd.opcode = MMC_SELECT_CARD; + //cmd.arg = rca << 16; + cmd.arg = cid << 16; + //cmd.flags = MMC_RSP_R1B; + cmd.flags = MMC_RSP_R1; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + } + + /* CMD16 - Set the block size */ + { + struct mmc_command cmd; + cmd.opcode = MMC_SET_BLOCKLEN; + cmd.arg = TMIO_BBS; + cmd.flags = MMC_RSP_R1; + err = sdhi_boot_request(base, &cmd); + if (err) + return err; + } + + return high_capacity; +} diff --git a/arch/arm/boot/compressed/sdhi-shmobile.h b/arch/arm/boot/compressed/sdhi-shmobile.h new file mode 100644 index 000000000000..92eaa09f985e --- /dev/null +++ b/arch/arm/boot/compressed/sdhi-shmobile.h @@ -0,0 +1,11 @@ +#ifndef SDHI_MOBILE_H +#define SDHI_MOBILE_H + +#include + +int sdhi_boot_do_read(void __iomem *base, int high_capacity, + unsigned long offset, unsigned short count, + unsigned short *buf); +int sdhi_boot_init(void __iomem *base); + +#endif diff --git a/arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h b/arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h new file mode 100644 index 000000000000..4a81b01f1e8f --- /dev/null +++ b/arch/arm/mach-shmobile/include/mach/sdhi-sh7372.h @@ -0,0 +1,21 @@ +#ifndef SDHI_SH7372_H +#define SDHI_SH7372_H + +#define SDGENCNTA 0xfe40009c + +/* The countdown of SDGENCNTA is controlled by + * ZB3D2CLK which runs at 149.5MHz. + * That is 149.5ticks/us. Approximate this as 150ticks/us. + */ +static void udelay(int us) +{ + __raw_writel(us * 150, SDGENCNTA); + while(__raw_readl(SDGENCNTA)) ; +} + +static void msleep(int ms) +{ + udelay(ms * 1000); +} + +#endif diff --git a/arch/arm/mach-shmobile/include/mach/sdhi.h b/arch/arm/mach-shmobile/include/mach/sdhi.h new file mode 100644 index 000000000000..0ec9e69f2c3b --- /dev/null +++ b/arch/arm/mach-shmobile/include/mach/sdhi.h @@ -0,0 +1,16 @@ +#ifndef SDHI_H +#define SDHI_H + +/************************************************** + * + * CPU specific settings + * + **************************************************/ + +#ifdef CONFIG_ARCH_SH7372 +#include "mach/sdhi-sh7372.h" +#else +#error "unsupported CPU." +#endif + +#endif /* SDHI_H */ -- cgit v1.2.3 From ac8b9c1ce094d43372d0259de08045ffee745a41 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 10:22:08 +0100 Subject: ARM: entry: prefetch/data abort helpers: convert to macros Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 85 ++++++++++++++++++-------------------------- 1 file changed, 35 insertions(+), 50 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 90c62cd51ca9..dbe9eb88d550 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -44,6 +44,37 @@ 9997: .endm + .macro pabt_helper + mov r0, r2 @ pass address of aborted instruction. +#ifdef MULTI_PABORT + ldr r4, .LCprocfns + mov lr, pc + ldr pc, [r4, #PROCESSOR_PABT_FUNC] +#else + bl CPU_PABORT_HANDLER +#endif + .endm + + .macro dabt_helper + + @ + @ Call the processor-specific abort handler: + @ + @ r2 - aborted context pc + @ r3 - aborted context cpsr + @ + @ The abort handler must return the aborted address in r0, and + @ the fault status register in r1. r9 must be preserved. + @ +#ifdef MULTI_DABORT + ldr r4, .LCprocfns + mov lr, pc + ldr pc, [r4, #PROCESSOR_DABT_FUNC] +#else + bl CPU_DABORT_HANDLER +#endif + .endm + #ifdef CONFIG_KPROBES .section .kprobes.text,"ax",%progbits #else @@ -159,22 +190,7 @@ __dabt_svc: tst r3, #PSR_I_BIT biceq r9, r9, #PSR_I_BIT - @ - @ Call the processor-specific abort handler: - @ - @ r2 - aborted context pc - @ r3 - aborted context cpsr - @ - @ The abort handler must return the aborted address in r0, and - @ the fault status register in r1. r9 must be preserved. - @ -#ifdef MULTI_DABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_DABT_FUNC] -#else - bl CPU_DABORT_HANDLER -#endif + dabt_helper @ @ set desired IRQ state, then call main handler @@ -298,14 +314,7 @@ __pabt_svc: tst r3, #PSR_I_BIT biceq r9, r9, #PSR_I_BIT - mov r0, r2 @ pass address of aborted instruction. -#ifdef MULTI_PABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_PABT_FUNC] -#else - bl CPU_PABORT_HANDLER -#endif + pabt_helper debug_entry r1 msr cpsr_c, r9 @ Maybe enable interrupts mov r2, sp @ regs @@ -401,23 +410,7 @@ ENDPROC(__pabt_svc) __dabt_usr: usr_entry kuser_cmpxchg_check - - @ - @ Call the processor-specific abort handler: - @ - @ r2 - aborted context pc - @ r3 - aborted context cpsr - @ - @ The abort handler must return the aborted address in r0, and - @ the fault status register in r1. - @ -#ifdef MULTI_DABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_DABT_FUNC] -#else - bl CPU_DABORT_HANDLER -#endif + dabt_helper @ @ IRQs on, then call the main handler @@ -682,15 +675,7 @@ ENDPROC(__und_usr_unknown) .align 5 __pabt_usr: usr_entry - - mov r0, r2 @ pass address of aborted instruction. -#ifdef MULTI_PABORT - ldr r4, .LCprocfns - mov lr, pc - ldr pc, [r4, #PROCESSOR_PABT_FUNC] -#else - bl CPU_PABORT_HANDLER -#endif + pabt_helper debug_entry r1 enable_irq @ Enable interrupts mov r2, sp @ regs -- cgit v1.2.3 From 0402becef94c43bb2bb483653a5cee2fb5049764 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 15:46:08 +0100 Subject: ARM: entry: prefetch/data abort helpers: avoid corrupting r4 Replace r4 with ip for calling abort helpers - ip is allowed to be corrupted by called functions in the ABI, so it makes more sense to use such a register. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index dbe9eb88d550..6855f6dd72d0 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -47,9 +47,9 @@ .macro pabt_helper mov r0, r2 @ pass address of aborted instruction. #ifdef MULTI_PABORT - ldr r4, .LCprocfns + ldr ip, .LCprocfns mov lr, pc - ldr pc, [r4, #PROCESSOR_PABT_FUNC] + ldr pc, [ip, #PROCESSOR_PABT_FUNC] #else bl CPU_PABORT_HANDLER #endif @@ -67,9 +67,9 @@ @ the fault status register in r1. r9 must be preserved. @ #ifdef MULTI_DABORT - ldr r4, .LCprocfns + ldr ip, .LCprocfns mov lr, pc - ldr pc, [r4, #PROCESSOR_DABT_FUNC] + ldr pc, [ip, #PROCESSOR_DABT_FUNC] #else bl CPU_DABORT_HANDLER #endif -- cgit v1.2.3 From be020f8618caa0670a2a5b5a5df79549520f7867 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 13:42:01 +0100 Subject: ARM: entry: abort-macro: specify registers to be used for macros Require all callers of abort macros to specify the registers to be used. This improves the documentation at the callsites as to which registers are being used by this assembly code. Signed-off-by: Russell King --- arch/arm/mm/abort-ev4t.S | 2 +- arch/arm/mm/abort-ev5t.S | 4 ++-- arch/arm/mm/abort-ev5tj.S | 4 ++-- arch/arm/mm/abort-ev6.S | 4 ++-- arch/arm/mm/abort-macro.S | 30 +++++++++++++++--------------- 5 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/arm/mm/abort-ev4t.S b/arch/arm/mm/abort-ev4t.S index b6282548f922..9910123079ce 100644 --- a/arch/arm/mm/abort-ev4t.S +++ b/arch/arm/mm/abort-ev4t.S @@ -22,7 +22,7 @@ ENTRY(v4t_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - do_thumb_abort + do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 ldreq r3, [r2] @ read aborted ARM instruction bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR tst r3, #1 << 20 @ check write diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S index 02251b526c0d..800e8d42d39e 100644 --- a/arch/arm/mm/abort-ev5t.S +++ b/arch/arm/mm/abort-ev5t.S @@ -22,10 +22,10 @@ ENTRY(v5t_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - do_thumb_abort + do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 ldreq r3, [r2] @ read aborted ARM instruction bic r1, r1, #1 << 11 @ clear bits 11 of FSR - do_ldrd_abort + do_ldrd_abort tmp=r2, insn=r3 tst r3, #1 << 20 @ check write orreq r1, r1, #1 << 11 mov pc, lr diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S index bce68d601c8b..bcb58d2fc11a 100644 --- a/arch/arm/mm/abort-ev5tj.S +++ b/arch/arm/mm/abort-ev5tj.S @@ -25,9 +25,9 @@ ENTRY(v5tj_early_abort) bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR tst r3, #PSR_J_BIT @ Java? movne pc, lr - do_thumb_abort + do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 ldreq r3, [r2] @ read aborted ARM instruction - do_ldrd_abort + do_ldrd_abort tmp=r2, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. mov pc, lr diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 1478aa522144..ef526e702a5c 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -35,12 +35,12 @@ ENTRY(v6_early_abort) bic r1, r1, #1 << 11 @ clear bit 11 of FSR tst r3, #PSR_J_BIT @ Java? movne pc, lr - do_thumb_abort + do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 ldreq r3, [r2] @ read aborted ARM instruction #ifdef CONFIG_CPU_ENDIAN_BE8 reveq r3, r3 #endif - do_ldrd_abort + do_ldrd_abort tmp=r2, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. mov pc, lr diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S index d7cb1bfa51a4..8d3b9f999d1e 100644 --- a/arch/arm/mm/abort-macro.S +++ b/arch/arm/mm/abort-macro.S @@ -9,33 +9,33 @@ * */ - .macro do_thumb_abort - tst r3, #PSR_T_BIT + .macro do_thumb_abort, fsr, pc, psr, tmp + tst \psr, #PSR_T_BIT beq not_thumb - ldrh r3, [r2] @ Read aborted Thumb instruction - and r3, r3, # 0xfe00 @ Mask opcode field - cmp r3, # 0x5600 @ Is it ldrsb? - orreq r3, r3, #1 << 11 @ Set L-bit if yes - tst r3, #1 << 11 @ L = 0 -> write - orreq r1, r1, #1 << 11 @ yes. + ldrh \tmp, [\pc] @ Read aborted Thumb instruction + and \tmp, \tmp, # 0xfe00 @ Mask opcode field + cmp \tmp, # 0x5600 @ Is it ldrsb? + orreq \tmp, \tmp, #1 << 11 @ Set L-bit if yes + tst \tmp, #1 << 11 @ L = 0 -> write + orreq \psr, \psr, #1 << 11 @ yes. mov pc, lr not_thumb: .endm /* - * We check for the following insturction encoding for LDRD. + * We check for the following instruction encoding for LDRD. * - * [27:25] == 0 + * [27:25] == 000 * [7:4] == 1101 * [20] == 0 */ - .macro do_ldrd_abort - tst r3, #0x0e000000 @ [27:25] == 0 + .macro do_ldrd_abort, tmp, insn + tst \insn, #0x0e000000 @ [27:25] == 0 bne not_ldrd - and r2, r3, #0x000000f0 @ [7:4] == 1101 - cmp r2, #0x000000d0 + and \tmp, \insn, #0x000000f0 @ [7:4] == 1101 + cmp \tmp, #0x000000d0 bne not_ldrd - tst r3, #1 << 20 @ [20] == 0 + tst \insn, #1 << 20 @ [20] == 0 moveq pc, lr not_ldrd: .endm -- cgit v1.2.3 From 198a0a927ab9c52a68297120ee6dd4e36a975b0e Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 13:51:44 +0100 Subject: ARM: entry: abort-macro: simplify do_ldrd_abort We can test bits 27:25 and 20 of the instruction at the same time; there's no need to separate out the check of bit 20. Signed-off-by: Russell King --- arch/arm/mm/abort-macro.S | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S index 8d3b9f999d1e..af97a10bc5ed 100644 --- a/arch/arm/mm/abort-macro.S +++ b/arch/arm/mm/abort-macro.S @@ -30,12 +30,10 @@ not_thumb: * [20] == 0 */ .macro do_ldrd_abort, tmp, insn - tst \insn, #0x0e000000 @ [27:25] == 0 + tst \insn, #0x0e100000 @ [27:25,20] == 0 bne not_ldrd and \tmp, \insn, #0x000000f0 @ [7:4] == 1101 cmp \tmp, #0x000000d0 - bne not_ldrd - tst \insn, #1 << 20 @ [20] == 0 moveq pc, lr not_ldrd: .endm -- cgit v1.2.3 From 1613cc1119ecdb1bdb950da53065e615e4c4b8db Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 10:57:57 +0100 Subject: ARM: entry: no need to increase preempt count for IRQ handlers irq_enter() and irq_exit() already take care of the preempt_count handling for interrupts, which increment and decrement the hardirq bits of the preempt count. So we can remove the preempt count handing in our IRQ entry/exit assembly, like x86 did some 9 years ago. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 6855f6dd72d0..1e5f387c70ae 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -220,16 +220,12 @@ __irq_svc: #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif -#ifdef CONFIG_PREEMPT - get_thread_info tsk - ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - add r7, r8, #1 @ increment it - str r7, [tsk, #TI_PREEMPT] -#endif irq_handler + #ifdef CONFIG_PREEMPT - str r8, [tsk, #TI_PREEMPT] @ restore preempt count + get_thread_info tsk + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count ldr r0, [tsk, #TI_FLAGS] @ get flags teq r8, #0 @ if preempt count != 0 movne r0, #0 @ force flags to 0 @@ -432,23 +428,8 @@ __irq_usr: bl trace_hardirqs_off #endif - get_thread_info tsk -#ifdef CONFIG_PREEMPT - ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - add r7, r8, #1 @ increment it - str r7, [tsk, #TI_PREEMPT] -#endif - irq_handler -#ifdef CONFIG_PREEMPT - ldr r0, [tsk, #TI_PREEMPT] - str r8, [tsk, #TI_PREEMPT] - teq r0, r7 - ARM( strne r0, [r0, -r0] ) - THUMB( movne r0, #0 ) - THUMB( strne r0, [r0] ) -#endif - + get_thread_info tsk mov why, #0 b ret_to_user_from_irq UNWIND(.fnend ) -- cgit v1.2.3 From fbab1c809467efe001194ab8bb17f0f451a17f97 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 16:57:50 +0100 Subject: ARM: entry: no need to check parent IRQ mask in IRQ handler return There's no point checking to see whether IRQs were masked in the parent context when returning from IRQ handling - the fact that we're handling an IRQ means that the parent context must have had IRQs unmasked. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 1e5f387c70ae..fd42e667a81b 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -234,8 +234,9 @@ __irq_svc: #endif ldr r4, [sp, #S_PSR] @ irqs are already disabled #ifdef CONFIG_TRACE_IRQFLAGS - tst r4, #PSR_I_BIT - bleq trace_hardirqs_on + @ 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 svc_exit r4 @ return from exception UNWIND(.fnend ) -- cgit v1.2.3 From f12482c9393da2c1f5cb3217f29aa79c653dd980 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 22 Jun 2011 15:30:51 +0100 Subject: ARM: 6974/1: pmu: refactor reservation Currently, PMU platform_device reservation relies on some minor abuse of the platform_device::id field for determining the type of PMU. This is problematic for device tree based probing, where the ID cannot be controlled. This patch removes reliance on the id field, and depends on each PMU's platform driver to figure out which type it is. As all PMUs handled by the current platform_driver name "arm-pmu" are CPU PMUs, this convention is hardcoded. New PMU types can be supported through the use of {of,platform}_device_id tables Signed-off-by: Mark Rutland Acked-by: Jamie Iles Acked-by: Will Deacon Cc: Rob Herring Cc: Mathieu Desnoyers Signed-off-by: Russell King --- arch/arm/include/asm/pmu.h | 2 +- arch/arm/kernel/perf_event.c | 4 ++-- arch/arm/kernel/pmu.c | 33 +++++++++++++++++++-------------- 3 files changed, 22 insertions(+), 17 deletions(-) diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index 7544ce6b481a..67c70a31a1be 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -52,7 +52,7 @@ reserve_pmu(enum arm_pmu_type device); * a cookie. */ extern int -release_pmu(struct platform_device *pdev); +release_pmu(enum arm_pmu_type type); /** * init_pmu() - Initialise the PMU. diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index d53c0abc4dd3..a6c643f2d2ca 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -435,7 +435,7 @@ armpmu_reserve_hardware(void) if (irq >= 0) free_irq(irq, NULL); } - release_pmu(pmu_device); + release_pmu(ARM_PMU_DEVICE_CPU); pmu_device = NULL; } @@ -454,7 +454,7 @@ armpmu_release_hardware(void) } armpmu->stop(); - release_pmu(pmu_device); + release_pmu(ARM_PMU_DEVICE_CPU); pmu_device = NULL; } diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index 2c79eec19262..87942b931c62 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -25,36 +25,41 @@ static volatile long pmu_lock; static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES]; -static int __devinit pmu_device_probe(struct platform_device *pdev) +static int __devinit pmu_register(struct platform_device *pdev, + enum arm_pmu_type type) { - - if (pdev->id < 0 || pdev->id >= ARM_NUM_PMU_DEVICES) { + if (type < 0 || type >= ARM_NUM_PMU_DEVICES) { pr_warning("received registration request for unknown " - "device %d\n", pdev->id); + "device %d\n", type); return -EINVAL; } - if (pmu_devices[pdev->id]) + if (pmu_devices[type]) pr_warning("registering new PMU device type %d overwrites " - "previous registration!\n", pdev->id); + "previous registration!\n", type); else pr_info("registered new PMU device of type %d\n", - pdev->id); + type); - pmu_devices[pdev->id] = pdev; + pmu_devices[type] = pdev; return 0; } -static struct platform_driver pmu_driver = { +static int __devinit armpmu_device_probe(struct platform_device *pdev) +{ + return pmu_register(pdev, ARM_PMU_DEVICE_CPU); +} + +static struct platform_driver armpmu_driver = { .driver = { .name = "arm-pmu", }, - .probe = pmu_device_probe, + .probe = armpmu_device_probe, }; static int __init register_pmu_driver(void) { - return platform_driver_register(&pmu_driver); + return platform_driver_register(&armpmu_driver); } device_initcall(register_pmu_driver); @@ -77,11 +82,11 @@ reserve_pmu(enum arm_pmu_type device) EXPORT_SYMBOL_GPL(reserve_pmu); int -release_pmu(struct platform_device *pdev) +release_pmu(enum arm_pmu_type device) { - if (WARN_ON(pdev != pmu_devices[pdev->id])) + if (WARN_ON(!pmu_devices[device])) return -EINVAL; - clear_bit_unlock(pdev->id, &pmu_lock); + clear_bit_unlock(device, &pmu_lock); return 0; } EXPORT_SYMBOL_GPL(release_pmu); -- cgit v1.2.3 From ae0c3751ab08d3fe039d48935e9ad2c46711b23b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 22 Jun 2011 15:32:48 +0100 Subject: ARM: 6975/1: pmu: reject duplicate PMU registrations Currently, the PMU reservation framework allows for multiple PMUs of the same type to register themselves. This can lead to a bug with the sequence: register_pmu(pmu1); reserve_pmu(pmu_type); register_pmu(pmu2); release_pmu(pmu1); Here, pmu1 cannot be released, and pmu2 cannot be reserved. This patch modifies register_pmu to reject registrations where a PMU is already present, preventing this problem. PMUs which can have multiple instances should not use the PMU reservation framework. Signed-off-by: Mark Rutland Acked-by: Jamie Iles Acked-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/pmu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index 87942b931c62..de6b1b0860c2 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -34,13 +34,13 @@ static int __devinit pmu_register(struct platform_device *pdev, return -EINVAL; } - if (pmu_devices[type]) - pr_warning("registering new PMU device type %d overwrites " - "previous registration!\n", type); - else - pr_info("registered new PMU device of type %d\n", - type); + if (pmu_devices[type]) { + pr_warning("rejecting duplicate registration of PMU device " + "type %d.", type); + return -ENOSPC; + } + pr_info("registered new PMU device of type %d\n", type); pmu_devices[type] = pdev; return 0; } -- cgit v1.2.3 From e73c34c3d522a60d9f7b38a7683076362bad98f5 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 22 Jun 2011 15:33:55 +0100 Subject: ARM: 6976/1: pmu: add OF probing support This is based on an earlier patch from Rob Herring > Add OF match table to enable OF style driver binding. The dts entry is like > this: > > pmu { > compatible = "arm,cortex-a9-pmu"; > interrupts = <100 101>; > }; > > The use of pdev->id as an index breaks with OF device binding, so set the type > based on the OF compatible string. This modification sets the PMU hardware type based on data embedded in the binding, allowing easy addition of new PMU types in future. Support for new PMU types not provided by devicetree can be added later using platform_device_id tables in a similar fashion. Signed-off-by: Mark Rutland Acked-by: Jamie Iles Acked-by: Rob Herring Cc: Will Deacon Signed-off-by: Russell King --- Documentation/devicetree/bindings/arm/pmu.txt | 21 +++++++++++++++++ arch/arm/kernel/pmu.c | 34 ++++++++++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletion(-) create mode 100644 Documentation/devicetree/bindings/arm/pmu.txt diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt new file mode 100644 index 000000000000..1c044eb320cc --- /dev/null +++ b/Documentation/devicetree/bindings/arm/pmu.txt @@ -0,0 +1,21 @@ +* ARM Performance Monitor Units + +ARM cores often have a PMU for counting cpu and cache events like cache misses +and hits. The interface to the PMU is part of the ARM ARM. The ARM PMU +representation in the device tree should be done as under:- + +Required properties: + +- compatible : should be one of + "arm,cortex-a9-pmu" + "arm,cortex-a8-pmu" + "arm,arm1176-pmu" + "arm,arm1136-pmu" +- interrupts : 1 combined interrupt or 1 per core. + +Example: + +pmu { + compatible = "arm,cortex-a9-pmu"; + interrupts = <100 101>; +}; diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index de6b1b0860c2..2ce00be697ea 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -45,14 +46,45 @@ static int __devinit pmu_register(struct platform_device *pdev, return 0; } +#define OF_MATCH_PMU(_name, _type) { \ + .compatible = _name, \ + .data = (void *)_type, \ +} + +#define OF_MATCH_CPU(name) OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU) + +static struct of_device_id armpmu_of_device_ids[] = { + OF_MATCH_CPU("arm,cortex-a9-pmu"), + OF_MATCH_CPU("arm,cortex-a8-pmu"), + OF_MATCH_CPU("arm,arm1136-pmu"), + OF_MATCH_CPU("arm,arm1176-pmu"), + {}, +}; + +enum arm_pmu_type armpmu_device_type(struct platform_device *pdev) +{ + const struct of_device_id *of_id; + + /* provided by of_device_id table */ + if (pdev->dev.of_node) { + of_id = of_match_device(armpmu_of_device_ids, &pdev->dev); + BUG_ON(!of_id); + return (enum arm_pmu_type)of_id->data; + } + + /* Provided by a 'legacy' platform_device */ + return ARM_PMU_DEVICE_CPU; +} + static int __devinit armpmu_device_probe(struct platform_device *pdev) { - return pmu_register(pdev, ARM_PMU_DEVICE_CPU); + return pmu_register(pdev, armpmu_device_type(pdev)); } static struct platform_driver armpmu_driver = { .driver = { .name = "arm-pmu", + .of_match_table = armpmu_of_device_ids, }, .probe = armpmu_device_probe, }; -- cgit v1.2.3 From e4b6381009d740bd3a97e6b841d8efe7fc70c1b7 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 22 Jun 2011 15:34:56 +0100 Subject: ARM: 6977/1: pmu: add platform_device_id table support This patch adds support for platform_device_id tables, allowing new PMU types to be registered with the correct type, without requiring new platform_driver shims to provide the type. An single entry for existing devices is provided. Macros matching functionality of the of_device_id table macros are provided for convenience. Signed-off-by: Mark Rutland Acked-by: Jamie Iles Cc: Rob Herring Cc: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/pmu.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index 2ce00be697ea..2b70709376c3 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -61,9 +61,22 @@ static struct of_device_id armpmu_of_device_ids[] = { {}, }; +#define PLAT_MATCH_PMU(_name, _type) { \ + .name = _name, \ + .driver_data = _type, \ +} + +#define PLAT_MATCH_CPU(_name) PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU) + +static struct platform_device_id armpmu_plat_device_ids[] = { + PLAT_MATCH_CPU("arm-pmu"), + {}, +}; + enum arm_pmu_type armpmu_device_type(struct platform_device *pdev) { const struct of_device_id *of_id; + const struct platform_device_id *pdev_id; /* provided by of_device_id table */ if (pdev->dev.of_node) { @@ -72,8 +85,10 @@ enum arm_pmu_type armpmu_device_type(struct platform_device *pdev) return (enum arm_pmu_type)of_id->data; } - /* Provided by a 'legacy' platform_device */ - return ARM_PMU_DEVICE_CPU; + /* Provided by platform_device_id table */ + pdev_id = platform_get_device_id(pdev); + BUG_ON(!pdev_id); + return pdev_id->driver_data; } static int __devinit armpmu_device_probe(struct platform_device *pdev) @@ -87,6 +102,7 @@ static struct platform_driver armpmu_driver = { .of_match_table = armpmu_of_device_ids, }, .probe = armpmu_device_probe, + .id_table = armpmu_plat_device_ids, }; static int __init register_pmu_driver(void) -- cgit v1.2.3 From 46e130d298a384b677426e19faec311749ff2677 Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Wed, 29 Jun 2011 18:40:23 +0200 Subject: ARM: pm: omap3: run the ASM sleep code from DDR Most of the ASM sleep code (in arch/arm/mach-omap2/sleep34xx.S) is copied to internal SRAM at boot and after wake-up from CORE OFF mode. However only a small part of the code really needs to run from internal SRAM. This fix lets most of the ASM idle code run from the DDR in order to minimize the SRAM usage and the overhead in the code copy. The only pieces of code that are mandatory in SRAM are: - the i443 erratum WA, - the i581 erratum WA, - the security extension code. SRAM usage: - original code: . 560 bytes for omap3_sram_configure_core_dpll (used by DVFS), . 852 bytes for omap_sram_idle (used by suspend/resume in RETention), . 124 bytes for es3_sdrc_fix (used by suspend/resume in OFF mode on ES3.x), . 108 bytes for save_secure_ram_context (used on HS parts only). With this fix the usage for suspend/resume in RETention goes down 288 bytes, so the gain in SRAM usage for suspend/resume is 564 bytes. Also fixed the SRAM initialization sequence to avoid an unnecessary copy to SRAM at boot time and for readability. Tested on Beagleboard (ES2.x) in idle with full RET and OFF modes. Kevin Hilman tested retention and off on 3430/n900, 3530/Overo and 3630/Zoom3 Signed-off-by: Jean Pihet Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Russell King --- arch/arm/mach-omap2/pm.h | 20 ++- arch/arm/mach-omap2/pm34xx.c | 20 +-- arch/arm/mach-omap2/sleep34xx.S | 303 +++++++++++++++++++++++----------------- arch/arm/plat-omap/sram.c | 15 +- 4 files changed, 206 insertions(+), 152 deletions(-) diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h index 45bcfce77352..a4ec213e30c0 100644 --- a/arch/arm/mach-omap2/pm.h +++ b/arch/arm/mach-omap2/pm.h @@ -88,18 +88,28 @@ extern int pm_dbg_regset_init(int reg_set); #define pm_dbg_regset_init(reg_set) do {} while (0); #endif /* CONFIG_PM_DEBUG */ +/* 24xx */ extern void omap24xx_idle_loop_suspend(void); +extern unsigned int omap24xx_idle_loop_suspend_sz; extern void omap24xx_cpu_suspend(u32 dll_ctrl, void __iomem *sdrc_dlla_ctrl, void __iomem *sdrc_power); +extern unsigned int omap24xx_cpu_suspend_sz; + +/* 3xxx */ extern void omap34xx_cpu_suspend(u32 *addr, int save_state); -extern int save_secure_ram_context(u32 *addr); -extern void omap3_save_scratchpad_contents(void); -extern unsigned int omap24xx_idle_loop_suspend_sz; +/* omap3_do_wfi function pointer and size, for copy to SRAM */ +extern void omap3_do_wfi(void); +extern unsigned int omap3_do_wfi_sz; +/* ... and its pointer from SRAM after copy */ +extern void (*omap3_do_wfi_sram)(void); + +/* save_secure_ram_context function pointer and size, for copy to SRAM */ +extern int save_secure_ram_context(u32 *addr); extern unsigned int save_secure_ram_context_sz; -extern unsigned int omap24xx_cpu_suspend_sz; -extern unsigned int omap34xx_cpu_suspend_sz; + +extern void omap3_save_scratchpad_contents(void); #define PM_RTA_ERRATUM_i608 (1 << 0) #define PM_SDRC_WAKEUP_ERRATUM_i583 (1 << 1) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 3e9a13e1ac57..e1c79bae7670 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -78,9 +78,8 @@ struct power_state { static LIST_HEAD(pwrst_list); -static void (*_omap_sram_idle)(u32 *addr, int save_state); - static int (*_omap_save_secure_sram)(u32 *addr); +void (*omap3_do_wfi_sram)(void); static struct powerdomain *mpu_pwrdm, *neon_pwrdm; static struct powerdomain *core_pwrdm, *per_pwrdm; @@ -309,7 +308,7 @@ static irqreturn_t prcm_interrupt_handler (int irq, void *dev_id) static void omap34xx_do_sram_idle(unsigned long save_state) { - _omap_sram_idle(omap3_arm_context, save_state); + omap34xx_cpu_suspend(omap3_arm_context, save_state); } void omap_sram_idle(void) @@ -328,9 +327,6 @@ void omap_sram_idle(void) int core_prev_state, per_prev_state; u32 sdrc_pwr = 0; - if (!_omap_sram_idle) - return; - pwrdm_clear_all_prev_pwrst(mpu_pwrdm); pwrdm_clear_all_prev_pwrst(neon_pwrdm); pwrdm_clear_all_prev_pwrst(core_pwrdm); @@ -826,10 +822,17 @@ static int __init clkdms_setup(struct clockdomain *clkdm, void *unused) return 0; } +/* + * Push functions to SRAM + * + * The minimum set of functions is pushed to SRAM for execution: + * - omap3_do_wfi for erratum i581 WA, + * - save_secure_ram_context for security extensions. + */ void omap_push_sram_idle(void) { - _omap_sram_idle = omap_sram_push(omap34xx_cpu_suspend, - omap34xx_cpu_suspend_sz); + omap3_do_wfi_sram = omap_sram_push(omap3_do_wfi, omap3_do_wfi_sz); + if (omap_type() != OMAP2_DEVICE_TYPE_GP) _omap_save_secure_sram = omap_sram_push(save_secure_ram_context, save_secure_ram_context_sz); @@ -894,7 +897,6 @@ static int __init omap3_pm_init(void) per_clkdm = clkdm_lookup("per_clkdm"); core_clkdm = clkdm_lookup("core_clkdm"); - omap_push_sram_idle(); #ifdef CONFIG_SUSPEND suspend_set_ops(&omap_pm_ops); #endif /* CONFIG_SUSPEND */ diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index d18f52e46c7c..17dbc5af6915 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -139,8 +139,10 @@ ENTRY(save_secure_ram_context_sz) * * * Notes: - * - this code gets copied to internal SRAM at boot and after wake-up - * from OFF mode. The execution pointer in SRAM is _omap_sram_idle. + * - only the minimum set of functions gets copied to internal SRAM at boot + * and after wake-up from OFF mode, cf. omap_push_sram_idle. The function + * pointers in SDRAM or SRAM are called depending on the desired low power + * target state. * - when the OMAP wakes up it continues at different execution points * depending on the low power mode (non-OFF vs OFF modes), * cf. 'Resume path for xxx mode' comments. @@ -158,9 +160,15 @@ ENTRY(omap34xx_cpu_suspend) * 3 - Both L1 and L2 lost and logic lost */ - /* Directly jump to WFI is the context save is not required */ - cmp r1, #0x0 - beq omap3_do_wfi + /* + * For OFF mode: save context and jump to WFI in SDRAM (omap3_do_wfi) + * For non-OFF modes: jump to the WFI code in SRAM (omap3_do_wfi_sram) + */ + ldr r4, omap3_do_wfi_sram_addr + ldr r5, [r4] + cmp r1, #0x0 @ If no context save required, + bxeq r5 @ jump to the WFI code in SRAM + /* Otherwise fall through to the save context code */ save_context_wfi: @@ -213,7 +221,32 @@ save_context_wfi: THUMB( nop ) .arm -omap3_do_wfi: + b omap3_do_wfi + +/* + * Local variables + */ +omap3_do_wfi_sram_addr: + .word omap3_do_wfi_sram +kernel_flush: + .word v7_flush_dcache_all + +/* =================================== + * == WFI instruction => Enter idle == + * =================================== + */ + +/* + * Do WFI instruction + * Includes the resume path for non-OFF modes + * + * This code gets copied to internal SRAM and is accessible + * from both SDRAM and SRAM: + * - executed from SRAM for non-off modes (omap3_do_wfi_sram), + * - executed from SDRAM for OFF mode (omap3_do_wfi). + */ + .align 3 +ENTRY(omap3_do_wfi) ldr r4, sdrc_power @ read the SDRC_POWER register ldr r5, [r4] @ read the contents of SDRC_POWER orr r5, r5, #0x40 @ enable self refresh on idle req @@ -245,8 +278,86 @@ omap3_do_wfi: nop nop nop - bl wait_sdrc_ok +/* + * This function implements the erratum ID i581 WA: + * SDRC state restore before accessing the SDRAM + * + * Only used at return from non-OFF mode. For OFF + * mode the ROM code configures the SDRC and + * the DPLL before calling the restore code directly + * from DDR. + */ + +/* Make sure SDRC accesses are ok */ +wait_sdrc_ok: + +/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */ + ldr r4, cm_idlest_ckgen +wait_dpll3_lock: + ldr r5, [r4] + tst r5, #1 + beq wait_dpll3_lock + + ldr r4, cm_idlest1_core +wait_sdrc_ready: + ldr r5, [r4] + tst r5, #0x2 + bne wait_sdrc_ready + /* allow DLL powerdown upon hw idle req */ + ldr r4, sdrc_power + ldr r5, [r4] + bic r5, r5, #0x40 + str r5, [r4] + +/* + * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a + * base instead. + * Be careful not to clobber r7 when maintaing this code. + */ + +is_dll_in_lock_mode: + /* Is dll in lock mode? */ + ldr r4, sdrc_dlla_ctrl + ldr r5, [r4] + tst r5, #0x4 + bne exit_nonoff_modes @ Return if locked + /* wait till dll locks */ + adr r7, kick_counter +wait_dll_lock_timed: + ldr r4, wait_dll_lock_counter + add r4, r4, #1 + str r4, [r7, #wait_dll_lock_counter - kick_counter] + ldr r4, sdrc_dlla_status + /* Wait 20uS for lock */ + mov r6, #8 +wait_dll_lock: + subs r6, r6, #0x1 + beq kick_dll + ldr r5, [r4] + and r5, r5, #0x4 + cmp r5, #0x4 + bne wait_dll_lock + b exit_nonoff_modes @ Return when locked + + /* disable/reenable DLL if not locked */ +kick_dll: + ldr r4, sdrc_dlla_ctrl + ldr r5, [r4] + mov r6, r5 + bic r6, #(1<<3) @ disable dll + str r6, [r4] + dsb + orr r6, r6, #(1<<3) @ enable dll + str r6, [r4] + dsb + ldr r4, kick_counter + add r4, r4, #1 + str r4, [r7] @ kick_counter + b wait_dll_lock_timed + +exit_nonoff_modes: + /* Re-enable C-bit if needed */ mrc p15, 0, r0, c1, c0, 0 tst r0, #(1 << 2) @ Check C bit enabled? orreq r0, r0, #(1 << 2) @ Enable the C bit if cleared @@ -260,6 +371,31 @@ omap3_do_wfi: */ ldmfd sp!, {r4 - r11, pc} @ restore regs and return +/* + * Local variables + */ +sdrc_power: + .word SDRC_POWER_V +cm_idlest1_core: + .word CM_IDLEST1_CORE_V +cm_idlest_ckgen: + .word CM_IDLEST_CKGEN_V +sdrc_dlla_status: + .word SDRC_DLLA_STATUS_V +sdrc_dlla_ctrl: + .word SDRC_DLLA_CTRL_V + /* + * When exporting to userspace while the counters are in SRAM, + * these 2 words need to be at the end to facilitate retrival! + */ +kick_counter: + .word 0 +wait_dll_lock_counter: + .word 0 + +ENTRY(omap3_do_wfi_sz) + .word . - omap3_do_wfi + /* * ============================== @@ -275,13 +411,17 @@ omap3_do_wfi: * restore_es3: applies to 34xx >= ES3.0 * restore_3630: applies to 36xx * restore: common code for 3xxx + * + * Note: when back from CORE and MPU OFF mode we are running + * from SDRAM, without MMU, without the caches and prediction. + * Also the SRAM content has been cleared. */ ENTRY(omap3_restore_es3) ldr r5, pm_prepwstst_core_p ldr r4, [r5] and r4, r4, #0x3 cmp r4, #0x0 @ Check if previous power state of CORE is OFF - bne omap3_restore + bne omap3_restore @ Fall through to OMAP3 common code adr r0, es3_sdrc_fix ldr r1, sram_base ldr r2, es3_sdrc_fix_sz @@ -293,7 +433,7 @@ copy_to_sram: bne copy_to_sram ldr r1, sram_base blx r1 - b omap3_restore + b omap3_restore @ Fall through to OMAP3 common code ENDPROC(omap3_restore_es3) ENTRY(omap3_restore_3630) @@ -301,7 +441,7 @@ ENTRY(omap3_restore_3630) ldr r2, [r1] and r2, r2, #0x3 cmp r2, #0x0 @ Check if previous power state of CORE is OFF - bne omap3_restore + bne omap3_restore @ Fall through to OMAP3 common code /* Disable RTA before giving control */ ldr r1, control_mem_rta mov r2, #OMAP36XX_RTA_DISABLE @@ -404,11 +544,32 @@ ENDPROC(omap3_restore) .ltorg +/* + * Local variables + */ +pm_prepwstst_core_p: + .word PM_PREPWSTST_CORE_P +pm_pwstctrl_mpu: + .word PM_PWSTCTRL_MPU_P +scratchpad_base: + .word SCRATCHPAD_BASE_P +sram_base: + .word SRAM_BASE_P + 0x8000 +control_stat: + .word CONTROL_STAT +control_mem_rta: + .word CONTROL_MEM_RTA_CTRL +l2dis_3630: + .word 0 + /* * Internal functions */ -/* This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0 */ +/* + * This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0 + * Copied to and run from SRAM in order to reconfigure the SDRC parameters. + */ .text .align 3 ENTRY(es3_sdrc_fix) @@ -438,6 +599,9 @@ ENTRY(es3_sdrc_fix) str r5, [r4] @ kick off refreshes bx lr +/* + * Local variables + */ .align sdrc_syscfg: .word SDRC_SYSCONFIG_P @@ -456,120 +620,3 @@ sdrc_manual_1: ENDPROC(es3_sdrc_fix) ENTRY(es3_sdrc_fix_sz) .word . - es3_sdrc_fix - -/* - * This function implements the erratum ID i581 WA: - * SDRC state restore before accessing the SDRAM - * - * Only used at return from non-OFF mode. For OFF - * mode the ROM code configures the SDRC and - * the DPLL before calling the restore code directly - * from DDR. - */ - -/* Make sure SDRC accesses are ok */ -wait_sdrc_ok: - -/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */ - ldr r4, cm_idlest_ckgen -wait_dpll3_lock: - ldr r5, [r4] - tst r5, #1 - beq wait_dpll3_lock - - ldr r4, cm_idlest1_core -wait_sdrc_ready: - ldr r5, [r4] - tst r5, #0x2 - bne wait_sdrc_ready - /* allow DLL powerdown upon hw idle req */ - ldr r4, sdrc_power - ldr r5, [r4] - bic r5, r5, #0x40 - str r5, [r4] - -/* - * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a - * base instead. - * Be careful not to clobber r7 when maintaing this code. - */ - -is_dll_in_lock_mode: - /* Is dll in lock mode? */ - ldr r4, sdrc_dlla_ctrl - ldr r5, [r4] - tst r5, #0x4 - bxne lr @ Return if locked - /* wait till dll locks */ - adr r7, kick_counter -wait_dll_lock_timed: - ldr r4, wait_dll_lock_counter - add r4, r4, #1 - str r4, [r7, #wait_dll_lock_counter - kick_counter] - ldr r4, sdrc_dlla_status - /* Wait 20uS for lock */ - mov r6, #8 -wait_dll_lock: - subs r6, r6, #0x1 - beq kick_dll - ldr r5, [r4] - and r5, r5, #0x4 - cmp r5, #0x4 - bne wait_dll_lock - bx lr @ Return when locked - - /* disable/reenable DLL if not locked */ -kick_dll: - ldr r4, sdrc_dlla_ctrl - ldr r5, [r4] - mov r6, r5 - bic r6, #(1<<3) @ disable dll - str r6, [r4] - dsb - orr r6, r6, #(1<<3) @ enable dll - str r6, [r4] - dsb - ldr r4, kick_counter - add r4, r4, #1 - str r4, [r7] @ kick_counter - b wait_dll_lock_timed - - .align -cm_idlest1_core: - .word CM_IDLEST1_CORE_V -cm_idlest_ckgen: - .word CM_IDLEST_CKGEN_V -sdrc_dlla_status: - .word SDRC_DLLA_STATUS_V -sdrc_dlla_ctrl: - .word SDRC_DLLA_CTRL_V -pm_prepwstst_core_p: - .word PM_PREPWSTST_CORE_P -pm_pwstctrl_mpu: - .word PM_PWSTCTRL_MPU_P -scratchpad_base: - .word SCRATCHPAD_BASE_P -sram_base: - .word SRAM_BASE_P + 0x8000 -sdrc_power: - .word SDRC_POWER_V -control_stat: - .word CONTROL_STAT -control_mem_rta: - .word CONTROL_MEM_RTA_CTRL -kernel_flush: - .word v7_flush_dcache_all -l2dis_3630: - .word 0 - /* - * When exporting to userspace while the counters are in SRAM, - * these 2 words need to be at the end to facilitate retrival! - */ -kick_counter: - .word 0 -wait_dll_lock_counter: - .word 0 -ENDPROC(omap34xx_cpu_suspend) - -ENTRY(omap34xx_cpu_suspend_sz) - .word . - omap34xx_cpu_suspend diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c index 6af3d0b1f8d0..363c91e44efb 100644 --- a/arch/arm/plat-omap/sram.c +++ b/arch/arm/plat-omap/sram.c @@ -394,20 +394,15 @@ void omap3_sram_restore_context(void) } #endif /* CONFIG_PM */ -static int __init omap34xx_sram_init(void) -{ - _omap3_sram_configure_core_dpll = - omap_sram_push(omap3_sram_configure_core_dpll, - omap3_sram_configure_core_dpll_sz); - omap_push_sram_idle(); - return 0; -} -#else +#endif /* CONFIG_ARCH_OMAP3 */ + static inline int omap34xx_sram_init(void) { +#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM) + omap3_sram_restore_context(); +#endif return 0; } -#endif int __init omap_sram_init(void) { -- cgit v1.2.3 From cbe263497def23befb6f475977661bae5d1f82e4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 30 Jun 2011 08:45:49 +0100 Subject: ARM: pm: omap3: move saving of the auxiliary control registers to C Move the saving of the auxiliary control registers into C; there's no need for this to be in assembly code. This results in less assembly code to deal with in OMAP. Kevin tested full-chip retention and off on 3430/n900, 3530/Overo and 3630/Zoom3. Tested-by: Kevin Hilman Signed-off-by: Russell King --- arch/arm/mach-omap2/pm.h | 2 +- arch/arm/mach-omap2/pm34xx.c | 19 ++++++++++++++++++- arch/arm/mach-omap2/sleep34xx.S | 12 ++---------- 3 files changed, 21 insertions(+), 12 deletions(-) diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h index a4ec213e30c0..04ee56646126 100644 --- a/arch/arm/mach-omap2/pm.h +++ b/arch/arm/mach-omap2/pm.h @@ -97,7 +97,7 @@ extern void omap24xx_cpu_suspend(u32 dll_ctrl, void __iomem *sdrc_dlla_ctrl, extern unsigned int omap24xx_cpu_suspend_sz; /* 3xxx */ -extern void omap34xx_cpu_suspend(u32 *addr, int save_state); +extern void omap34xx_cpu_suspend(int save_state); /* omap3_do_wfi function pointer and size, for copy to SRAM */ extern void omap3_do_wfi(void); diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index e1c79bae7670..7238a63e24e2 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -306,9 +306,24 @@ static irqreturn_t prcm_interrupt_handler (int irq, void *dev_id) return IRQ_HANDLED; } +static void omap34xx_save_context(u32 *save) +{ + u32 val; + + /* Read Auxiliary Control Register */ + asm("mrc p15, 0, %0, c1, c0, 1" : "=r" (val)); + *save++ = 1; + *save++ = val; + + /* Read L2 AUX ctrl register */ + asm("mrc p15, 1, %0, c9, c0, 2" : "=r" (val)); + *save++ = 1; + *save++ = val; +} + static void omap34xx_do_sram_idle(unsigned long save_state) { - omap34xx_cpu_suspend(omap3_arm_context, save_state); + omap34xx_cpu_suspend(save_state); } void omap_sram_idle(void) @@ -408,6 +423,8 @@ void omap_sram_idle(void) * get saved. The rest is placed on the stack, and restored * from there before resuming. */ + if (save_state) + omap34xx_save_context(omap3_arm_context); if (save_state == 1 || save_state == 3) cpu_suspend(save_state, omap34xx_do_sram_idle); else diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 17dbc5af6915..f2ea1bd1c691 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -152,8 +152,7 @@ ENTRY(omap34xx_cpu_suspend) stmfd sp!, {r4 - r11, lr} @ save registers on stack /* - * r0 contains CPU context save/restore pointer in sdram - * r1 contains information about saving context: + * r0 contains information about saving context: * 0 - No context lost * 1 - Only L1 and logic lost * 2 - Only L2 lost (Even L1 is retained we clean it along with L2) @@ -166,19 +165,12 @@ ENTRY(omap34xx_cpu_suspend) */ ldr r4, omap3_do_wfi_sram_addr ldr r5, [r4] - cmp r1, #0x0 @ If no context save required, + cmp r0, #0x0 @ If no context save required, bxeq r5 @ jump to the WFI code in SRAM /* Otherwise fall through to the save context code */ save_context_wfi: - mov r8, r0 @ Store SDRAM address in r8 - mrc p15, 0, r5, c1, c0, 1 @ Read Auxiliary Control Register - mov r4, #0x1 @ Number of parameters for restore call - stmia r8!, {r4-r5} @ Push parameters for restore call - mrc p15, 1, r5, c9, c0, 2 @ Read L2 AUX ctrl register - stmia r8!, {r4-r5} @ Push parameters for restore call - /* * jump out to kernel flush routine * - reuse that code is better -- cgit v1.2.3 From b059bdc39321696fe8f344acb7117d57fbd7b475 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 15:44:20 +0100 Subject: ARM: entry: rejig register allocation in exception entry handlers This allows us to avoid moving registers twice to work around the clobbered registers when we add calls to trace_hardirqs_{on,off}. Ensure that all SVC handlers return with SPSR in r5 for consistency. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 81 +++++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 38 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index fd42e667a81b..582bb2310446 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -45,7 +45,7 @@ .endm .macro pabt_helper - mov r0, r2 @ pass address of aborted instruction. + mov r0, r4 @ pass address of aborted instruction. #ifdef MULTI_PABORT ldr ip, .LCprocfns mov lr, pc @@ -56,6 +56,8 @@ .endm .macro dabt_helper + mov r2, r4 + mov r3, r5 @ @ Call the processor-specific abort handler: @@ -157,26 +159,26 @@ ENDPROC(__und_invalid) SPFIX( subeq sp, sp, #4 ) stmia sp, {r1 - r12} - ldmia r0, {r1 - r3} - add r5, sp, #S_SP - 4 @ here for interlock avoidance - mov r4, #-1 @ "" "" "" "" - add r0, sp, #(S_FRAME_SIZE + \stack_hole - 4) - SPFIX( addeq r0, r0, #4 ) - str r1, [sp, #-4]! @ save the "real" r0 copied + 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) + SPFIX( addeq r2, r2, #4 ) + str r3, [sp, #-4]! @ save the "real" r0 copied @ from the exception stack - mov r1, lr + mov r3, lr @ @ We are now ready to fill in the remaining blanks on the stack: @ - @ r0 - sp_svc - @ r1 - lr_svc - @ r2 - lr_, already fixed up for correct return/restart - @ r3 - spsr_ - @ r4 - orig_r0 (see pt_regs definition in ptrace.h) + @ r2 - sp_svc + @ r3 - lr_svc + @ r4 - lr_, already fixed up for correct return/restart + @ r5 - spsr_ + @ r6 - orig_r0 (see pt_regs definition in ptrace.h) @ - stmia r5, {r0 - r4} + stmia r7, {r2 - r6} .endm .align 5 @@ -187,7 +189,7 @@ __dabt_svc: @ get ready to re-enable interrupts if appropriate @ mrs r9, cpsr - tst r3, #PSR_I_BIT + tst r5, #PSR_I_BIT biceq r9, r9, #PSR_I_BIT dabt_helper @@ -208,8 +210,8 @@ __dabt_svc: @ @ restore SPSR and restart the instruction @ - ldr r2, [sp, #S_PSR] - svc_exit r2 @ return from exception + ldr r5, [sp, #S_PSR] + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) @@ -232,13 +234,13 @@ __irq_svc: tst r0, #_TIF_NEED_RESCHED blne svc_preempt #endif - ldr r4, [sp, #S_PSR] @ irqs are already disabled + ldr r5, [sp, #S_PSR] #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 - svc_exit r4 @ return from exception + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__irq_svc) @@ -273,15 +275,16 @@ __und_svc: @ r0 - instruction @ #ifndef CONFIG_THUMB2_KERNEL - ldr r0, [r2, #-4] + ldr r0, [r4, #-4] #else - ldrh r0, [r2, #-2] @ Thumb instruction at LR - 2 + ldrh r0, [r4, #-2] @ Thumb instruction at LR - 2 and r9, r0, #0xf800 cmp r9, #0xe800 @ 32-bit instruction if xx >= 0 - ldrhhs r9, [r2] @ bottom 16 bits + ldrhhs r9, [r4] @ bottom 16 bits orrhs r0, r9, r0, lsl #16 #endif adr r9, BSYM(1f) + mov r2, r4 bl call_fpe mov r0, sp @ struct pt_regs *regs @@ -295,8 +298,8 @@ __und_svc: @ @ restore SPSR and restart the instruction @ - ldr r2, [sp, #S_PSR] @ Get SVC cpsr - svc_exit r2 @ return from exception + ldr r5, [sp, #S_PSR] @ Get SVC cpsr + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__und_svc) @@ -308,7 +311,7 @@ __pabt_svc: @ re-enable interrupts if appropriate @ mrs r9, cpsr - tst r3, #PSR_I_BIT + tst r5, #PSR_I_BIT biceq r9, r9, #PSR_I_BIT pabt_helper @@ -325,8 +328,8 @@ __pabt_svc: @ @ restore SPSR and restart the instruction @ - ldr r2, [sp, #S_PSR] - svc_exit r2 @ return from exception + ldr r5, [sp, #S_PSR] + svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__pabt_svc) @@ -357,23 +360,23 @@ ENDPROC(__pabt_svc) ARM( stmib sp, {r1 - r12} ) THUMB( stmia sp, {r0 - r12} ) - ldmia r0, {r1 - r3} + ldmia r0, {r3 - r5} add r0, sp, #S_PC @ here for interlock avoidance - mov r4, #-1 @ "" "" "" "" + mov r6, #-1 @ "" "" "" "" - str r1, [sp] @ save the "real" r0 copied + str r3, [sp] @ save the "real" r0 copied @ from the exception stack @ @ We are now ready to fill in the remaining blanks on the stack: @ - @ r2 - lr_, already fixed up for correct return/restart - @ r3 - spsr_ - @ r4 - orig_r0 (see pt_regs definition in ptrace.h) + @ r4 - lr_, already fixed up for correct return/restart + @ r5 - spsr_ + @ r6 - orig_r0 (see pt_regs definition in ptrace.h) @ @ Also, separately save sp_usr and lr_usr @ - stmia r0, {r2 - r4} + stmia r0, {r4 - r6} ARM( stmdb r0, {sp, lr}^ ) THUMB( store_user_sp_lr r0, r1, S_SP - S_PC ) @@ -397,7 +400,7 @@ ENDPROC(__pabt_svc) @ if it was interrupted in a critical region. Here we @ 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 + cmp r4, #TASK_SIZE blhs kuser_cmpxchg_fixup #endif #endif @@ -441,6 +444,8 @@ ENDPROC(__irq_usr) .align 5 __und_usr: usr_entry + mov r2, r4 + mov r3, r5 @ @ fall through to the emulation code, which returns using r9 if @@ -894,13 +899,13 @@ __kuser_cmpxchg: @ 0xffff0fc0 .text kuser_cmpxchg_fixup: @ Called from kuser_cmpxchg_check macro. - @ r2 = address of interrupted insn (must be preserved). + @ r4 = 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. + @ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b. mov r7, #0xffff0fff sub r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg))) - subs r8, r2, r7 + subs r8, r4, r7 rsbcss r8, r8, #(2b - 1b) strcs r7, [sp, #S_PC] mov pc, lr -- cgit v1.2.3 From 8b4186160b7894ca4583f702a562856d5d9e9118 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 19:25:02 +0100 Subject: ARM: entry: prefetch abort helper: pass aborted pc in r4 rather than r0 This avoids unnecessary instructions for CPUs which implement the IFAR (instruction fault address register). Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 2 +- arch/arm/mm/pabort-legacy.S | 3 ++- arch/arm/mm/pabort-v6.S | 3 ++- arch/arm/mm/pabort-v7.S | 2 +- 4 files changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 582bb2310446..d644d0240ad3 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -45,7 +45,7 @@ .endm .macro pabt_helper - mov r0, r4 @ pass address of aborted instruction. + @ PABORT handler takes fault address in r4 #ifdef MULTI_PABORT ldr ip, .LCprocfns mov lr, pc diff --git a/arch/arm/mm/pabort-legacy.S b/arch/arm/mm/pabort-legacy.S index 87970eba88ea..8a5d8aaf2d5e 100644 --- a/arch/arm/mm/pabort-legacy.S +++ b/arch/arm/mm/pabort-legacy.S @@ -4,7 +4,7 @@ /* * Function: legacy_pabort * - * Params : r0 = address of aborted instruction + * Params : r4 = address of aborted instruction * * Returns : r0 = address of abort * : r1 = Simulated IFSR with section translation fault status @@ -14,6 +14,7 @@ .align 5 ENTRY(legacy_pabort) + mov r0, r4 mov r1, #5 mov pc, lr ENDPROC(legacy_pabort) diff --git a/arch/arm/mm/pabort-v6.S b/arch/arm/mm/pabort-v6.S index 06e3d1ef2115..eaac1cb7c4cc 100644 --- a/arch/arm/mm/pabort-v6.S +++ b/arch/arm/mm/pabort-v6.S @@ -4,7 +4,7 @@ /* * Function: v6_pabort * - * Params : r0 = address of aborted instruction + * Params : r4 = address of aborted instruction * * Returns : r0 = address of abort * : r1 = IFSR @@ -14,6 +14,7 @@ .align 5 ENTRY(v6_pabort) + mov r0, r4 mrc p15, 0, r1, c5, c0, 1 @ get IFSR mov pc, lr ENDPROC(v6_pabort) diff --git a/arch/arm/mm/pabort-v7.S b/arch/arm/mm/pabort-v7.S index a8b3b300a18d..b515e0b059b3 100644 --- a/arch/arm/mm/pabort-v7.S +++ b/arch/arm/mm/pabort-v7.S @@ -4,7 +4,7 @@ /* * Function: v6_pabort * - * Params : r0 = address of aborted instruction + * Params : r4 = address of aborted instruction * * Returns : r0 = address of abort * : r1 = IFSR -- cgit v1.2.3 From 29cb3cd208dd0e4471bb80bec4facc49ceb199fa Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 2 Jul 2011 09:54:01 +0100 Subject: ARM: pm: allow suspend finisher to return error codes There are SoCs where attempting to enter a low power state is ignored, and the CPU continues executing instructions with all state preserved. It is over-complex at that point to disable the MMU just to call the resume path. Instead, allow the suspend finisher to return error codes to abort suspend in this circumstance, where the cpu_suspend internals will then unwind the saved state on the stack. Also omit the tlb flush as no changes to the page tables will have happened. Signed-off-by: Russell King --- arch/arm/include/asm/suspend.h | 9 +++++---- arch/arm/kernel/sleep.S | 11 +++++++++-- arch/arm/mach-exynos4/pm.c | 2 +- arch/arm/mach-omap2/pm34xx.c | 3 ++- arch/arm/mach-pxa/include/mach/pm.h | 4 ++-- arch/arm/mach-pxa/pxa3xx.c | 2 +- arch/arm/mach-s3c2412/pm.c | 4 +++- arch/arm/mach-s3c2416/pm.c | 4 +++- arch/arm/mach-s3c64xx/pm.c | 2 +- arch/arm/mach-sa1100/pm.c | 2 +- arch/arm/plat-samsung/include/plat/pm.h | 4 ++-- arch/arm/plat-samsung/pm.c | 2 +- 12 files changed, 31 insertions(+), 18 deletions(-) diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h index f8db9d096bc7..b0e4e1a02318 100644 --- a/arch/arm/include/asm/suspend.h +++ b/arch/arm/include/asm/suspend.h @@ -10,12 +10,13 @@ extern void cpu_resume(void); * Hide the first two arguments to __cpu_suspend - these are an implementation * detail which platform code shouldn't have to know about. */ -static inline void cpu_suspend(unsigned long arg, void (*fn)(unsigned long)) +static inline int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { - extern void __cpu_suspend(int, long, unsigned long, - void (*)(unsigned long)); - __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn); + extern int __cpu_suspend(int, long, unsigned long, + int (*)(unsigned long)); + int ret = __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn); flush_tlb_all(); + return ret; } #endif diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index c156d0e5f455..dc902f2c6845 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -12,7 +12,6 @@ * r1 = v:p offset * r2 = suspend function arg0 * r3 = suspend function - * Note: does not return until system resumes */ ENTRY(__cpu_suspend) stmfd sp!, {r4 - r11, lr} @@ -26,7 +25,7 @@ ENTRY(__cpu_suspend) #endif mov r6, sp @ current virtual SP sub sp, sp, r5 @ allocate CPU state on stack - mov r0, sp @ save pointer + mov r0, sp @ save pointer to CPU save block add ip, ip, r1 @ convert resume fn to phys stmfd sp!, {r1, r6, ip} @ save v:p, virt SP, phys resume fn ldr r5, =sleep_save_sp @@ -55,10 +54,17 @@ ENTRY(__cpu_suspend) #else bl __cpuc_flush_kern_all #endif + adr lr, BSYM(cpu_suspend_abort) ldmfd sp!, {r0, pc} @ call suspend fn ENDPROC(__cpu_suspend) .ltorg +cpu_suspend_abort: + ldmia sp!, {r1 - r3} @ pop v:p, virt SP, phys resume fn + mov sp, r2 + ldmfd sp!, {r4 - r11, pc} +ENDPROC(cpu_suspend_abort) + /* * r0 = control register value * r1 = v:p offset (preserved by cpu_do_resume) @@ -89,6 +95,7 @@ cpu_resume_after_mmu: str r5, [r2, r4, lsl #2] @ restore old mapping mcr p15, 0, r0, c1, c0, 0 @ turn on D-cache bl cpu_init @ restore the und/abt/irq banked regs + mov r0, #0 @ return zero on success ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_resume_after_mmu) diff --git a/arch/arm/mach-exynos4/pm.c b/arch/arm/mach-exynos4/pm.c index 5c01c6076645..533c28f758ca 100644 --- a/arch/arm/mach-exynos4/pm.c +++ b/arch/arm/mach-exynos4/pm.c @@ -280,7 +280,7 @@ static struct sleep_save exynos4_l2cc_save[] = { SAVE_ITEM(S5P_VA_L2CC + L2X0_AUX_CTRL), }; -void exynos4_cpu_suspend(unsigned long arg) +static int exynos4_cpu_suspend(unsigned long arg) { unsigned long tmp; unsigned long mask = 0xFFFFFFFF; diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 7238a63e24e2..b77d82665abb 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -321,9 +321,10 @@ static void omap34xx_save_context(u32 *save) *save++ = val; } -static void omap34xx_do_sram_idle(unsigned long save_state) +static int omap34xx_do_sram_idle(unsigned long save_state) { omap34xx_cpu_suspend(save_state); + return 0; } void omap_sram_idle(void) diff --git a/arch/arm/mach-pxa/include/mach/pm.h b/arch/arm/mach-pxa/include/mach/pm.h index a566720527cf..51558bcee999 100644 --- a/arch/arm/mach-pxa/include/mach/pm.h +++ b/arch/arm/mach-pxa/include/mach/pm.h @@ -22,8 +22,8 @@ struct pxa_cpu_pm_fns { extern struct pxa_cpu_pm_fns *pxa_cpu_pm_fns; /* sleep.S */ -extern void pxa25x_finish_suspend(unsigned long); -extern void pxa27x_finish_suspend(unsigned long); +extern int pxa25x_finish_suspend(unsigned long); +extern int pxa27x_finish_suspend(unsigned long); extern int pxa_pm_enter(suspend_state_t state); extern int pxa_pm_prepare(void); diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c index 9fe947b5d5f7..ef1c56a67afc 100644 --- a/arch/arm/mach-pxa/pxa3xx.c +++ b/arch/arm/mach-pxa/pxa3xx.c @@ -148,7 +148,7 @@ static void pxa3xx_cpu_pm_suspend(void) asm volatile("mra %Q0, %R0, acc0" : "=r" (acc0)); #endif - extern void pxa3xx_finish_suspend(unsigned long); + extern int pxa3xx_finish_suspend(unsigned long); /* resuming from D2 requires the HSIO2/BOOT/TPM clocks enabled */ CKENA |= (1 << CKEN_BOOT) | (1 << CKEN_TPM); diff --git a/arch/arm/mach-s3c2412/pm.c b/arch/arm/mach-s3c2412/pm.c index 9a1fb898db53..f4077efa51fa 100644 --- a/arch/arm/mach-s3c2412/pm.c +++ b/arch/arm/mach-s3c2412/pm.c @@ -37,7 +37,7 @@ extern void s3c2412_sleep_enter(void); -static void s3c2412_cpu_suspend(unsigned long arg) +static int s3c2412_cpu_suspend(unsigned long arg) { unsigned long tmp; @@ -48,6 +48,8 @@ static void s3c2412_cpu_suspend(unsigned long arg) __raw_writel(tmp, S3C2412_PWRCFG); s3c2412_sleep_enter(); + + panic("sleep resumed to originator?"); } static void s3c2412_pm_prepare(void) diff --git a/arch/arm/mach-s3c2416/pm.c b/arch/arm/mach-s3c2416/pm.c index 9e67a2a07a86..9ec54f1d8e75 100644 --- a/arch/arm/mach-s3c2416/pm.c +++ b/arch/arm/mach-s3c2416/pm.c @@ -24,7 +24,7 @@ extern void s3c2412_sleep_enter(void); -static void s3c2416_cpu_suspend(unsigned long arg) +static int s3c2416_cpu_suspend(unsigned long arg) { /* enable wakeup sources regardless of battery state */ __raw_writel(S3C2443_PWRCFG_SLEEP, S3C2443_PWRCFG); @@ -33,6 +33,8 @@ static void s3c2416_cpu_suspend(unsigned long arg) __raw_writel(0x2BED, S3C2443_PWRMODE); s3c2412_sleep_enter(); + + panic("sleep resumed to originator?"); } static void s3c2416_pm_prepare(void) diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c index 7cc1879af722..8bad64370689 100644 --- a/arch/arm/mach-s3c64xx/pm.c +++ b/arch/arm/mach-s3c64xx/pm.c @@ -112,7 +112,7 @@ void s3c_pm_save_core(void) * this. */ -static void s3c64xx_cpu_suspend(unsigned long arg) +static int s3c64xx_cpu_suspend(unsigned long arg) { unsigned long tmp; diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index cf9a1e9fb70d..bf85b8b259d5 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -33,7 +33,7 @@ #include #include -extern void sa1100_finish_suspend(unsigned long); +extern int sa1100_finish_suspend(unsigned long); #define SAVE(x) sleep_save[SLEEP_SAVE_##x] = x #define RESTORE(x) x = sleep_save[SLEEP_SAVE_##x] diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h index 0a5b7faca836..f6749916d194 100644 --- a/arch/arm/plat-samsung/include/plat/pm.h +++ b/arch/arm/plat-samsung/include/plat/pm.h @@ -42,7 +42,7 @@ extern unsigned long s3c_irqwake_eintallow; /* per-cpu sleep functions */ extern void (*pm_cpu_prep)(void); -extern void (*pm_cpu_sleep)(unsigned long); +extern int (*pm_cpu_sleep)(unsigned long); /* Flags for PM Control */ @@ -54,7 +54,7 @@ extern unsigned char pm_uart_udivslot; /* true to save UART UDIVSLOT */ extern void s3c_cpu_resume(void); -extern void s3c2410_cpu_suspend(unsigned long); +extern int s3c2410_cpu_suspend(unsigned long); /* sleep save info */ diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c index 69d6b040a019..5fa1742d019b 100644 --- a/arch/arm/plat-samsung/pm.c +++ b/arch/arm/plat-samsung/pm.c @@ -232,7 +232,7 @@ static void __maybe_unused s3c_pm_show_resume_irqs(int start, void (*pm_cpu_prep)(void); -void (*pm_cpu_sleep)(unsigned long); +int (*pm_cpu_sleep)(unsigned long); #define any_allowed(mask, allow) (((mask) & (allow)) != (allow)) -- cgit v1.2.3 From 02fe2845d6a837ab02f0738f6cf4591a02cc88d4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 11:44:06 +0100 Subject: ARM: entry: avoid enabling interrupts in prefetch/data abort handlers Avoid enabling interrupts if the parent context had interrupts enabled in the abort handler assembly code, and move this into the breakpoint/ page/alignment fault handlers instead. This gets rid of some special-casing for the breakpoint fault handlers from the low level abort handler path. Acked-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 43 ++++++++++++++++++----------------------- arch/arm/kernel/entry-header.S | 19 ------------------ arch/arm/kernel/hw_breakpoint.c | 12 +++++------- arch/arm/mm/alignment.c | 3 +++ arch/arm/mm/fault.c | 4 ++++ 5 files changed, 31 insertions(+), 50 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index d644d0240ad3..c46bafa2f6dc 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -185,20 +185,15 @@ ENDPROC(__und_invalid) __dabt_svc: svc_entry - @ - @ get ready to re-enable interrupts if appropriate - @ - mrs r9, cpsr - tst r5, #PSR_I_BIT - biceq r9, r9, #PSR_I_BIT +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif dabt_helper @ - @ set desired IRQ state, then call main handler + @ call main handler @ - debug_entry r1 - msr cpsr_c, r9 mov r2, sp bl do_DataAbort @@ -211,6 +206,12 @@ __dabt_svc: @ restore SPSR and restart the instruction @ ldr r5, [sp, #S_PSR] +#ifdef CONFIG_TRACE_IRQFLAGS + tst r5, #PSR_I_BIT + bleq trace_hardirqs_on + tst r5, #PSR_I_BIT + blne trace_hardirqs_off +#endif svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) @@ -307,16 +308,11 @@ ENDPROC(__und_svc) __pabt_svc: svc_entry - @ - @ re-enable interrupts if appropriate - @ - mrs r9, cpsr - tst r5, #PSR_I_BIT - biceq r9, r9, #PSR_I_BIT +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif pabt_helper - debug_entry r1 - msr cpsr_c, r9 @ Maybe enable interrupts mov r2, sp @ regs bl do_PrefetchAbort @ call abort handler @@ -329,6 +325,12 @@ __pabt_svc: @ restore SPSR and restart the instruction @ ldr r5, [sp, #S_PSR] +#ifdef CONFIG_TRACE_IRQFLAGS + tst r5, #PSR_I_BIT + bleq trace_hardirqs_on + tst r5, #PSR_I_BIT + blne trace_hardirqs_off +#endif svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__pabt_svc) @@ -412,11 +414,6 @@ __dabt_usr: kuser_cmpxchg_check dabt_helper - @ - @ IRQs on, then call the main handler - @ - debug_entry r1 - enable_irq mov r2, sp adr lr, BSYM(ret_from_exception) b do_DataAbort @@ -663,8 +660,6 @@ ENDPROC(__und_usr_unknown) __pabt_usr: usr_entry pabt_helper - debug_entry r1 - enable_irq @ Enable interrupts mov r2, sp @ regs bl do_PrefetchAbort @ call abort handler UNWIND(.fnend ) diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 051166c2a932..4d6ad8348e89 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -165,25 +165,6 @@ .endm #endif /* !CONFIG_THUMB2_KERNEL */ - @ - @ Debug exceptions are taken as prefetch or data aborts. - @ We must disable preemption during the handler so that - @ we can access the debug registers safely. - @ - .macro debug_entry, fsr -#if defined(CONFIG_HAVE_HW_BREAKPOINT) && defined(CONFIG_PREEMPT) - ldr r4, =0x40f @ mask out fsr.fs - and r5, r4, \fsr - cmp r5, #2 @ debug exception - bne 1f - get_thread_info r10 - ldr r6, [r10, #TI_PREEMPT] @ get preempt count - add r11, r6, #1 @ increment it - str r11, [r10, #TI_PREEMPT] -1: -#endif - .endm - /* * These are the registers used in the syscall handler, and allow us to * have in theory up to 7 arguments to a function - r0 to r6. diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 87acc25d7a3e..a927ca1f5566 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -796,7 +796,7 @@ unlock: /* * Called from either the Data Abort Handler [watchpoint] or the - * Prefetch Abort Handler [breakpoint] with preemption disabled. + * Prefetch Abort Handler [breakpoint] with interrupts disabled. */ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, struct pt_regs *regs) @@ -804,8 +804,10 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, int ret = 0; u32 dscr; - /* We must be called with preemption disabled. */ - WARN_ON(preemptible()); + preempt_disable(); + + if (interrupts_enabled(regs)) + local_irq_enable(); /* We only handle watchpoints and hardware breakpoints. */ ARM_DBG_READ(c1, 0, dscr); @@ -824,10 +826,6 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, ret = 1; /* Unhandled fault. */ } - /* - * Re-enable preemption after it was disabled in the - * low-level exception handling code. - */ preempt_enable(); return ret; diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 724ba3bce72c..be7c638b648b 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -727,6 +727,9 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) int isize = 4; int thumb2_32b = 0; + if (interrupts_enabled(regs)) + local_irq_enable(); + instrptr = instruction_pointer(regs); fs = get_fs(); diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index bc0e1d88fd3b..20e5d5120609 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -285,6 +285,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) tsk = current; mm = tsk->mm; + /* Enable interrupts if they were enabled in the parent context. */ + if (interrupts_enabled(regs)) + local_irq_enable(); + /* * If we're in an interrupt or have no user * context, we must not take the fault.. -- cgit v1.2.3 From df295df6c391e322a06dea0d2bc3d22debd15fb9 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 16:55:58 +0100 Subject: ARM: entry: instrument svc undefined exception handler with irqtrace Add irqtrace function calls to the undefined exception handler, so that we get sane lockdep traces from locking problems in undefined exception handlers. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index c46bafa2f6dc..920dd3d07957 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -268,6 +268,10 @@ __und_svc: svc_entry #endif +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif + @ @ call emulation code, which returns using r9 if it has emulated @ the instruction, or the more conventional lr if we are to treat @@ -300,6 +304,12 @@ __und_svc: @ restore SPSR and restart the instruction @ ldr r5, [sp, #S_PSR] @ Get SVC cpsr +#ifdef CONFIG_TRACE_IRQFLAGS + tst r5, #PSR_I_BIT + bleq trace_hardirqs_on + tst r5, #PSR_I_BIT + blne trace_hardirqs_off +#endif svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__und_svc) -- cgit v1.2.3 From bc089602d206b2abc2d2e8e5324d90342cc0447b Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 18:28:19 +0100 Subject: ARM: entry: instrument usr exception handlers with irqsoff tracing As we no longer re-enable interrupts in these exception handlers, add the irqsoff tracing calls to them so that the kernel tracks the state more accurately. Note that these calls are conditional on IRQSOFF_TRACER: kernel ----------> user ---------> kernel ^ irqs enabled ^ irqs disabled No kernel code can run on the local CPU until we've re-entered the kernel through one of the exception handlers - and userspace can not take any locks etc. So, the kernel doesn't care about the IRQ mask state while userspace is running unless we're doing IRQ off latency tracing. So, we can (and do) avoid the overhead of updating the IRQ mask state on every kernel->user and user->kernel transition. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 920dd3d07957..f863ee79093e 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -421,6 +421,11 @@ ENDPROC(__pabt_svc) .align 5 __dabt_usr: usr_entry + +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif + kuser_cmpxchg_check dabt_helper @@ -433,12 +438,12 @@ ENDPROC(__dabt_usr) .align 5 __irq_usr: usr_entry - kuser_cmpxchg_check #ifdef CONFIG_IRQSOFF_TRACER bl trace_hardirqs_off #endif + kuser_cmpxchg_check irq_handler get_thread_info tsk mov why, #0 @@ -451,6 +456,11 @@ ENDPROC(__irq_usr) .align 5 __und_usr: usr_entry + +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif + mov r2, r4 mov r3, r5 @@ -669,6 +679,11 @@ ENDPROC(__und_usr_unknown) .align 5 __pabt_usr: usr_entry + +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif + pabt_helper mov r2, sp @ regs bl do_PrefetchAbort @ call abort handler -- cgit v1.2.3 From f2741b78b607576f0c256604cb3d9256b3428a32 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 25 Jun 2011 17:35:19 +0100 Subject: ARM: entry: consolidate trace_hardirqs_off into (svc|usr)_entry macros All handlers now call trace_hardirqs_off, so move this common code into the (svc|usr)_entry assembler macros. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 47 ++++++++------------------------------------ 1 file changed, 8 insertions(+), 39 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index f863ee79093e..a5b2c40d44e8 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -179,16 +179,15 @@ ENDPROC(__und_invalid) @ r6 - orig_r0 (see pt_regs definition in ptrace.h) @ stmia r7, {r2 - r6} - .endm - - .align 5 -__dabt_svc: - svc_entry #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif + .endm + .align 5 +__dabt_svc: + svc_entry dabt_helper @ @@ -219,11 +218,6 @@ ENDPROC(__dabt_svc) .align 5 __irq_svc: svc_entry - -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - irq_handler #ifdef CONFIG_PREEMPT @@ -267,11 +261,6 @@ __und_svc: #else svc_entry #endif - -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - @ @ call emulation code, which returns using r9 if it has emulated @ the instruction, or the more conventional lr if we are to treat @@ -317,11 +306,6 @@ ENDPROC(__und_svc) .align 5 __pabt_svc: svc_entry - -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - pabt_helper mov r2, sp @ regs bl do_PrefetchAbort @ call abort handler @@ -401,6 +385,10 @@ ENDPROC(__pabt_svc) @ Clear FP to mark the first stack frame @ zero_fp + +#ifdef CONFIG_IRQSOFF_TRACER + bl trace_hardirqs_off +#endif .endm .macro kuser_cmpxchg_check @@ -421,11 +409,6 @@ ENDPROC(__pabt_svc) .align 5 __dabt_usr: usr_entry - -#ifdef CONFIG_IRQSOFF_TRACER - bl trace_hardirqs_off -#endif - kuser_cmpxchg_check dabt_helper @@ -438,11 +421,6 @@ ENDPROC(__dabt_usr) .align 5 __irq_usr: usr_entry - -#ifdef CONFIG_IRQSOFF_TRACER - bl trace_hardirqs_off -#endif - kuser_cmpxchg_check irq_handler get_thread_info tsk @@ -457,10 +435,6 @@ ENDPROC(__irq_usr) __und_usr: usr_entry -#ifdef CONFIG_IRQSOFF_TRACER - bl trace_hardirqs_off -#endif - mov r2, r4 mov r3, r5 @@ -679,11 +653,6 @@ ENDPROC(__und_usr_unknown) .align 5 __pabt_usr: usr_entry - -#ifdef CONFIG_IRQSOFF_TRACER - bl trace_hardirqs_off -#endif - pabt_helper mov r2, sp @ regs bl do_PrefetchAbort @ call abort handler -- cgit v1.2.3 From d9600c99c549732a501cb727157800623a06175d Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 10:34:02 +0100 Subject: ARM: entry: re-allocate registers in irq entry assembly macros This avoids the irq entry assembly corrupting r5, thereby allowing it to be preserved through to the svc exit code. Signed-off-by: Russell King --- arch/arm/include/asm/entry-macro-multi.S | 14 +++++++------- arch/arm/kernel/entry-armv.S | 10 +++++----- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S index 2da8547de6d6..2f1e2098dfe7 100644 --- a/arch/arm/include/asm/entry-macro-multi.S +++ b/arch/arm/include/asm/entry-macro-multi.S @@ -4,8 +4,8 @@ * Interrupt handling. Preserves r7, r8, r9 */ .macro arch_irq_handler_default - get_irqnr_preamble r5, lr -1: get_irqnr_and_base r0, r6, r5, lr + get_irqnr_preamble r6, lr +1: get_irqnr_and_base r0, r2, r6, lr movne r1, sp @ @ routine called with r0 = irq number, r1 = struct pt_regs * @@ -17,17 +17,17 @@ /* * XXX * - * this macro assumes that irqstat (r6) and base (r5) are + * this macro assumes that irqstat (r2) and base (r6) are * preserved from get_irqnr_and_base above */ - ALT_SMP(test_for_ipi r0, r6, r5, lr) + ALT_SMP(test_for_ipi r0, r2, r6, lr) ALT_UP_B(9997f) movne r1, sp adrne lr, BSYM(1b) bne do_IPI #ifdef CONFIG_LOCAL_TIMERS - test_for_ltirq r0, r6, r5, lr + test_for_ltirq r0, r2, r6, lr movne r0, sp adrne lr, BSYM(1b) bne do_local_timer @@ -40,7 +40,7 @@ .align 5 .global \symbol_name \symbol_name: - mov r4, lr + mov r8, lr arch_irq_handler_default - mov pc, r4 + mov pc, r8 .endm diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index a5b2c40d44e8..b17e57949d3b 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -29,16 +29,16 @@ #include /* - * Interrupt handling. Preserves r7, r8, r9 + * Interrupt handling. */ .macro irq_handler #ifdef CONFIG_MULTI_IRQ_HANDLER - ldr r5, =handle_arch_irq + ldr r1, =handle_arch_irq mov r0, sp - ldr r5, [r5] + ldr r1, [r1] adr lr, BSYM(9997f) - teq r5, #0 - movne pc, r5 + teq r1, #0 + movne pc, r1 #endif arch_irq_handler_default 9997: -- cgit v1.2.3 From 8dfe7ac96fedd4f5219879f63a8a546a33609daf Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 12:37:35 +0100 Subject: ARM: entry: prefetch abort: tail-call the main prefetch abort handler Tail-call the main C prefetch abort handler code from the per-CPU helper code. Also note that the helper function becomes ABI compliant in terms of the registers preserved. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 8 +++----- arch/arm/mm/pabort-legacy.S | 9 +++++---- arch/arm/mm/pabort-v6.S | 9 +++++---- arch/arm/mm/pabort-v7.S | 11 ++++++----- 4 files changed, 19 insertions(+), 18 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index b17e57949d3b..af2fba7a4cae 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -45,7 +45,7 @@ .endm .macro pabt_helper - @ PABORT handler takes fault address in r4 + @ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5 #ifdef MULTI_PABORT ldr ip, .LCprocfns mov lr, pc @@ -306,9 +306,8 @@ ENDPROC(__und_svc) .align 5 __pabt_svc: svc_entry - pabt_helper mov r2, sp @ regs - bl do_PrefetchAbort @ call abort handler + pabt_helper @ @ IRQs off again before pulling preserved data off the stack @@ -653,9 +652,8 @@ ENDPROC(__und_usr_unknown) .align 5 __pabt_usr: usr_entry - pabt_helper mov r2, sp @ regs - bl do_PrefetchAbort @ call abort handler + pabt_helper UNWIND(.fnend ) /* fall through */ /* diff --git a/arch/arm/mm/pabort-legacy.S b/arch/arm/mm/pabort-legacy.S index 8a5d8aaf2d5e..8bbff025269a 100644 --- a/arch/arm/mm/pabort-legacy.S +++ b/arch/arm/mm/pabort-legacy.S @@ -4,10 +4,11 @@ /* * Function: legacy_pabort * - * Params : r4 = address of aborted instruction + * Params : r2 = pt_regs + * : r4 = address of aborted instruction + * : r5 = psr for parent context * - * Returns : r0 = address of abort - * : r1 = Simulated IFSR with section translation fault status + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current prefetch abort. */ @@ -16,5 +17,5 @@ ENTRY(legacy_pabort) mov r0, r4 mov r1, #5 - mov pc, lr + b do_PrefetchAbort ENDPROC(legacy_pabort) diff --git a/arch/arm/mm/pabort-v6.S b/arch/arm/mm/pabort-v6.S index eaac1cb7c4cc..9627646ce783 100644 --- a/arch/arm/mm/pabort-v6.S +++ b/arch/arm/mm/pabort-v6.S @@ -4,10 +4,11 @@ /* * Function: v6_pabort * - * Params : r4 = address of aborted instruction + * Params : r2 = pt_regs + * : r4 = address of aborted instruction + * : r5 = psr for parent context * - * Returns : r0 = address of abort - * : r1 = IFSR + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current prefetch abort. */ @@ -16,5 +17,5 @@ ENTRY(v6_pabort) mov r0, r4 mrc p15, 0, r1, c5, c0, 1 @ get IFSR - mov pc, lr + b do_PrefetchAbort ENDPROC(v6_pabort) diff --git a/arch/arm/mm/pabort-v7.S b/arch/arm/mm/pabort-v7.S index b515e0b059b3..875761f44f3b 100644 --- a/arch/arm/mm/pabort-v7.S +++ b/arch/arm/mm/pabort-v7.S @@ -2,12 +2,13 @@ #include /* - * Function: v6_pabort + * Function: v7_pabort * - * Params : r4 = address of aborted instruction + * Params : r2 = pt_regs + * : r4 = address of aborted instruction + * : r5 = psr for parent context * - * Returns : r0 = address of abort - * : r1 = IFSR + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current prefetch abort. */ @@ -16,5 +17,5 @@ ENTRY(v7_pabort) mrc p15, 0, r0, c6, c0, 2 @ get IFAR mrc p15, 0, r1, c5, c0, 1 @ get IFSR - mov pc, lr + b do_PrefetchAbort ENDPROC(v7_pabort) -- cgit v1.2.3 From 3e287bec6fde088bff05ee7f998f53e8ac75b922 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 14:35:07 +0100 Subject: ARM: entry: data abort: arrange for CPU abort helpers to take pc/psr in r4/r5 Re-jig the CPU abort helpers to take the PC/PSR in r4/r5 rather than r2/r3. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 6 ++---- arch/arm/mm/abort-ev4.S | 8 +++----- arch/arm/mm/abort-ev4t.S | 8 ++++---- arch/arm/mm/abort-ev5t.S | 8 ++++---- arch/arm/mm/abort-ev5tj.S | 12 +++++------- arch/arm/mm/abort-ev6.S | 12 +++++------- arch/arm/mm/abort-ev7.S | 4 ++-- arch/arm/mm/abort-lv4t.S | 12 ++++++------ arch/arm/mm/abort-nommu.S | 4 ++-- arch/arm/mm/proc-arm6_7.S | 10 +++++----- 10 files changed, 38 insertions(+), 46 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index af2fba7a4cae..85298c093256 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -56,14 +56,12 @@ .endm .macro dabt_helper - mov r2, r4 - mov r3, r5 @ @ Call the processor-specific abort handler: @ - @ r2 - aborted context pc - @ r3 - aborted context cpsr + @ r4 - aborted context pc + @ r5 - aborted context psr @ @ The abort handler must return the aborted address in r0, and @ the fault status register in r1. r9 must be preserved. diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S index 4f18f9e87bae..beb112bdc049 100644 --- a/arch/arm/mm/abort-ev4.S +++ b/arch/arm/mm/abort-ev4.S @@ -3,8 +3,8 @@ /* * Function: v4_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write @@ -21,10 +21,8 @@ ENTRY(v4_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - ldr r3, [r2] @ read aborted ARM instruction + ldr r3, [r4] @ read aborted ARM instruction 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. mov pc, lr - - diff --git a/arch/arm/mm/abort-ev4t.S b/arch/arm/mm/abort-ev4t.S index 9910123079ce..eaa4ac023959 100644 --- a/arch/arm/mm/abort-ev4t.S +++ b/arch/arm/mm/abort-ev4t.S @@ -4,8 +4,8 @@ /* * Function: v4t_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write @@ -22,8 +22,8 @@ ENTRY(v4t_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 - ldreq r3, [r2] @ read aborted ARM instruction + do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 + ldreq r3, [r4] @ read aborted ARM instruction bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR tst r3, #1 << 20 @ check write orreq r1, r1, #1 << 11 diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S index 800e8d42d39e..97eee7c48019 100644 --- a/arch/arm/mm/abort-ev5t.S +++ b/arch/arm/mm/abort-ev5t.S @@ -4,8 +4,8 @@ /* * Function: v5t_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write @@ -22,8 +22,8 @@ ENTRY(v5t_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 - ldreq r3, [r2] @ read aborted ARM instruction + do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 + ldreq r3, [r4] @ read aborted ARM instruction bic r1, r1, #1 << 11 @ clear bits 11 of FSR do_ldrd_abort tmp=r2, insn=r3 tst r3, #1 << 20 @ check write diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S index bcb58d2fc11a..9a365cf1936f 100644 --- a/arch/arm/mm/abort-ev5tj.S +++ b/arch/arm/mm/abort-ev5tj.S @@ -4,8 +4,8 @@ /* * Function: v5tj_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write @@ -23,13 +23,11 @@ ENTRY(v5tj_early_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR - tst r3, #PSR_J_BIT @ Java? + tst r5, #PSR_J_BIT @ Java? movne pc, lr - do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 - ldreq r3, [r2] @ read aborted ARM instruction + do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 + ldreq r3, [r4] @ read aborted ARM instruction do_ldrd_abort tmp=r2, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. mov pc, lr - - diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index ef526e702a5c..52db4a3fc5f2 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -4,8 +4,8 @@ /* * Function: v6_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write @@ -33,10 +33,10 @@ ENTRY(v6_early_abort) * The test below covers all the write situations, including Java bytecodes */ bic r1, r1, #1 << 11 @ clear bit 11 of FSR - tst r3, #PSR_J_BIT @ Java? + tst r5, #PSR_J_BIT @ Java? movne pc, lr - do_thumb_abort fsr=r1, pc=r2, psr=r3, tmp=r3 - ldreq r3, [r2] @ read aborted ARM instruction + do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 + ldreq r3, [r4] @ read aborted ARM instruction #ifdef CONFIG_CPU_ENDIAN_BE8 reveq r3, r3 #endif @@ -44,5 +44,3 @@ ENTRY(v6_early_abort) tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. mov pc, lr - - diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index ec88b157d3bb..6cb51431a859 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -3,8 +3,8 @@ /* * Function: v7_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index 9fb7b0e25ea1..fea7514225a6 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -3,8 +3,8 @@ /* * Function: v4t_late_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = address of abort * : r1 = FSR, bit 11 = write @@ -18,7 +18,7 @@ * picture. Unfortunately, this does happen. We live with it. */ ENTRY(v4t_late_abort) - tst r3, #PSR_T_BIT @ check for thumb mode + tst r5, #PSR_T_BIT @ check for thumb mode #ifdef CONFIG_CPU_CP15_MMU mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR @@ -28,7 +28,7 @@ ENTRY(v4t_late_abort) mov r1, #0 #endif bne .data_thumb_abort - ldr r8, [r2] @ read arm instruction + ldr r8, [r4] @ read arm instruction tst r8, #1 << 20 @ L = 1 -> write? orreq r1, r1, #1 << 11 @ yes. and r7, r8, #15 << 24 @@ -52,7 +52,7 @@ ENTRY(v4t_late_abort) /* e */ b .data_unknown /* f */ .data_unknown: @ Part of jumptable - mov r0, r2 + mov r0, r4 mov r1, r8 mov r2, sp bl baddataabort @@ -159,7 +159,7 @@ ENTRY(v4t_late_abort) b .data_unknown @ F: MUL? .data_thumb_abort: - ldrh r8, [r2] @ read instruction + ldrh r8, [r4] @ read instruction 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-nommu.S b/arch/arm/mm/abort-nommu.S index 625e580945b5..9eaef6f846c3 100644 --- a/arch/arm/mm/abort-nommu.S +++ b/arch/arm/mm/abort-nommu.S @@ -3,8 +3,8 @@ /* * Function: nommu_early_abort * - * Params : r2 = address of aborted instruction - * : r3 = saved SPSR + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Returns : r0 = 0 (abort address) * : r1 = 0 (FSR) diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index 5f79dc4ce3fb..e7be700db08c 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -29,8 +29,8 @@ ENTRY(cpu_arm7_dcache_clean_area) /* * Function: arm6_7_data_abort () * - * Params : r2 = address of aborted instruction - * : sp = pointer to registers + * Params : r4 = aborted context pc + * : r5 = aborted context psr * * Purpose : obtain information about current aborted instruction * @@ -41,7 +41,7 @@ ENTRY(cpu_arm7_dcache_clean_area) ENTRY(cpu_arm7_data_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - ldr r8, [r2] @ read arm instruction + ldr r8, [r4] @ read arm instruction tst r8, #1 << 20 @ L = 0 -> write? orreq r1, r1, #1 << 11 @ yes. and r7, r8, #15 << 24 @@ -65,7 +65,7 @@ ENTRY(cpu_arm7_data_abort) /* e */ b .data_unknown /* f */ .data_unknown: @ Part of jumptable - mov r0, r2 + mov r0, r4 mov r1, r8 mov r2, sp bl baddataabort @@ -74,7 +74,7 @@ ENTRY(cpu_arm7_data_abort) ENTRY(cpu_arm6_data_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR mrc p15, 0, r0, c6, c0, 0 @ get FAR - ldr r8, [r2] @ read arm instruction + ldr r8, [r4] @ read arm instruction tst r8, #1 << 20 @ L = 0 -> write? orreq r1, r1, #1 << 11 @ yes. and r7, r8, #14 << 24 -- cgit v1.2.3 From 0d147db0c127c561f8f9ead9f3c1ec38f89f1040 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 14:42:02 +0100 Subject: ARM: entry: data abort: avoid using r2 in abort helpers This allows us to pass the pt_regs pointer in to these functions ready for tail-calling the abort handler. Signed-off-by: Russell King --- arch/arm/mm/abort-ev5t.S | 2 +- arch/arm/mm/abort-ev5tj.S | 2 +- arch/arm/mm/abort-ev6.S | 2 +- arch/arm/mm/abort-ev7.S | 8 ++++---- arch/arm/mm/abort-lv4t.S | 34 +++++++++++++++++----------------- arch/arm/mm/proc-arm6_7.S | 18 +++++++++--------- 6 files changed, 33 insertions(+), 33 deletions(-) diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S index 97eee7c48019..751391a5de59 100644 --- a/arch/arm/mm/abort-ev5t.S +++ b/arch/arm/mm/abort-ev5t.S @@ -25,7 +25,7 @@ ENTRY(v5t_early_abort) do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 ldreq r3, [r4] @ read aborted ARM instruction bic r1, r1, #1 << 11 @ clear bits 11 of FSR - do_ldrd_abort tmp=r2, insn=r3 + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ check write orreq r1, r1, #1 << 11 mov pc, lr diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S index 9a365cf1936f..ccfbc937054d 100644 --- a/arch/arm/mm/abort-ev5tj.S +++ b/arch/arm/mm/abort-ev5tj.S @@ -27,7 +27,7 @@ ENTRY(v5tj_early_abort) movne pc, lr do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 ldreq r3, [r4] @ read aborted ARM instruction - do_ldrd_abort tmp=r2, insn=r3 + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. mov pc, lr diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 52db4a3fc5f2..b64d886c0be7 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -40,7 +40,7 @@ ENTRY(v6_early_abort) #ifdef CONFIG_CPU_ENDIAN_BE8 reveq r3, r3 #endif - do_ldrd_abort tmp=r2, insn=r3 + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. mov pc, lr diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index 6cb51431a859..6f98b3a17ac7 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -41,13 +41,13 @@ ENTRY(v7_early_abort) mcr p15, 0, r0, c7, c8, 0 @ Retranslate FAR isb - mrc p15, 0, r2, c7, c4, 0 @ Read the PAR - and r3, r2, #0x7b @ On translation fault + mrc p15, 0, ip, c7, c4, 0 @ Read the PAR + and r3, ip, #0x7b @ On translation fault cmp r3, #0x0b movne pc, lr bic r1, r1, #0xf @ Fix up FSR FS[5:0] - and r2, r2, #0x7e - orr r1, r1, r2, LSR #1 + and ip, ip, #0x7e + orr r1, r1, ip, LSR #1 #endif mov pc, lr diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index fea7514225a6..d032b1f2067b 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -64,12 +64,12 @@ ENTRY(v4t_late_abort) mov r7, #0x11 orr r7, r7, #0x1100 and r6, r8, r7 - and r2, r8, r7, lsl #1 - add r6, r6, r2, lsr #1 - and r2, r8, r7, lsl #2 - add r6, r6, r2, lsr #2 - and r2, r8, r7, lsl #3 - add r6, r6, r2, lsr #3 + and r9, r8, r7, lsl #1 + add r6, r6, r9, lsr #1 + and r9, r8, r7, lsl #2 + add r6, r6, r9, lsr #2 + and r9, r8, r7, lsl #3 + add r6, r6, r9, lsr #3 add r6, r6, r6, lsr #8 add r6, r6, r6, lsr #4 and r6, r6, #15 @ r6 = no. of registers to transfer. @@ -103,13 +103,13 @@ ENTRY(v4t_late_abort) tst r8, #1 << 21 @ check writeback bit moveq pc, lr @ no writeback -> no fixup .data_arm_lateldrpostconst: - movs r2, r8, lsl #20 @ Get offset + movs r9, r8, lsl #20 @ Get offset moveq pc, lr @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit - subne r7, r7, r2, lsr #20 @ Undo increment - addeq r7, r7, r2, lsr #20 @ Undo decrement + subne r7, r7, r9, lsr #20 @ Undo increment + addeq r7, r7, r9, lsr #20 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' mov pc, lr @@ -194,11 +194,11 @@ ENTRY(v4t_late_abort) tst r8, #1 << 10 beq .data_unknown and r6, r8, #0x55 @ hweight8(r8) + R bit - and r2, r8, #0xaa - add r6, r6, r2, lsr #1 - and r2, r6, #0xcc + and r9, r8, #0xaa + add r6, r6, r9, lsr #1 + and r9, r6, #0xcc and r6, r6, #0x33 - add r6, r6, r2, lsr #2 + add r6, r6, r9, lsr #2 movs r7, r8, lsr #9 @ C = r8 bit 8 (R bit) adc r6, r6, r6, lsr #4 @ high + low nibble + R bit and r6, r6, #15 @ number of regs to transfer @@ -211,11 +211,11 @@ ENTRY(v4t_late_abort) .data_thumb_ldmstm: and r6, r8, #0x55 @ hweight8(r8) - and r2, r8, #0xaa - add r6, r6, r2, lsr #1 - and r2, r6, #0xcc + and r9, r8, #0xaa + add r6, r6, r9, lsr #1 + and r9, r6, #0xcc and r6, r6, #0x33 - add r6, r6, r2, lsr #2 + add r6, r6, r9, lsr #2 add r6, r6, r6, lsr #4 and r5, r8, #7 << 8 ldr r7, [sp, r5, lsr #6] diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index e7be700db08c..d4c328ecf3ba 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -87,12 +87,12 @@ ENTRY(cpu_arm6_data_abort) mov r7, #0x11 orr r7, r7, #0x1100 and r6, r8, r7 - and r2, r8, r7, lsl #1 - add r6, r6, r2, lsr #1 - and r2, r8, r7, lsl #2 - add r6, r6, r2, lsr #2 - and r2, r8, r7, lsl #3 - add r6, r6, r2, lsr #3 + and r9, r8, r7, lsl #1 + add r6, r6, r9, lsr #1 + and r9, r8, r7, lsl #2 + add r6, r6, r9, lsr #2 + and r9, r8, r7, lsl #3 + add r6, r6, r9, lsr #3 add r6, r6, r6, lsr #8 add r6, r6, r6, lsr #4 and r6, r6, #15 @ r6 = no. of registers to transfer. @@ -117,13 +117,13 @@ ENTRY(cpu_arm6_data_abort) tst r8, #1 << 21 @ check writeback bit moveq pc, lr @ no writeback -> no fixup .data_arm_lateldrpostconst: - movs r2, r8, lsl #20 @ Get offset + movs r9, r8, lsl #20 @ Get offset moveq pc, lr @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit - subne r7, r7, r2, lsr #20 @ Undo increment - addeq r7, r7, r2, lsr #20 @ Undo decrement + subne r7, r7, r9, lsr #20 @ Undo increment + addeq r7, r7, r9, lsr #20 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' mov pc, lr -- cgit v1.2.3 From da7404725781bc7c736e10cae5521e5604e222a5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 16:01:26 +0100 Subject: ARM: entry: data abort: tail-call the main data abort handler Tail-call the main C data abort handler code from the per-CPU helper code. Update the comments in the code wrt the new calling and return register state. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 14 ++++---------- arch/arm/mm/abort-ev4.S | 11 ++++------- arch/arm/mm/abort-ev4t.S | 11 ++++------- arch/arm/mm/abort-ev5t.S | 11 ++++------- arch/arm/mm/abort-ev5tj.S | 13 +++++-------- arch/arm/mm/abort-ev6.S | 13 +++++-------- arch/arm/mm/abort-ev7.S | 15 ++++++--------- arch/arm/mm/abort-lv4t.S | 43 +++++++++++++++++++++---------------------- arch/arm/mm/abort-macro.S | 4 ++-- arch/arm/mm/abort-nommu.S | 8 ++++---- arch/arm/mm/proc-arm6_7.S | 29 ++++++++++++++--------------- 11 files changed, 73 insertions(+), 99 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 85298c093256..bbdd443b8055 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -60,6 +60,7 @@ @ @ Call the processor-specific abort handler: @ + @ r2 - pt_regs @ r4 - aborted context pc @ r5 - aborted context psr @ @@ -186,13 +187,8 @@ ENDPROC(__und_invalid) .align 5 __dabt_svc: svc_entry - dabt_helper - - @ - @ call main handler - @ mov r2, sp - bl do_DataAbort + dabt_helper @ @ IRQs off again before pulling preserved data off the stack @@ -407,11 +403,9 @@ ENDPROC(__pabt_svc) __dabt_usr: usr_entry kuser_cmpxchg_check - dabt_helper - mov r2, sp - adr lr, BSYM(ret_from_exception) - b do_DataAbort + dabt_helper + b ret_from_exception UNWIND(.fnend ) ENDPROC(__dabt_usr) diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S index beb112bdc049..54473cd4aba9 100644 --- a/arch/arm/mm/abort-ev4.S +++ b/arch/arm/mm/abort-ev4.S @@ -3,14 +3,11 @@ /* * Function: v4_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -25,4 +22,4 @@ ENTRY(v4_early_abort) 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. - mov pc, lr + b do_DataAbort diff --git a/arch/arm/mm/abort-ev4t.S b/arch/arm/mm/abort-ev4t.S index eaa4ac023959..9da704e7b86e 100644 --- a/arch/arm/mm/abort-ev4t.S +++ b/arch/arm/mm/abort-ev4t.S @@ -4,14 +4,11 @@ /* * Function: v4t_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -27,4 +24,4 @@ ENTRY(v4t_early_abort) bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR tst r3, #1 << 20 @ check write orreq r1, r1, #1 << 11 - mov pc, lr + b do_DataAbort diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S index 751391a5de59..a0908d4653a3 100644 --- a/arch/arm/mm/abort-ev5t.S +++ b/arch/arm/mm/abort-ev5t.S @@ -4,14 +4,11 @@ /* * Function: v5t_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -28,4 +25,4 @@ ENTRY(v5t_early_abort) do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ check write orreq r1, r1, #1 << 11 - mov pc, lr + b do_DataAbort diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S index ccfbc937054d..4006b7a61264 100644 --- a/arch/arm/mm/abort-ev5tj.S +++ b/arch/arm/mm/abort-ev5tj.S @@ -4,14 +4,11 @@ /* * Function: v5tj_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -24,10 +21,10 @@ ENTRY(v5tj_early_abort) mrc p15, 0, r0, c6, c0, 0 @ get FAR bic r1, r1, #1 << 11 | 1 << 10 @ clear bits 11 and 10 of FSR tst r5, #PSR_J_BIT @ Java? - movne pc, lr + 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 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. - mov pc, lr + b do_DataAbort diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index b64d886c0be7..ff1f7cc11f87 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -4,14 +4,11 @@ /* * Function: v6_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -34,7 +31,7 @@ ENTRY(v6_early_abort) */ bic r1, r1, #1 << 11 @ clear bit 11 of FSR tst r5, #PSR_J_BIT @ Java? - movne pc, lr + bne do_DataAbort do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3 ldreq r3, [r4] @ read aborted ARM instruction #ifdef CONFIG_CPU_ENDIAN_BE8 @@ -43,4 +40,4 @@ ENTRY(v6_early_abort) do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. - mov pc, lr + b do_DataAbort diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S index 6f98b3a17ac7..703375277ba6 100644 --- a/arch/arm/mm/abort-ev7.S +++ b/arch/arm/mm/abort-ev7.S @@ -3,14 +3,11 @@ /* * Function: v7_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4 - r11, r13 preserved * * Purpose : obtain information about current aborted instruction. */ @@ -37,18 +34,18 @@ ENTRY(v7_early_abort) ldr r3, =0x40d @ On permission fault and r3, r1, r3 cmp r3, #0x0d - movne pc, lr + bne do_DataAbort mcr p15, 0, r0, c7, c8, 0 @ Retranslate FAR isb mrc p15, 0, ip, c7, c4, 0 @ Read the PAR and r3, ip, #0x7b @ On translation fault cmp r3, #0x0b - movne pc, lr + bne do_DataAbort bic r1, r1, #0xf @ Fix up FSR FS[5:0] and ip, ip, #0x7e orr r1, r1, ip, LSR #1 #endif - mov pc, lr + b do_DataAbort ENDPROC(v7_early_abort) diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index d032b1f2067b..d432f31cdab5 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -3,7 +3,8 @@ /* * Function: v4t_late_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * * Returns : r0 = address of abort @@ -47,20 +48,18 @@ ENTRY(v4t_late_abort) /* 9 */ b .data_arm_ldmstm @ ldm*b rn, /* a */ b .data_unknown /* b */ b .data_unknown -/* c */ mov pc, lr @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m -/* d */ mov pc, lr @ ldc rd, [rn, #m] +/* c */ b do_DataAbort @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m +/* d */ b do_DataAbort @ ldc rd, [rn, #m] /* e */ b .data_unknown /* f */ .data_unknown: @ Part of jumptable mov r0, r4 mov r1, r8 - mov r2, sp - bl baddataabort - b ret_from_exception + b baddataabort .data_arm_ldmstm: tst r8, #1 << 21 @ check writeback bit - moveq pc, lr @ no writeback -> no fixup + beq do_DataAbort @ no writeback -> no fixup mov r7, #0x11 orr r7, r7, #0x1100 and r6, r8, r7 @@ -79,11 +78,11 @@ ENTRY(v4t_late_abort) subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' - mov pc, lr + b do_DataAbort .data_arm_lateldrhpre: tst r8, #1 << 21 @ Check writeback bit - moveq pc, lr @ No writeback -> no fixup + beq do_DataAbort @ No writeback -> no fixup .data_arm_lateldrhpost: and r5, r8, #0x00f @ get Rm / low nibble of immediate value tst r8, #1 << 22 @ if (immediate offset) @@ -97,25 +96,25 @@ ENTRY(v4t_late_abort) subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' - mov pc, lr + b do_DataAbort .data_arm_lateldrpreconst: tst r8, #1 << 21 @ check writeback bit - moveq pc, lr @ no writeback -> no fixup + beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostconst: movs r9, r8, lsl #20 @ Get offset - moveq pc, lr @ zero -> no fixup + beq do_DataAbort @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r9, lsr #20 @ Undo increment addeq r7, r7, r9, lsr #20 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' - mov pc, lr + b do_DataAbort .data_arm_lateldrprereg: tst r8, #1 << 21 @ check writeback bit - moveq pc, lr @ no writeback -> no fixup + beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction ldr r6, [sp, r7, lsl #2] @ Get register 'Rm' @@ -172,10 +171,10 @@ ENTRY(v4t_late_abort) /* 3 */ b .data_unknown /* 4 */ b .data_unknown /* 5 */ b .data_thumb_reg -/* 6 */ mov pc, lr -/* 7 */ mov pc, lr -/* 8 */ mov pc, lr -/* 9 */ mov pc, lr +/* 6 */ b do_DataAbort +/* 7 */ b do_DataAbort +/* 8 */ b do_DataAbort +/* 9 */ b do_DataAbort /* A */ b .data_unknown /* B */ b .data_thumb_pushpop /* C */ b .data_thumb_ldmstm @@ -185,10 +184,10 @@ ENTRY(v4t_late_abort) .data_thumb_reg: tst r8, #1 << 9 - moveq pc, lr + beq do_DataAbort tst r8, #1 << 10 @ If 'S' (signed) bit is set movne r1, #0 @ it must be a load instr - mov pc, lr + b do_DataAbort .data_thumb_pushpop: tst r8, #1 << 10 @@ -207,7 +206,7 @@ ENTRY(v4t_late_abort) addeq r7, r7, r6, lsl #2 @ increment SP if PUSH subne r7, r7, r6, lsl #2 @ decrement SP if POP str r7, [sp, #13 << 2] - mov pc, lr + b do_DataAbort .data_thumb_ldmstm: and r6, r8, #0x55 @ hweight8(r8) @@ -222,4 +221,4 @@ ENTRY(v4t_late_abort) and r6, r6, #15 @ number of regs to transfer sub r7, r7, r6, lsl #2 @ always decrement str r7, [sp, r5, lsr #6] - mov pc, lr + b do_DataAbort diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S index af97a10bc5ed..52162d59407a 100644 --- a/arch/arm/mm/abort-macro.S +++ b/arch/arm/mm/abort-macro.S @@ -18,7 +18,7 @@ orreq \tmp, \tmp, #1 << 11 @ Set L-bit if yes tst \tmp, #1 << 11 @ L = 0 -> write orreq \psr, \psr, #1 << 11 @ yes. - mov pc, lr + b do_DataAbort not_thumb: .endm @@ -34,7 +34,7 @@ not_thumb: bne not_ldrd and \tmp, \insn, #0x000000f0 @ [7:4] == 1101 cmp \tmp, #0x000000d0 - moveq pc, lr + beq do_DataAbort not_ldrd: .endm diff --git a/arch/arm/mm/abort-nommu.S b/arch/arm/mm/abort-nommu.S index 9eaef6f846c3..119cb479c2ab 100644 --- a/arch/arm/mm/abort-nommu.S +++ b/arch/arm/mm/abort-nommu.S @@ -3,11 +3,11 @@ /* * Function: nommu_early_abort * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = 0 (abort address) - * : r1 = 0 (FSR) + * Returns : r4 - r11, r13 preserved * * Note: There is no FSR/FAR on !CPU_CP15_MMU cores. * Just fill zero into the registers. @@ -16,5 +16,5 @@ ENTRY(nommu_early_abort) mov r0, #0 @ clear r0, r1 (no FSR/FAR) mov r1, #0 - mov pc, lr + b do_DataAbort ENDPROC(nommu_early_abort) diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index d4c328ecf3ba..d755d5b83898 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -29,7 +29,8 @@ ENTRY(cpu_arm7_dcache_clean_area) /* * Function: arm6_7_data_abort () * - * Params : r4 = aborted context pc + * Params : r2 = pt_regs + * : r4 = aborted context pc * : r5 = aborted context psr * * Purpose : obtain information about current aborted instruction @@ -49,7 +50,7 @@ ENTRY(cpu_arm7_data_abort) nop /* 0 */ b .data_unknown -/* 1 */ mov pc, lr @ swp +/* 1 */ b do_DataAbort @ swp /* 2 */ b .data_unknown /* 3 */ b .data_unknown /* 4 */ b .data_arm_lateldrpostconst @ ldr rd, [rn], #m @@ -60,16 +61,14 @@ ENTRY(cpu_arm7_data_abort) /* 9 */ b .data_arm_ldmstm @ ldm*b rn, /* a */ b .data_unknown /* b */ b .data_unknown -/* c */ mov pc, lr @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m -/* d */ mov pc, lr @ ldc rd, [rn, #m] +/* c */ b do_DataAbort @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m +/* d */ b do_DataAbort @ ldc rd, [rn, #m] /* e */ b .data_unknown /* f */ .data_unknown: @ Part of jumptable mov r0, r4 mov r1, r8 - mov r2, sp - bl baddataabort - b ret_from_exception + b baddataabort ENTRY(cpu_arm6_data_abort) mrc p15, 0, r1, c5, c0, 0 @ get FSR @@ -79,11 +78,11 @@ ENTRY(cpu_arm6_data_abort) orreq r1, r1, #1 << 11 @ yes. and r7, r8, #14 << 24 teq r7, #8 << 24 @ was it ldm/stm - movne pc, lr + bne do_DataAbort .data_arm_ldmstm: tst r8, #1 << 21 @ check writeback bit - moveq pc, lr @ no writeback -> no fixup + beq do_DataAbort @ no writeback -> no fixup mov r7, #0x11 orr r7, r7, #0x1100 and r6, r8, r7 @@ -102,7 +101,7 @@ ENTRY(cpu_arm6_data_abort) subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' - mov pc, lr + b do_DataAbort .data_arm_apply_r6_and_rn: and r5, r8, #15 << 16 @ Extract 'n' from instruction @@ -111,25 +110,25 @@ ENTRY(cpu_arm6_data_abort) subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' - mov pc, lr + b do_DataAbort .data_arm_lateldrpreconst: tst r8, #1 << 21 @ check writeback bit - moveq pc, lr @ no writeback -> no fixup + beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostconst: movs r9, r8, lsl #20 @ Get offset - moveq pc, lr @ zero -> no fixup + beq do_DataAbort @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r9, lsr #20 @ Undo increment addeq r7, r7, r9, lsr #20 @ Undo decrement str r7, [sp, r5, lsr #14] @ Put register 'Rn' - mov pc, lr + b do_DataAbort .data_arm_lateldrprereg: tst r8, #1 << 21 @ check writeback bit - moveq pc, lr @ no writeback -> no fixup + beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction ldr r6, [sp, r7, lsl #2] @ Get register 'Rm' -- cgit v1.2.3 From e22c12f9146d50ee6b0cf97db46b3310409f64e6 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 27 Jun 2011 09:52:54 +0100 Subject: ARM: entry: data abort: use r2 as base of pt_regs rather than stack Now that we pass r2 into these helper functions as the pointer to pt_regs, use r2 as the base of the registers on the stack rather than using the stack pointer directly. Signed-off-by: Russell King --- arch/arm/mm/abort-lv4t.S | 24 ++++++++++++------------ arch/arm/mm/proc-arm6_7.S | 14 +++++++------- 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index d432f31cdab5..921aaab0c8c5 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -73,11 +73,11 @@ ENTRY(v4t_late_abort) add r6, r6, r6, lsr #4 and r6, r6, #15 @ r6 = no. of registers to transfer. and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' + ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement - str r7, [sp, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrhpre: @@ -88,14 +88,14 @@ ENTRY(v4t_late_abort) tst r8, #1 << 22 @ if (immediate offset) andne r6, r8, #0xf00 @ { immediate high nibble orrne r6, r5, r6, lsr #4 @ combine nibbles } else - ldreq r6, [sp, r5, lsl #2] @ { load Rm value } + ldreq r6, [r2, r5, lsl #2] @ { load Rm value } .data_arm_apply_r6_and_rn: and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' + ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement - str r7, [sp, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrpreconst: @@ -105,11 +105,11 @@ ENTRY(v4t_late_abort) movs r9, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' + ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r9, lsr #20 @ Undo increment addeq r7, r7, r9, lsr #20 @ Undo decrement - str r7, [sp, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrprereg: @@ -117,7 +117,7 @@ ENTRY(v4t_late_abort) beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction - ldr r6, [sp, r7, lsl #2] @ Get register 'Rm' + ldr r6, [r2, r7, lsl #2] @ Get register 'Rm' mov r5, r8, lsr #7 @ get shift count ands r5, r5, #31 and r7, r8, #0x70 @ get shift type @@ -201,11 +201,11 @@ ENTRY(v4t_late_abort) movs r7, r8, lsr #9 @ C = r8 bit 8 (R bit) adc r6, r6, r6, lsr #4 @ high + low nibble + R bit and r6, r6, #15 @ number of regs to transfer - ldr r7, [sp, #13 << 2] + ldr r7, [r2, #13 << 2] tst r8, #1 << 11 addeq r7, r7, r6, lsl #2 @ increment SP if PUSH subne r7, r7, r6, lsl #2 @ decrement SP if POP - str r7, [sp, #13 << 2] + str r7, [r2, #13 << 2] b do_DataAbort .data_thumb_ldmstm: @@ -217,8 +217,8 @@ ENTRY(v4t_late_abort) add r6, r6, r9, lsr #2 add r6, r6, r6, lsr #4 and r5, r8, #7 << 8 - ldr r7, [sp, r5, lsr #6] + ldr r7, [r2, r5, lsr #6] and r6, r6, #15 @ number of regs to transfer sub r7, r7, r6, lsl #2 @ always decrement - str r7, [sp, r5, lsr #6] + str r7, [r2, r5, lsr #6] b do_DataAbort diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index d755d5b83898..141906eae260 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -96,20 +96,20 @@ ENTRY(cpu_arm6_data_abort) add r6, r6, r6, lsr #4 and r6, r6, #15 @ r6 = no. of registers to transfer. and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' + ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement - str r7, [sp, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_apply_r6_and_rn: and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' + ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement - str r7, [sp, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrpreconst: @@ -119,11 +119,11 @@ ENTRY(cpu_arm6_data_abort) movs r9, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [sp, r5, lsr #14] @ Get register 'Rn' + ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r9, lsr #20 @ Undo increment addeq r7, r7, r9, lsr #20 @ Undo decrement - str r7, [sp, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrprereg: @@ -131,7 +131,7 @@ ENTRY(cpu_arm6_data_abort) beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction - ldr r6, [sp, r7, lsl #2] @ Get register 'Rm' + ldr r6, [r2, r7, lsl #2] @ Get register 'Rm' mov r5, r8, lsr #7 @ get shift count ands r5, r5, #31 and r7, r8, #0x70 @ get shift type -- cgit v1.2.3 From 108f6af0a82cf3b61f3ac6728e2241805a935b64 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 27 Jun 2011 12:23:11 +0100 Subject: ARM: entry: data abort: always use r6 for offset Signed-off-by: Russell King --- arch/arm/mm/abort-lv4t.S | 6 +++--- arch/arm/mm/proc-arm6_7.S | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index 921aaab0c8c5..54b6d279371a 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -102,13 +102,13 @@ ENTRY(v4t_late_abort) tst r8, #1 << 21 @ check writeback bit beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostconst: - movs r9, r8, lsl #20 @ Get offset + movs r6, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit - subne r7, r7, r9, lsr #20 @ Undo increment - addeq r7, r7, r9, lsr #20 @ Undo decrement + subne r7, r7, r6, lsr #20 @ Undo increment + addeq r7, r7, r6, lsr #20 @ Undo decrement str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index 141906eae260..4d963114c66b 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -116,13 +116,13 @@ ENTRY(cpu_arm6_data_abort) tst r8, #1 << 21 @ check writeback bit beq do_DataAbort @ no writeback -> no fixup .data_arm_lateldrpostconst: - movs r9, r8, lsl #20 @ Get offset + movs r6, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup and r5, r8, #15 << 16 @ Extract 'n' from instruction ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit - subne r7, r7, r9, lsr #20 @ Undo increment - addeq r7, r7, r9, lsr #20 @ Undo decrement + subne r7, r7, r6, lsr #20 @ Undo increment + addeq r7, r7, r6, lsr #20 @ Undo decrement str r7, [r2, r5, lsr #14] @ Put register 'Rn' b do_DataAbort -- cgit v1.2.3 From 40f0b90a2f16f433f9afbfef4b7c312efb54e933 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 27 Jun 2011 12:27:47 +0100 Subject: ARM: entry: data abort: ensure r5 is preserved by abort functions Signed-off-by: Russell King --- arch/arm/mm/abort-lv4t.S | 48 ++++++++++++++++++++++------------------------- arch/arm/mm/proc-arm6_7.S | 33 ++++++++++++++++---------------- 2 files changed, 38 insertions(+), 43 deletions(-) diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S index 54b6d279371a..f3982580c273 100644 --- a/arch/arm/mm/abort-lv4t.S +++ b/arch/arm/mm/abort-lv4t.S @@ -7,11 +7,7 @@ * : r4 = aborted context pc * : r5 = aborted context psr * - * Returns : r0 = address of abort - * : r1 = FSR, bit 11 = write - * : r2-r8 = corrupted - * : r9 = preserved - * : sp = pointer to registers + * Returns : r4-r5, r10-r11, r13 preserved * * Purpose : obtain information about current aborted instruction. * Note: we read user space. This means we might cause a data @@ -72,30 +68,30 @@ ENTRY(v4t_late_abort) add r6, r6, r6, lsr #8 add r6, r6, r6, lsr #4 and r6, r6, #15 @ r6 = no. of registers to transfer. - and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' + and r9, r8, #15 << 16 @ Extract 'n' from instruction + ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement - str r7, [r2, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r9, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrhpre: tst r8, #1 << 21 @ Check writeback bit beq do_DataAbort @ No writeback -> no fixup .data_arm_lateldrhpost: - and r5, r8, #0x00f @ get Rm / low nibble of immediate value + and r9, r8, #0x00f @ get Rm / low nibble of immediate value tst r8, #1 << 22 @ if (immediate offset) andne r6, r8, #0xf00 @ { immediate high nibble - orrne r6, r5, r6, lsr #4 @ combine nibbles } else - ldreq r6, [r2, r5, lsl #2] @ { load Rm value } + orrne r6, r9, r6, lsr #4 @ combine nibbles } else + ldreq r6, [r2, r9, lsl #2] @ { load Rm value } .data_arm_apply_r6_and_rn: - and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' + and r9, r8, #15 << 16 @ Extract 'n' from instruction + ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement - str r7, [r2, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r9, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrpreconst: @@ -104,12 +100,12 @@ ENTRY(v4t_late_abort) .data_arm_lateldrpostconst: movs r6, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup - and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' + and r9, r8, #15 << 16 @ Extract 'n' from instruction + ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsr #20 @ Undo increment addeq r7, r7, r6, lsr #20 @ Undo decrement - str r7, [r2, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r9, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrprereg: @@ -118,14 +114,14 @@ ENTRY(v4t_late_abort) .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction ldr r6, [r2, r7, lsl #2] @ Get register 'Rm' - mov r5, r8, lsr #7 @ get shift count - ands r5, r5, #31 + mov r9, r8, lsr #7 @ get shift count + ands r9, r9, #31 and r7, r8, #0x70 @ get shift type orreq r7, r7, #8 @ shift count = 0 add pc, pc, r7 nop - mov r6, r6, lsl r5 @ 0: LSL #!0 + mov r6, r6, lsl r9 @ 0: LSL #!0 b .data_arm_apply_r6_and_rn b .data_arm_apply_r6_and_rn @ 1: LSL #0 nop @@ -133,7 +129,7 @@ ENTRY(v4t_late_abort) nop b .data_unknown @ 3: MUL? nop - mov r6, r6, lsr r5 @ 4: LSR #!0 + mov r6, r6, lsr r9 @ 4: LSR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, lsr #32 @ 5: LSR #32 b .data_arm_apply_r6_and_rn @@ -141,7 +137,7 @@ ENTRY(v4t_late_abort) nop b .data_unknown @ 7: MUL? nop - mov r6, r6, asr r5 @ 8: ASR #!0 + mov r6, r6, asr r9 @ 8: ASR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, asr #32 @ 9: ASR #32 b .data_arm_apply_r6_and_rn @@ -149,7 +145,7 @@ ENTRY(v4t_late_abort) nop b .data_unknown @ B: MUL? nop - mov r6, r6, ror r5 @ C: ROR #!0 + mov r6, r6, ror r9 @ C: ROR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, rrx @ D: RRX b .data_arm_apply_r6_and_rn @@ -216,9 +212,9 @@ ENTRY(v4t_late_abort) and r6, r6, #0x33 add r6, r6, r9, lsr #2 add r6, r6, r6, lsr #4 - and r5, r8, #7 << 8 - ldr r7, [r2, r5, lsr #6] + and r9, r8, #7 << 8 + ldr r7, [r2, r9, lsr #6] and r6, r6, #15 @ number of regs to transfer sub r7, r7, r6, lsl #2 @ always decrement - str r7, [r2, r5, lsr #6] + str r7, [r2, r9, lsr #6] b do_DataAbort diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index 4d963114c66b..50e3543d03bf 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -35,8 +35,7 @@ ENTRY(cpu_arm7_dcache_clean_area) * * Purpose : obtain information about current aborted instruction * - * Returns : r0 = address of abort - * : r1 = FSR + * Returns : r4-r5, r10-r11, r13 preserved */ ENTRY(cpu_arm7_data_abort) @@ -95,21 +94,21 @@ ENTRY(cpu_arm6_data_abort) add r6, r6, r6, lsr #8 add r6, r6, r6, lsr #4 and r6, r6, #15 @ r6 = no. of registers to transfer. - and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' + and r9, r8, #15 << 16 @ Extract 'n' from instruction + ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsl #2 @ Undo increment addeq r7, r7, r6, lsl #2 @ Undo decrement - str r7, [r2, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r9, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_apply_r6_and_rn: - and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' + and r9, r8, #15 << 16 @ Extract 'n' from instruction + ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6 @ Undo incrmenet addeq r7, r7, r6 @ Undo decrement - str r7, [r2, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r9, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrpreconst: @@ -118,12 +117,12 @@ ENTRY(cpu_arm6_data_abort) .data_arm_lateldrpostconst: movs r6, r8, lsl #20 @ Get offset beq do_DataAbort @ zero -> no fixup - and r5, r8, #15 << 16 @ Extract 'n' from instruction - ldr r7, [r2, r5, lsr #14] @ Get register 'Rn' + and r9, r8, #15 << 16 @ Extract 'n' from instruction + ldr r7, [r2, r9, lsr #14] @ Get register 'Rn' tst r8, #1 << 23 @ Check U bit subne r7, r7, r6, lsr #20 @ Undo increment addeq r7, r7, r6, lsr #20 @ Undo decrement - str r7, [r2, r5, lsr #14] @ Put register 'Rn' + str r7, [r2, r9, lsr #14] @ Put register 'Rn' b do_DataAbort .data_arm_lateldrprereg: @@ -132,14 +131,14 @@ ENTRY(cpu_arm6_data_abort) .data_arm_lateldrpostreg: and r7, r8, #15 @ Extract 'm' from instruction ldr r6, [r2, r7, lsl #2] @ Get register 'Rm' - mov r5, r8, lsr #7 @ get shift count - ands r5, r5, #31 + mov r9, r8, lsr #7 @ get shift count + ands r9, r9, #31 and r7, r8, #0x70 @ get shift type orreq r7, r7, #8 @ shift count = 0 add pc, pc, r7 nop - mov r6, r6, lsl r5 @ 0: LSL #!0 + mov r6, r6, lsl r9 @ 0: LSL #!0 b .data_arm_apply_r6_and_rn b .data_arm_apply_r6_and_rn @ 1: LSL #0 nop @@ -147,7 +146,7 @@ ENTRY(cpu_arm6_data_abort) nop b .data_unknown @ 3: MUL? nop - mov r6, r6, lsr r5 @ 4: LSR #!0 + mov r6, r6, lsr r9 @ 4: LSR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, lsr #32 @ 5: LSR #32 b .data_arm_apply_r6_and_rn @@ -155,7 +154,7 @@ ENTRY(cpu_arm6_data_abort) nop b .data_unknown @ 7: MUL? nop - mov r6, r6, asr r5 @ 8: ASR #!0 + mov r6, r6, asr r9 @ 8: ASR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, asr #32 @ 9: ASR #32 b .data_arm_apply_r6_and_rn @@ -163,7 +162,7 @@ ENTRY(cpu_arm6_data_abort) nop b .data_unknown @ B: MUL? nop - mov r6, r6, ror r5 @ C: ROR #!0 + mov r6, r6, ror r9 @ C: ROR #!0 b .data_arm_apply_r6_and_rn mov r6, r6, rrx @ D: RRX b .data_arm_apply_r6_and_rn -- cgit v1.2.3 From 30891c90d81133179cc47eb77c30764a3b5dad5c Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 26 Jun 2011 12:47:08 +0100 Subject: ARM: entry: no need to reload the SPSR value from struct pt_regs The SVC IRQ, prefetch and data abort handlers preserve the SPSR value via r5 across the exception. Rather than re-loading it from pt_regs, use the preserved value instead. Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index bbdd443b8055..fa02a22a4c4b 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -195,10 +195,6 @@ __dabt_svc: @ disable_irq_notrace - @ - @ restore SPSR and restart the instruction - @ - ldr r5, [sp, #S_PSR] #ifdef CONFIG_TRACE_IRQFLAGS tst r5, #PSR_I_BIT bleq trace_hardirqs_on @@ -223,7 +219,7 @@ __irq_svc: tst r0, #_TIF_NEED_RESCHED blne svc_preempt #endif - ldr r5, [sp, #S_PSR] + #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. @@ -308,10 +304,6 @@ __pabt_svc: @ disable_irq_notrace - @ - @ restore SPSR and restart the instruction - @ - ldr r5, [sp, #S_PSR] #ifdef CONFIG_TRACE_IRQFLAGS tst r5, #PSR_I_BIT bleq trace_hardirqs_on -- cgit v1.2.3 From 8021a4a048a85906302bd0236f3d125473be65b1 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 16:13:58 +0100 Subject: ARM: dma-mapping: define dma_(un)?map_single in terms of dma_(un)?map_page Use dma_map_page()/dma_unmap_page() internals to handle dma_map_single() and dma_unmap_single(). Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 28 ---------------------------- arch/arm/include/asm/dma-mapping.h | 31 +++++++++---------------------- 2 files changed, 9 insertions(+), 50 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 841df7d21c2f..8a0588b007e4 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -328,34 +328,6 @@ static inline void unmap_single(struct device *dev, dma_addr_t dma_addr, * substitute the safe buffer for the unsafe one. * (basically move the buffer from an unsafe area to a safe one) */ -dma_addr_t __dma_map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction dir) -{ - dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n", - __func__, ptr, size, dir); - - BUG_ON(!valid_dma_direction(dir)); - - return map_single(dev, ptr, size, dir); -} -EXPORT_SYMBOL(__dma_map_single); - -/* - * see if a mapped address was really a "safe" buffer and if so, copy - * the data from the safe buffer back to the unsafe buffer and free up - * the safe buffer. (basically return things back to the way they - * should be) - */ -void __dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction dir) -{ - dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n", - __func__, (void *) dma_addr, size, dir); - - unmap_single(dev, dma_addr, size, dir); -} -EXPORT_SYMBOL(__dma_unmap_single); - dma_addr_t __dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir) { diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 4fff837363ed..d2903d0c3085 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -298,10 +298,6 @@ extern int dma_needs_bounce(struct device*, dma_addr_t, size_t); /* * The DMA API, implemented by dmabounce.c. See below for descriptions. */ -extern dma_addr_t __dma_map_single(struct device *, void *, size_t, - enum dma_data_direction); -extern void __dma_unmap_single(struct device *, dma_addr_t, size_t, - enum dma_data_direction); extern dma_addr_t __dma_map_page(struct device *, struct page *, unsigned long, size_t, enum dma_data_direction); extern void __dma_unmap_page(struct device *, dma_addr_t, size_t, @@ -328,13 +324,6 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr, } -static inline dma_addr_t __dma_map_single(struct device *dev, void *cpu_addr, - size_t size, enum dma_data_direction dir) -{ - __dma_single_cpu_to_dev(cpu_addr, size, dir); - return virt_to_dma(dev, cpu_addr); -} - static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir) { @@ -342,12 +331,6 @@ static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page, return pfn_to_dma(dev, page_to_pfn(page)) + offset; } -static inline void __dma_unmap_single(struct device *dev, dma_addr_t handle, - size_t size, enum dma_data_direction dir) -{ - __dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir); -} - static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { @@ -373,14 +356,18 @@ static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle, static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr, size_t size, enum dma_data_direction dir) { + unsigned long offset; + struct page *page; dma_addr_t addr; + BUG_ON(!virt_addr_valid(cpu_addr)); + BUG_ON(!virt_addr_valid(cpu_addr + size - 1)); BUG_ON(!valid_dma_direction(dir)); - addr = __dma_map_single(dev, cpu_addr, size, dir); - debug_dma_map_page(dev, virt_to_page(cpu_addr), - (unsigned long)cpu_addr & ~PAGE_MASK, size, - dir, addr, true); + page = virt_to_page(cpu_addr); + offset = (unsigned long)cpu_addr & ~PAGE_MASK; + addr = __dma_map_page(dev, page, offset, size, dir); + debug_dma_map_page(dev, page, offset, size, dir, addr, true); return addr; } @@ -430,7 +417,7 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { debug_dma_unmap_page(dev, handle, size, dir, true); - __dma_unmap_single(dev, handle, size, dir); + __dma_unmap_page(dev, handle, size, dir); } /** -- cgit v1.2.3 From 71695dd8b9eacfcda1b548a5b1780d34213ad654 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 19:46:39 +0100 Subject: ARM: dmabounce: avoid needless valid_dma_direction() check This check is done at the DMA API level, so there's no point repeating it here. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 8a0588b007e4..3e0fa1548582 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -334,8 +334,6 @@ dma_addr_t __dma_map_page(struct device *dev, struct page *page, dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n", __func__, page, offset, size, dir); - BUG_ON(!valid_dma_direction(dir)); - if (PageHighMem(page)) { dev_err(dev, "DMA buffer bouncing of HIGHMEM pages " "is not supported\n"); -- cgit v1.2.3 From 23bc9873ba60ee661d8e9f3a6b22fc3bcc4b7015 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 22:28:32 +0100 Subject: ARM: dmabounce: separate out decision to bounce Move the decision to perform DMA bouncing out of map_single() into its own stand-alone function. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 46 +++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 3e0fa1548582..643e1d660677 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -219,36 +219,46 @@ static struct safe_buffer *find_safe_buffer_dev(struct device *dev, return find_safe_buffer(dev->archdata.dmabounce, dma_addr); } -static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction dir) +static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) { - struct dmabounce_device_info *device_info = dev->archdata.dmabounce; - dma_addr_t dma_addr; - int needs_bounce = 0; - - if (device_info) - DO_STATS ( device_info->map_op_count++ ); - - dma_addr = virt_to_dma(dev, ptr); + if (!dev || !dev->archdata.dmabounce) + return 0; if (dev->dma_mask) { - unsigned long mask = *dev->dma_mask; - unsigned long limit; + unsigned long limit, mask = *dev->dma_mask; limit = (mask + 1) & ~mask; if (limit && size > limit) { dev_err(dev, "DMA mapping too big (requested %#x " "mask %#Lx)\n", size, *dev->dma_mask); - return ~0; + return -E2BIG; } - /* - * Figure out if we need to bounce from the DMA mask. - */ - needs_bounce = (dma_addr | (dma_addr + size - 1)) & ~mask; + /* Figure out if we need to bounce from the DMA mask. */ + if ((dma_addr | (dma_addr + size - 1)) & ~mask) + return 1; } - if (device_info && (needs_bounce || dma_needs_bounce(dev, dma_addr, size))) { + return dma_needs_bounce(dev, dma_addr, size) ? 1 : 0; +} + +static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, + enum dma_data_direction dir) +{ + struct dmabounce_device_info *device_info = dev->archdata.dmabounce; + dma_addr_t dma_addr; + int ret; + + if (device_info) + DO_STATS ( device_info->map_op_count++ ); + + dma_addr = virt_to_dma(dev, ptr); + + ret = needs_bounce(dev, dma_addr, size); + if (ret < 0) + return ~0; + + if (ret > 0) { struct safe_buffer *buf; buf = alloc_safe_buffer(device_info, ptr, size, dir); -- cgit v1.2.3 From dd3641fc3cf6d10b7cf4e266c2f651517779e727 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 22:39:43 +0100 Subject: ARM: dmabounce: move decision for bouncing into __dma_map_page() Move the decision whether to bounce into __dma_map_page(), before the check for high pages. This avoids triggering the high page check for devices which aren't using dmabounce. Fix the unmap path to cope too. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 124 +++++++++++++++++++++----------------------- 1 file changed, 58 insertions(+), 66 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 643e1d660677..6ae292cc43bf 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -246,88 +246,58 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir) { struct dmabounce_device_info *device_info = dev->archdata.dmabounce; - dma_addr_t dma_addr; - int ret; + struct safe_buffer *buf; if (device_info) DO_STATS ( device_info->map_op_count++ ); - dma_addr = virt_to_dma(dev, ptr); - - ret = needs_bounce(dev, dma_addr, size); - if (ret < 0) + buf = alloc_safe_buffer(device_info, ptr, size, dir); + if (buf == 0) { + dev_err(dev, "%s: unable to map unsafe buffer %p!\n", + __func__, ptr); return ~0; + } - if (ret > 0) { - struct safe_buffer *buf; - - buf = alloc_safe_buffer(device_info, ptr, size, dir); - if (buf == 0) { - dev_err(dev, "%s: unable to map unsafe buffer %p!\n", - __func__, ptr); - return ~0; - } - - dev_dbg(dev, - "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", - __func__, buf->ptr, virt_to_dma(dev, buf->ptr), - buf->safe, buf->safe_dma_addr); - - if ((dir == DMA_TO_DEVICE) || - (dir == DMA_BIDIRECTIONAL)) { - dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n", - __func__, ptr, buf->safe, size); - memcpy(buf->safe, ptr, size); - } - ptr = buf->safe; + dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", + __func__, buf->ptr, virt_to_dma(dev, buf->ptr), + buf->safe, buf->safe_dma_addr); - dma_addr = buf->safe_dma_addr; - } else { - /* - * We don't need to sync the DMA buffer since - * it was allocated via the coherent allocators. - */ - __dma_single_cpu_to_dev(ptr, size, dir); + if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) { + dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n", + __func__, ptr, buf->safe, size); + memcpy(buf->safe, ptr, size); } - return dma_addr; + return buf->safe_dma_addr; } -static inline void unmap_single(struct device *dev, dma_addr_t dma_addr, +static inline void unmap_single(struct device *dev, struct safe_buffer *buf, size_t size, enum dma_data_direction dir) { - struct safe_buffer *buf = find_safe_buffer_dev(dev, dma_addr, "unmap"); - - if (buf) { - BUG_ON(buf->size != size); - BUG_ON(buf->direction != dir); + BUG_ON(buf->size != size); + BUG_ON(buf->direction != dir); - dev_dbg(dev, - "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", - __func__, buf->ptr, virt_to_dma(dev, buf->ptr), - buf->safe, buf->safe_dma_addr); + dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n", + __func__, buf->ptr, virt_to_dma(dev, buf->ptr), + buf->safe, buf->safe_dma_addr); - DO_STATS(dev->archdata.dmabounce->bounce_count++); + DO_STATS(dev->archdata.dmabounce->bounce_count++); - if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) { - void *ptr = buf->ptr; + if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) { + void *ptr = buf->ptr; - dev_dbg(dev, - "%s: copy back safe %p to unsafe %p size %d\n", - __func__, buf->safe, ptr, size); - memcpy(ptr, buf->safe, size); + dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n", + __func__, buf->safe, ptr, size); + memcpy(ptr, buf->safe, size); - /* - * Since we may have written to a page cache page, - * we need to ensure that the data will be coherent - * with user mappings. - */ - __cpuc_flush_dcache_area(ptr, size); - } - free_safe_buffer(dev->archdata.dmabounce, buf); - } else { - __dma_single_dev_to_cpu(dma_to_virt(dev, dma_addr), size, dir); + /* + * Since we may have written to a page cache page, + * we need to ensure that the data will be coherent + * with user mappings. + */ + __cpuc_flush_dcache_area(ptr, size); } + free_safe_buffer(dev->archdata.dmabounce, buf); } /* ************************************************** */ @@ -341,12 +311,25 @@ static inline void unmap_single(struct device *dev, dma_addr_t dma_addr, dma_addr_t __dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir) { + dma_addr_t dma_addr; + int ret; + dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n", __func__, page, offset, size, dir); + dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset; + + ret = needs_bounce(dev, dma_addr, size); + if (ret < 0) + return ~0; + + if (ret == 0) { + __dma_page_cpu_to_dev(page, offset, size, dir); + return dma_addr; + } + if (PageHighMem(page)) { - dev_err(dev, "DMA buffer bouncing of HIGHMEM pages " - "is not supported\n"); + dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n"); return ~0; } @@ -363,10 +346,19 @@ EXPORT_SYMBOL(__dma_map_page); void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir) { + struct safe_buffer *buf; + dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n", __func__, (void *) dma_addr, size, dir); - unmap_single(dev, dma_addr, size, dir); + buf = find_safe_buffer_dev(dev, dma_addr, __func__); + if (!buf) { + __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, dma_addr)), + dma_addr & ~PAGE_MASK, size, dir); + return; + } + + unmap_single(dev, buf, size, dir); } EXPORT_SYMBOL(__dma_unmap_page); -- cgit v1.2.3 From e2f521e247576c897e1bf0ada801e87c7e2db89f Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 23:53:13 +0100 Subject: ARM: dmabounce: remove useless pr_err We already check that dev != NULL, so this won't be reached. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 6ae292cc43bf..0077c1b7d7ff 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -210,10 +210,7 @@ static struct safe_buffer *find_safe_buffer_dev(struct device *dev, if (!dev || !dev->archdata.dmabounce) return NULL; if (dma_mapping_error(dev, dma_addr)) { - if (dev) - dev_err(dev, "Trying to %s invalid mapping\n", where); - else - pr_err("unknown device: Trying to %s invalid mapping\n", where); + dev_err(dev, "Trying to %s invalid mapping\n", where); return NULL; } return find_safe_buffer(dev->archdata.dmabounce, dma_addr); -- cgit v1.2.3 From dfa322fceb15227c07670c415e835d2dfa8a4307 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 23:54:34 +0100 Subject: ARM: dmabounce: check pointer against NULL not 0 Pointers should be checked against NULL rather than 0, otherwise we get sparse warnings. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 0077c1b7d7ff..b4a8759e0fa4 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -249,7 +249,7 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, DO_STATS ( device_info->map_op_count++ ); buf = alloc_safe_buffer(device_info, ptr, size, dir); - if (buf == 0) { + if (buf == NULL) { dev_err(dev, "%s: unable to map unsafe buffer %p!\n", __func__, ptr); return ~0; -- cgit v1.2.3 From c289b2e0ccff1142908e20398930dc2e14697e74 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 3 Jul 2011 23:56:17 +0100 Subject: ARM: dmabounce: correct unmap_single dev_dbg DMA addresses should not be casted to void * for printing. Fix that to be consistent with the rest of the file. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index b4a8759e0fa4..4f13505ac936 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -345,8 +345,8 @@ void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, { struct safe_buffer *buf; - dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n", - __func__, (void *) dma_addr, size, dir); + dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n", + __func__, dma_addr, size, dir); buf = find_safe_buffer_dev(dev, dma_addr, __func__); if (!buf) { -- cgit v1.2.3 From 0703ed2a6b260cd743adf49a8281eb064d728832 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 4 Jul 2011 08:32:21 +0100 Subject: ARM: dmabounce: get rid of dma_needs_bounce global function Pass the device type specific needs_bounce function in at dmabounce register time, avoiding the need for a platform specific global function to do this. Signed-off-by: Russell King --- arch/arm/common/dmabounce.c | 8 +++-- arch/arm/common/it8152.c | 17 +++++------ arch/arm/common/sa1111.c | 60 ++++++++++++++++++++------------------ arch/arm/include/asm/dma-mapping.h | 22 ++------------ arch/arm/mach-ixp4xx/common-pci.c | 12 ++++---- 5 files changed, 53 insertions(+), 66 deletions(-) diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 4f13505ac936..595ecd290ebf 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -79,6 +79,8 @@ struct dmabounce_device_info { struct dmabounce_pool large; rwlock_t lock; + + int (*needs_bounce)(struct device *, dma_addr_t, size_t); }; #ifdef STATS @@ -236,7 +238,7 @@ static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) return 1; } - return dma_needs_bounce(dev, dma_addr, size) ? 1 : 0; + return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size); } static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, @@ -430,7 +432,8 @@ static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev, } int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size, - unsigned long large_buffer_size) + unsigned long large_buffer_size, + int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t)) { struct dmabounce_device_info *device_info; int ret; @@ -466,6 +469,7 @@ int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size, device_info->dev = dev; INIT_LIST_HEAD(&device_info->safe_buffers); rwlock_init(&device_info->lock); + device_info->needs_bounce = needs_bounce_fn; #ifdef STATS device_info->total_allocs = 0; diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 7a21927c52e1..80b49e1e0992 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -243,6 +243,13 @@ static struct resource it8152_mem = { * ITE8152 chip can address up to 64MByte, so all the devices * connected to ITE8152 (PCI and USB) should have limited DMA window */ +static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) +{ + dev_dbg(dev, "%s: dma_addr %08x, size %08x\n", + __func__, dma_addr, size); + return dev->bus == &pci_bus_type && + (dma_addr + size - PHYS_OFFSET) >= SZ_64M; +} /* * Setup DMA mask to 64MB on devices connected to ITE8152. Ignore all @@ -254,7 +261,7 @@ static int it8152_pci_platform_notify(struct device *dev) if (dev->dma_mask) *dev->dma_mask = (SZ_64M - 1) | PHYS_OFFSET; dev->coherent_dma_mask = (SZ_64M - 1) | PHYS_OFFSET; - dmabounce_register_dev(dev, 2048, 4096); + dmabounce_register_dev(dev, 2048, 4096, it8152_needs_bounce); } return 0; } @@ -267,14 +274,6 @@ static int it8152_pci_platform_notify_remove(struct device *dev) return 0; } -int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) -{ - dev_dbg(dev, "%s: dma_addr %08x, size %08x\n", - __func__, dma_addr, size); - return (dev->bus == &pci_bus_type) && - ((dma_addr + size - PHYS_OFFSET) >= SZ_64M); -} - int dma_set_coherent_mask(struct device *dev, u64 mask) { if (mask >= PHYS_OFFSET + SZ_64M - 1) diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index 9c49a46a2b7a..0569de6acfba 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -579,7 +579,36 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac, sachip->dev->coherent_dma_mask &= sa1111_dma_mask[drac >> 2]; } +#endif +#ifdef CONFIG_DMABOUNCE +/* + * According to the "Intel StrongARM SA-1111 Microprocessor Companion + * Chip Specification Update" (June 2000), erratum #7, there is a + * significant bug in the SA1111 SDRAM shared memory controller. If + * an access to a region of memory above 1MB relative to the bank base, + * it is important that address bit 10 _NOT_ be asserted. Depending + * on the configuration of the RAM, bit 10 may correspond to one + * of several different (processor-relative) address bits. + * + * This routine only identifies whether or not a given DMA address + * is susceptible to the bug. + * + * This should only get called for sa1111_device types due to the + * way we configure our device dma_masks. + */ +static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size) +{ + /* + * Section 4.6 of the "Intel StrongARM SA-1111 Development Module + * User's Guide" mentions that jumpers R51 and R52 control the + * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or + * SDRAM bank 1 on Neponset). The default configuration selects + * Assabet, so any address in bank 1 is necessarily invalid. + */ + return (machine_is_assabet() || machine_is_pfs168()) && + (addr >= 0xc8000000 || (addr + size) >= 0xc8000000); +} #endif static void sa1111_dev_release(struct device *_dev) @@ -644,7 +673,8 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent, dev->dev.dma_mask = &dev->dma_mask; if (dev->dma_mask != 0xffffffffUL) { - ret = dmabounce_register_dev(&dev->dev, 1024, 4096); + ret = dmabounce_register_dev(&dev->dev, 1024, 4096, + sa1111_needs_bounce); if (ret) { dev_err(&dev->dev, "SA1111: Failed to register" " with dmabounce\n"); @@ -818,34 +848,6 @@ static void __sa1111_remove(struct sa1111 *sachip) kfree(sachip); } -/* - * According to the "Intel StrongARM SA-1111 Microprocessor Companion - * Chip Specification Update" (June 2000), erratum #7, there is a - * significant bug in the SA1111 SDRAM shared memory controller. If - * an access to a region of memory above 1MB relative to the bank base, - * it is important that address bit 10 _NOT_ be asserted. Depending - * on the configuration of the RAM, bit 10 may correspond to one - * of several different (processor-relative) address bits. - * - * This routine only identifies whether or not a given DMA address - * is susceptible to the bug. - * - * This should only get called for sa1111_device types due to the - * way we configure our device dma_masks. - */ -int dma_needs_bounce(struct device *dev, dma_addr_t addr, size_t size) -{ - /* - * Section 4.6 of the "Intel StrongARM SA-1111 Development Module - * User's Guide" mentions that jumpers R51 and R52 control the - * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or - * SDRAM bank 1 on Neponset). The default configuration selects - * Assabet, so any address in bank 1 is necessarily invalid. - */ - return ((machine_is_assabet() || machine_is_pfs168()) && - (addr >= 0xc8000000 || (addr + size) >= 0xc8000000)); -} - struct sa1111_save_data { unsigned int skcr; unsigned int skpcr; diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index d2903d0c3085..4ad25337f927 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -256,14 +256,14 @@ int dma_mmap_writecombine(struct device *, struct vm_area_struct *, * @dev: valid struct device pointer * @small_buf_size: size of buffers to use with small buffer pool * @large_buf_size: size of buffers to use with large buffer pool (can be 0) + * @needs_bounce_fn: called to determine whether buffer needs bouncing * * This function should be called by low-level platform code to register * a device as requireing DMA buffer bouncing. The function will allocate * appropriate DMA pools for the device. - * */ extern int dmabounce_register_dev(struct device *, unsigned long, - unsigned long); + unsigned long, int (*)(struct device *, dma_addr_t, size_t)); /** * dmabounce_unregister_dev @@ -277,24 +277,6 @@ extern int dmabounce_register_dev(struct device *, unsigned long, */ extern void dmabounce_unregister_dev(struct device *); -/** - * dma_needs_bounce - * - * @dev: valid struct device pointer - * @dma_handle: dma_handle of unbounced buffer - * @size: size of region being mapped - * - * Platforms that utilize the dmabounce mechanism must implement - * this function. - * - * The dmabounce routines call this function whenever a dma-mapping - * is requested to determine whether a given buffer needs to be bounced - * or not. The function must return 0 if the buffer is OK for - * DMA access and 1 if the buffer needs to be bounced. - * - */ -extern int dma_needs_bounce(struct device*, dma_addr_t, size_t); - /* * The DMA API, implemented by dmabounce.c. See below for descriptions. */ diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index e9a589395723..d7db10cfe53d 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -316,6 +316,11 @@ static int abort_handler(unsigned long addr, unsigned int fsr, struct pt_regs *r } +static int ixp4xx_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) +{ + return dev->bus == &pci_bus_type && (dma_addr + size) >= SZ_64M; +} + /* * Setup DMA mask to 64MB on PCI devices. Ignore all other devices. */ @@ -324,7 +329,7 @@ static int ixp4xx_pci_platform_notify(struct device *dev) if(dev->bus == &pci_bus_type) { *dev->dma_mask = SZ_64M - 1; dev->coherent_dma_mask = SZ_64M - 1; - dmabounce_register_dev(dev, 2048, 4096); + dmabounce_register_dev(dev, 2048, 4096, ixp4xx_needs_bounce); } return 0; } @@ -337,11 +342,6 @@ static int ixp4xx_pci_platform_notify_remove(struct device *dev) return 0; } -int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) -{ - return (dev->bus == &pci_bus_type ) && ((dma_addr + size) >= SZ_64M); -} - void __init ixp4xx_pci_preinit(void) { unsigned long cpuid = read_cpuid_id(); -- cgit v1.2.3 From 5c8598fca1a359520623ed5409d23bb9e23d7da3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 4 Jul 2011 08:34:33 +0100 Subject: ARM: dmabounce: no need to check dev->bus type in needs_bounce function As the needs_bounce function is passed at DMA bounce register time, we already know what the device bus type is, so we don't need to check it each time the needs_bounce function is called. Signed-off-by: Russell King --- arch/arm/common/it8152.c | 3 +-- arch/arm/mach-ixp4xx/common-pci.c | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 80b49e1e0992..14ad62e16dd1 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -247,8 +247,7 @@ static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t s { dev_dbg(dev, "%s: dma_addr %08x, size %08x\n", __func__, dma_addr, size); - return dev->bus == &pci_bus_type && - (dma_addr + size - PHYS_OFFSET) >= SZ_64M; + return (dma_addr + size - PHYS_OFFSET) >= SZ_64M; } /* diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index d7db10cfe53d..e2e98bbb6413 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -318,7 +318,7 @@ static int abort_handler(unsigned long addr, unsigned int fsr, struct pt_regs *r static int ixp4xx_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) { - return dev->bus == &pci_bus_type && (dma_addr + size) >= SZ_64M; + return (dma_addr + size) >= SZ_64M; } /* -- cgit v1.2.3 From 9715efb8dc9ffa629bf5a1215b11bf2f2f29908b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 1 Jul 2011 08:23:06 +0100 Subject: ARM: 6984/1: enhance TCM robustness The PB11MPCore reports "3" DTCM banks, but anything above 2 is an "undefined" value, so push this to become 0. Further add some checks if code is compiled to TCM even if there is no D/ITCM present in the system, and if we can really fit the compiled code. We don't do the BUG() since it's not helpful, it's better to deal with non-present TCM dynamically. If there is nothing compiled to the TCM and no TCM is detected, it will now just shut up even if TCM support is enabled. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/kernel/tcm.c | 47 +++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 39 insertions(+), 8 deletions(-) diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index f5cf660eefcc..d402d4829524 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -134,6 +134,10 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks, (tcm_region & 1) ? "" : "not "); } + /* Not much fun you can do with a size 0 bank */ + if (tcm_size == 0) + return 0; + /* Force move the TCM bank to where we want it, enable */ tcm_region = *offset | (tcm_region & 0x00000ffeU) | 1; @@ -165,12 +169,20 @@ void __init tcm_init(void) u32 tcm_status = read_cpuid_tcmstatus(); u8 dtcm_banks = (tcm_status >> 16) & 0x03; u8 itcm_banks = (tcm_status & 0x03); + size_t dtcm_code_sz = &__edtcm_data - &__sdtcm_data; + size_t itcm_code_sz = &__eitcm_text - &__sitcm_text; char *start; char *end; char *ram; int ret; int i; + /* Values greater than 2 for D/ITCM banks are "reserved" */ + if (dtcm_banks > 2) + dtcm_banks = 0; + if (itcm_banks > 2) + itcm_banks = 0; + /* Setup DTCM if present */ if (dtcm_banks > 0) { for (i = 0; i < dtcm_banks; i++) { @@ -178,6 +190,13 @@ void __init tcm_init(void) if (ret) return; } + /* This means you compiled more code than fits into DTCM */ + if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) { + pr_info("CPU DTCM: %u bytes of code compiled to " + "DTCM but only %lu bytes of DTCM present\n", + dtcm_code_sz, (dtcm_end - DTCM_OFFSET)); + goto no_dtcm; + } dtcm_res.end = dtcm_end - 1; request_resource(&iomem_resource, &dtcm_res); dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET; @@ -186,12 +205,15 @@ void __init tcm_init(void) start = &__sdtcm_data; end = &__edtcm_data; ram = &__dtcm_start; - /* This means you compiled more code than fits into DTCM */ - BUG_ON((end - start) > (dtcm_end - DTCM_OFFSET)); - memcpy(start, ram, (end-start)); - pr_debug("CPU DTCM: copied data from %p - %p\n", start, end); + memcpy(start, ram, dtcm_code_sz); + pr_debug("CPU DTCM: copied data from %p - %p\n", + start, end); + } else if (dtcm_code_sz) { + pr_info("CPU DTCM: %u bytes of code compiled to DTCM but no " + "DTCM banks present in CPU\n", dtcm_code_sz); } +no_dtcm: /* Setup ITCM if present */ if (itcm_banks > 0) { for (i = 0; i < itcm_banks; i++) { @@ -199,6 +221,13 @@ void __init tcm_init(void) if (ret) return; } + /* This means you compiled more code than fits into ITCM */ + if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) { + pr_info("CPU ITCM: %u bytes of code compiled to " + "ITCM but only %lu bytes of ITCM present\n", + itcm_code_sz, (itcm_end - ITCM_OFFSET)); + return; + } itcm_res.end = itcm_end - 1; request_resource(&iomem_resource, &itcm_res); itcm_iomap[0].length = itcm_end - ITCM_OFFSET; @@ -207,10 +236,12 @@ void __init tcm_init(void) start = &__sitcm_text; end = &__eitcm_text; ram = &__itcm_start; - /* This means you compiled more code than fits into ITCM */ - BUG_ON((end - start) > (itcm_end - ITCM_OFFSET)); - memcpy(start, ram, (end-start)); - pr_debug("CPU ITCM: copied code from %p - %p\n", start, end); + memcpy(start, ram, itcm_code_sz); + pr_debug("CPU ITCM: copied code from %p - %p\n", + start, end); + } else if (itcm_code_sz) { + pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no " + "ITCM banks present in CPU\n", itcm_code_sz); } } -- cgit v1.2.3 From 201043f227576d42529ddb340746a060a00f57f6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 1 Jul 2011 08:23:36 +0100 Subject: ARM: 6985/1: export functions to determine the presence of I/DTCM By allowing code to detect whether DTCM or ITCM is present, code paths involving TCM can be avoided when running on platforms that lack it. This is good for creating single kernels across several archs, if some of them utilize TCM but others don't. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/include/asm/tcm.h | 2 ++ arch/arm/kernel/tcm.c | 21 ++++++++++++++++++--- 2 files changed, 20 insertions(+), 3 deletions(-) diff --git a/arch/arm/include/asm/tcm.h b/arch/arm/include/asm/tcm.h index 5929ef5d927a..8578d726ad78 100644 --- a/arch/arm/include/asm/tcm.h +++ b/arch/arm/include/asm/tcm.h @@ -27,5 +27,7 @@ void *tcm_alloc(size_t len); void tcm_free(void *addr, size_t len); +bool tcm_dtcm_present(void); +bool tcm_itcm_present(void); #endif diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index d402d4829524..30e302d33e0a 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -19,6 +19,8 @@ #include "tcm.h" static struct gen_pool *tcm_pool; +static bool dtcm_present; +static bool itcm_present; /* TCM section definitions from the linker */ extern char __itcm_start, __sitcm_text, __eitcm_text; @@ -90,6 +92,18 @@ void tcm_free(void *addr, size_t len) } EXPORT_SYMBOL(tcm_free); +bool tcm_dtcm_present(void) +{ + return dtcm_present; +} +EXPORT_SYMBOL(tcm_dtcm_present); + +bool tcm_itcm_present(void) +{ + return itcm_present; +} +EXPORT_SYMBOL(tcm_itcm_present); + static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks, u32 *offset) { @@ -208,6 +222,7 @@ void __init tcm_init(void) memcpy(start, ram, dtcm_code_sz); pr_debug("CPU DTCM: copied data from %p - %p\n", start, end); + dtcm_present = true; } else if (dtcm_code_sz) { pr_info("CPU DTCM: %u bytes of code compiled to DTCM but no " "DTCM banks present in CPU\n", dtcm_code_sz); @@ -239,6 +254,7 @@ no_dtcm: memcpy(start, ram, itcm_code_sz); pr_debug("CPU ITCM: copied code from %p - %p\n", start, end); + itcm_present = true; } else if (itcm_code_sz) { pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no " "ITCM banks present in CPU\n", itcm_code_sz); @@ -252,7 +268,6 @@ no_dtcm: */ static int __init setup_tcm_pool(void) { - u32 tcm_status = read_cpuid_tcmstatus(); u32 dtcm_pool_start = (u32) &__edtcm_data; u32 itcm_pool_start = (u32) &__eitcm_text; int ret; @@ -267,7 +282,7 @@ static int __init setup_tcm_pool(void) pr_debug("Setting up TCM memory pool\n"); /* Add the rest of DTCM to the TCM pool */ - if (tcm_status & (0x03 << 16)) { + if (dtcm_present) { if (dtcm_pool_start < dtcm_end) { ret = gen_pool_add(tcm_pool, dtcm_pool_start, dtcm_end - dtcm_pool_start, -1); @@ -284,7 +299,7 @@ static int __init setup_tcm_pool(void) } /* Add the rest of ITCM to the TCM pool */ - if (tcm_status & 0x03) { + if (itcm_present) { if (itcm_pool_start < itcm_end) { ret = gen_pool_add(tcm_pool, itcm_pool_start, itcm_end - itcm_pool_start, -1); -- cgit v1.2.3 From f022e4e41bb339a8bded1063e718d463904ec716 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 1 Jul 2011 08:24:09 +0100 Subject: ARM: 6986/1: mach-realview: add TCM support for PB1176 Enable TCM support on the RealView PB1176 - we have now taken the precautions necessary to support even multi-board builds of RealView systems with TCM enabled. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/mach-realview/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig index b9a9805e4828..dba6d0c1fc17 100644 --- a/arch/arm/mach-realview/Kconfig +++ b/arch/arm/mach-realview/Kconfig @@ -50,6 +50,7 @@ config MACH_REALVIEW_PB1176 bool "Support RealView(R) Platform Baseboard for ARM1176JZF-S" select CPU_V6 select ARM_GIC + select HAVE_TCM help Include support for the ARM(R) RealView(R) Platform Baseboard for ARM1176JZF-S. -- cgit v1.2.3 From eca5dc2a0028d64229aef1b7839bcbae1d864c5f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 1 Jul 2011 14:37:08 +0100 Subject: ARM: 6988/1: multi-cpu: remove arguments from CPU proc macros The macros for invoking functions via the processor struct in the MULTI_CPU case define the arguments as part of the macros, making it impossible to take the address of those functions. This patch removes the arguments from the macro definitions so that we can take the address of these functions like we can for the !MULTI_CPU case. Reported-by: Frank Hofmann Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/proc-fns.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h index 8ec535e11fd7..633d1cb84d87 100644 --- a/arch/arm/include/asm/proc-fns.h +++ b/arch/arm/include/asm/proc-fns.h @@ -82,13 +82,13 @@ extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext); extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); #else -#define cpu_proc_init() processor._proc_init() -#define cpu_proc_fin() processor._proc_fin() -#define cpu_reset(addr) processor.reset(addr) -#define cpu_do_idle() processor._do_idle() -#define cpu_dcache_clean_area(addr,sz) processor.dcache_clean_area(addr,sz) -#define cpu_set_pte_ext(ptep,pte,ext) processor.set_pte_ext(ptep,pte,ext) -#define cpu_do_switch_mm(pgd,mm) processor.switch_mm(pgd,mm) +#define cpu_proc_init processor._proc_init +#define cpu_proc_fin processor._proc_fin +#define cpu_reset processor.reset +#define cpu_do_idle processor._do_idle +#define cpu_dcache_clean_area processor.dcache_clean_area +#define cpu_set_pte_ext processor.set_pte_ext +#define cpu_do_switch_mm processor.switch_mm #endif extern void cpu_resume(void); -- cgit v1.2.3 From 10cdc7e5129ac26aefece4c7a7d5b1a0285237c2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 13 Jun 2011 15:28:53 +0100 Subject: ARM: 6960/1: allow enabling SCU code on UP The scu_power_mode function can be used on UP builds as it drives signals to an SOC power controller. So make it selectable for !SMP. Signed-off-by: Rob Herring Signed-off-by: Russell King --- arch/arm/Kconfig | 1 - arch/arm/kernel/smp_scu.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index cd8f520dd03d..84fda2bebd7a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1349,7 +1349,6 @@ config SMP_ON_UP config HAVE_ARM_SCU bool - depends on SMP help This option enables support for the ARM system coherency unit diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index a1e757c3439b..79ed5e7f204a 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -20,6 +20,7 @@ #define SCU_INVALIDATE 0x0c #define SCU_FPGA_REVISION 0x10 +#ifdef CONFIG_SMP /* * Get the number of CPU cores from the SCU configuration */ @@ -50,6 +51,7 @@ void __init scu_enable(void __iomem *scu_base) */ flush_cache_all(); } +#endif /* * Set the executing CPUs power mode as defined. This will be in -- cgit v1.2.3 From 7fa22bd5460bb2021729fa5a1012c60b9b3a56e2 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 7 Jul 2011 01:56:51 +0100 Subject: ARM: 6993/1: platsmp: Allow secondary cpu hotplug with maxcpus=1 If an ARM system has multiple cpus in the same socket and the kernel is booted with maxcpus=1, secondary cpus are possible but not present due to how platform_smp_prepare_cpus() is called. Since most typical ARM processors don't actually support physical hotplug, initialize the present map to be equal to the possible map in generic ARM SMP code. Also, always call platform_smp_prepare_cpus() as long as max_cpus is non-zero (0 means no SMP) to allow platform code to do any SMP setup. After applying this patch it's possible to boot an ARM system with maxcpus=1 on the command line and then hotplug in secondary cpus via sysfs. This is more in line with how x86 does things. Signed-off-by: Stephen Boyd Cc: Paul Mundt Cc: Kukjin Kim Cc: David Brown Cc: Tony Lindgren Cc: Srinidhi Kasagar Cc: Linus Walleij Signed-off-by: Russell King --- arch/arm/kernel/smp.c | 11 +++++++++-- arch/arm/mach-exynos4/platsmp.c | 8 -------- arch/arm/mach-msm/platsmp.c | 8 -------- arch/arm/mach-omap2/omap-smp.c | 8 -------- arch/arm/mach-realview/platsmp.c | 8 -------- arch/arm/mach-shmobile/platsmp.c | 5 ----- arch/arm/mach-tegra/platsmp.c | 8 -------- arch/arm/mach-ux500/platsmp.c | 8 -------- arch/arm/mach-vexpress/ct-ca9x4.c | 4 ---- 9 files changed, 9 insertions(+), 59 deletions(-) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 344e52b16c8c..0ffcf5c0da43 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -361,14 +361,21 @@ void __init smp_prepare_cpus(unsigned int max_cpus) */ if (max_cpus > ncores) max_cpus = ncores; - - if (max_cpus > 1) { + if (ncores > 1 && max_cpus) { /* * Enable the local timer or broadcast device for the * boot CPU, but only if we have more than one CPU. */ percpu_timer_setup(); + /* + * Initialise the present map, which describes the set of CPUs + * actually populated at the present time. A platform should + * re-initialize the map in platform_smp_prepare_cpus() if + * present != possible (e.g. physical hotplug). + */ + init_cpu_present(&cpu_possible_map); + /* * Initialise the SCU if there are more than one CPU * and let them know where to start. diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c index c5e65a02be8d..b68d5bdf04cf 100644 --- a/arch/arm/mach-exynos4/platsmp.c +++ b/arch/arm/mach-exynos4/platsmp.c @@ -154,14 +154,6 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. - */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); scu_enable(scu_base_addr()); diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 2034098cf015..315b9f365329 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -157,12 +157,4 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. - */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); } diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index ecfe93c4b585..ce65e9329c7b 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -125,14 +125,6 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. - */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); /* * Initialise the SCU and wake up the secondary core using diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c index 963bf0d8119a..4ae943bafa92 100644 --- a/arch/arm/mach-realview/platsmp.c +++ b/arch/arm/mach-realview/platsmp.c @@ -68,14 +68,6 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. - */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); scu_enable(scu_base_addr()); diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index f3888feb1c68..66f980625a33 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -64,10 +64,5 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); - shmobile_smp_prepare_cpus(); } diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index b8ae3c978dee..1a594dce8fbc 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -129,14 +129,6 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. - */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); scu_enable(scu_base); } diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index 0c527fe2cebb..a33df5f4c27a 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -172,14 +172,6 @@ void __init smp_init_cpus(void) void __init platform_smp_prepare_cpus(unsigned int max_cpus) { - int i; - - /* - * Initialise the present map, which describes the set of CPUs - * actually populated at the present time. - */ - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); scu_enable(scu_base_addr()); wakeup_secondary(); diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index 765a71ff7f3b..bfd32f52c2db 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -229,10 +229,6 @@ static void ct_ca9x4_init_cpu_map(void) static void ct_ca9x4_smp_enable(unsigned int max_cpus) { - int i; - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); - scu_enable(MMIO_P2V(A9_MPCORE_SCU)); } #endif -- cgit v1.2.3 From 66a625a88174664fc252d7b1ac1773e76e52326b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:07:40 +0100 Subject: ARM: mm: proc-macros: Add generic proc/cache/tlb struct definition macros This patch adds some generic macros to reduce boilerplate when declaring certain common structures in arch/arm/mm/*.S Thanks to Russell King for outlining what the define_processor_functions macro could look like. Signed-off-by: Dave Martin Acked-by: Nicolas Pitre --- arch/arm/mm/proc-macros.S | 63 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 34261f9486b9..4ae9b4407074 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -254,3 +254,66 @@ mcr p15, 0, r0, c7, c10, 1 @ clean L1 D line mcr p15, 0, ip, c7, c10, 4 @ data write barrier .endm + +.macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0 + .type \name\()_processor_functions, #object + .align 2 +ENTRY(\name\()_processor_functions) + .word \dabort + .word \pabort + .word cpu_\name\()_proc_init + .word cpu_\name\()_proc_fin + .word cpu_\name\()_reset + .word cpu_\name\()_do_idle + .word cpu_\name\()_dcache_clean_area + .word cpu_\name\()_switch_mm + + .if \nommu + .word 0 + .else + .word cpu_\name\()_set_pte_ext + .endif + + .if \suspend + .word cpu_\name\()_suspend_size + .word cpu_\name\()_do_suspend + .word cpu_\name\()_do_resume + .else + .word 0 + .word 0 + .word 0 + .endif + + .size \name\()_processor_functions, . - \name\()_processor_functions +.endm + +.macro define_cache_functions name:req + .align 2 + .type \name\()_cache_fns, #object +ENTRY(\name\()_cache_fns) + .long \name\()_flush_icache_all + .long \name\()_flush_kern_cache_all + .long \name\()_flush_user_cache_all + .long \name\()_flush_user_cache_range + .long \name\()_coherent_kern_range + .long \name\()_coherent_user_range + .long \name\()_flush_kern_dcache_area + .long \name\()_dma_map_area + .long \name\()_dma_unmap_area + .long \name\()_dma_flush_range + .size \name\()_cache_fns, . - \name\()_cache_fns +.endm + +.macro define_tlb_functions name:req, flags_up:req, flags_smp + .type \name\()_tlb_fns, #object +ENTRY(\name\()_tlb_fns) + .long \name\()_flush_user_tlb_range + .long \name\()_flush_kern_tlb_range + .ifnb \flags_smp + ALT_SMP(.long \flags_smp ) + ALT_UP(.long \flags_up ) + .else + .long \flags_up + .endif + .size \name\()_tlb_fns, . - \name\()_tlb_fns +.endm -- cgit v1.2.3 From 8f51965e7033441cb10ce577d1ef2d580a80af08 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:10:05 +0100 Subject: ARM: assembler.h: Add string declaration macro Declaring strings in assembler source involves a certain amount of tedious boilerplate code in order to annotate the resulting symbol correctly. Encapsulating this boilerplate in a macro should help to avoid some duplication and the occasional mistake. Signed-off-by: Dave Martin Acked-by: Nicolas Pitre --- arch/arm/include/asm/assembler.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 65c3f2474f5e..29035e86a59d 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -293,4 +293,13 @@ .macro ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f usracc ldr, \reg, \ptr, \inc, \cond, \rept, \abort .endm + +/* Utility macro for declaring string literals */ + .macro string name:req, string + .type \name , #object +\name: + .asciz "\string" + .size \name , . - \name + .endm + #endif /* __ASM_ASSEMBLER_H__ */ -- cgit v1.2.3 From 9bc7491341040632a660ab5e82dababfa32d67e3 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:11:16 +0100 Subject: ARM: mm: cache-fa: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-fa.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S index 1fa6f71470de..072016371093 100644 --- a/arch/arm/mm/cache-fa.S +++ b/arch/arm/mm/cache-fa.S @@ -242,16 +242,5 @@ ENDPROC(fa_dma_unmap_area) __INITDATA - .type fa_cache_fns, #object -ENTRY(fa_cache_fns) - .long fa_flush_icache_all - .long fa_flush_kern_cache_all - .long fa_flush_user_cache_all - .long fa_flush_user_cache_range - .long fa_coherent_kern_range - .long fa_coherent_user_range - .long fa_flush_kern_dcache_area - .long fa_dma_map_area - .long fa_dma_unmap_area - .long fa_dma_flush_range - .size fa_cache_fns, . - fa_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions fa -- cgit v1.2.3 From 9c373968d64526ca56637ac929f1e4b03e84616b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:13:55 +0100 Subject: ARM: mm: cache-v3: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-v3.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S index 2e2bc406a18d..c2301f226100 100644 --- a/arch/arm/mm/cache-v3.S +++ b/arch/arm/mm/cache-v3.S @@ -129,16 +129,5 @@ ENDPROC(v3_dma_map_area) __INITDATA - .type v3_cache_fns, #object -ENTRY(v3_cache_fns) - .long v3_flush_icache_all - .long v3_flush_kern_cache_all - .long v3_flush_user_cache_all - .long v3_flush_user_cache_range - .long v3_coherent_kern_range - .long v3_coherent_user_range - .long v3_flush_kern_dcache_area - .long v3_dma_map_area - .long v3_dma_unmap_area - .long v3_dma_flush_range - .size v3_cache_fns, . - v3_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions v3 -- cgit v1.2.3 From 54d4e9ebbc73baf451e52ef2754224ae6c887dbd Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:14:52 +0100 Subject: ARM: mm: cache-v4: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-v4.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index a8fefb523f19..fd9bb7addc8d 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -141,16 +141,5 @@ ENDPROC(v4_dma_map_area) __INITDATA - .type v4_cache_fns, #object -ENTRY(v4_cache_fns) - .long v4_flush_icache_all - .long v4_flush_kern_cache_all - .long v4_flush_user_cache_all - .long v4_flush_user_cache_range - .long v4_coherent_kern_range - .long v4_coherent_user_range - .long v4_flush_kern_dcache_area - .long v4_dma_map_area - .long v4_dma_unmap_area - .long v4_dma_flush_range - .size v4_cache_fns, . - v4_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions v4 -- cgit v1.2.3 From eec95e56e6b73cd64468401ce171e70c825b246a Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:15:17 +0100 Subject: ARM: mm: cache-v4wb: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-v4wb.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S index f40c69656d8d..4f2c14151ccb 100644 --- a/arch/arm/mm/cache-v4wb.S +++ b/arch/arm/mm/cache-v4wb.S @@ -253,16 +253,5 @@ ENDPROC(v4wb_dma_unmap_area) __INITDATA - .type v4wb_cache_fns, #object -ENTRY(v4wb_cache_fns) - .long v4wb_flush_icache_all - .long v4wb_flush_kern_cache_all - .long v4wb_flush_user_cache_all - .long v4wb_flush_user_cache_range - .long v4wb_coherent_kern_range - .long v4wb_coherent_user_range - .long v4wb_flush_kern_dcache_area - .long v4wb_dma_map_area - .long v4wb_dma_unmap_area - .long v4wb_dma_flush_range - .size v4wb_cache_fns, . - v4wb_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions v4wb -- cgit v1.2.3 From d5b5b2e2f8ed10d747854a78f6fab74315eb3607 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:15:44 +0100 Subject: ARM: mm: cache-v4wt: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-v4wt.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S index a7b276dbda11..4d7b467631ce 100644 --- a/arch/arm/mm/cache-v4wt.S +++ b/arch/arm/mm/cache-v4wt.S @@ -197,16 +197,5 @@ ENDPROC(v4wt_dma_map_area) __INITDATA - .type v4wt_cache_fns, #object -ENTRY(v4wt_cache_fns) - .long v4wt_flush_icache_all - .long v4wt_flush_kern_cache_all - .long v4wt_flush_user_cache_all - .long v4wt_flush_user_cache_range - .long v4wt_coherent_kern_range - .long v4wt_coherent_user_range - .long v4wt_flush_kern_dcache_area - .long v4wt_dma_map_area - .long v4wt_dma_unmap_area - .long v4wt_dma_flush_range - .size v4wt_cache_fns, . - v4wt_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions v4wt -- cgit v1.2.3 From 641d8233a68e5b465d720d2c5e2f20f580d2797e Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:16:04 +0100 Subject: ARM: mm: cache-v6: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-v6.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index 73b4a8b66a57..74c2e5a33a4d 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -330,16 +330,5 @@ ENDPROC(v6_dma_unmap_area) __INITDATA - .type v6_cache_fns, #object -ENTRY(v6_cache_fns) - .long v6_flush_icache_all - .long v6_flush_kern_cache_all - .long v6_flush_user_cache_all - .long v6_flush_user_cache_range - .long v6_coherent_kern_range - .long v6_coherent_user_range - .long v6_flush_kern_dcache_area - .long v6_dma_map_area - .long v6_dma_unmap_area - .long v6_dma_flush_range - .size v6_cache_fns, . - v6_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions v6 -- cgit v1.2.3 From 455a01ec30e19bd21e36adc5c109ce879c16628a Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:16:25 +0100 Subject: ARM: mm: cache-v7: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/cache-v7.S | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index d32f02b61866..3b24bfa3b828 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -325,16 +325,5 @@ ENDPROC(v7_dma_unmap_area) __INITDATA - .type v7_cache_fns, #object -ENTRY(v7_cache_fns) - .long v7_flush_icache_all - .long v7_flush_kern_cache_all - .long v7_flush_user_cache_all - .long v7_flush_user_cache_range - .long v7_coherent_kern_range - .long v7_coherent_user_range - .long v7_flush_kern_dcache_area - .long v7_dma_map_area - .long v7_dma_unmap_area - .long v7_dma_flush_range - .size v7_cache_fns, . - v7_cache_fns + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions v7 -- cgit v1.2.3 From 56d916509bf5ec3f5342692d31556e822301029e Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:16:44 +0100 Subject: ARM: mm: proc-arm1020: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm1020.S | 45 ++++++--------------------------------------- 1 file changed, 6 insertions(+), 39 deletions(-) diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index 6c4e7fd6c8af..67469665d47a 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -364,17 +364,8 @@ ENTRY(arm1020_dma_unmap_area) mov pc, lr ENDPROC(arm1020_dma_unmap_area) -ENTRY(arm1020_cache_fns) - .long arm1020_flush_icache_all - .long arm1020_flush_kern_cache_all - .long arm1020_flush_user_cache_all - .long arm1020_flush_user_cache_range - .long arm1020_coherent_kern_range - .long arm1020_coherent_user_range - .long arm1020_flush_kern_dcache_area - .long arm1020_dma_map_area - .long arm1020_dma_unmap_area - .long arm1020_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm1020 .align 5 ENTRY(cpu_arm1020_dcache_clean_area) @@ -477,38 +468,14 @@ arm1020_crval: crval clear=0x0000593f, mmuset=0x00003935, ucset=0x00001930 __INITDATA + @ define struct processor (see and proc-macros.S) + define_processor_functions arm1020, dabort=v4t_early_abort, pabort=legacy_pabort -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm1020_processor_functions, #object -arm1020_processor_functions: - .word v4t_early_abort - .word legacy_pabort - .word cpu_arm1020_proc_init - .word cpu_arm1020_proc_fin - .word cpu_arm1020_reset - .word cpu_arm1020_do_idle - .word cpu_arm1020_dcache_clean_area - .word cpu_arm1020_switch_mm - .word cpu_arm1020_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm1020_processor_functions, . - arm1020_processor_functions .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name + string cpu_arch_name, "armv5t" + string cpu_elf_name, "v5" .type cpu_arm1020_name, #object cpu_arm1020_name: -- cgit v1.2.3 From fbaa8407304b28d9e768134cfa4188df6520149c Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:17:00 +0100 Subject: ARM: mm: proc-arm1020e: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm1020e.S | 52 ++++++--------------------------------------- 1 file changed, 7 insertions(+), 45 deletions(-) diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index 4ce947c19623..4251421c0ed5 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -350,17 +350,8 @@ ENTRY(arm1020e_dma_unmap_area) mov pc, lr ENDPROC(arm1020e_dma_unmap_area) -ENTRY(arm1020e_cache_fns) - .long arm1020e_flush_icache_all - .long arm1020e_flush_kern_cache_all - .long arm1020e_flush_user_cache_all - .long arm1020e_flush_user_cache_range - .long arm1020e_coherent_kern_range - .long arm1020e_coherent_user_range - .long arm1020e_flush_kern_dcache_area - .long arm1020e_dma_map_area - .long arm1020e_dma_unmap_area - .long arm1020e_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm1020e .align 5 ENTRY(cpu_arm1020e_dcache_clean_area) @@ -458,43 +449,14 @@ arm1020e_crval: crval clear=0x00007f3f, mmuset=0x00003935, ucset=0x00001930 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm1020e_processor_functions, #object -arm1020e_processor_functions: - .word v4t_early_abort - .word legacy_pabort - .word cpu_arm1020e_proc_init - .word cpu_arm1020e_proc_fin - .word cpu_arm1020e_reset - .word cpu_arm1020e_do_idle - .word cpu_arm1020e_dcache_clean_area - .word cpu_arm1020e_switch_mm - .word cpu_arm1020e_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm1020e_processor_functions, . - arm1020e_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm1020e, dabort=v4t_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm1020e_name, #object -cpu_arm1020e_name: - .asciz "ARM1020E" - .size cpu_arm1020e_name, . - cpu_arm1020e_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + string cpu_arm1020e_name, "ARM1020E" .align -- cgit v1.2.3 From f2d8cae1d56a28d4b2bcdaa4a6f7d551fd94be60 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:17:29 +0100 Subject: ARM: mm: proc-arm1022: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm1022.S | 52 +++++++--------------------------------------- 1 file changed, 7 insertions(+), 45 deletions(-) diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S index c8884c5413a2..d283cf3d06e3 100644 --- a/arch/arm/mm/proc-arm1022.S +++ b/arch/arm/mm/proc-arm1022.S @@ -339,17 +339,8 @@ ENTRY(arm1022_dma_unmap_area) mov pc, lr ENDPROC(arm1022_dma_unmap_area) -ENTRY(arm1022_cache_fns) - .long arm1022_flush_icache_all - .long arm1022_flush_kern_cache_all - .long arm1022_flush_user_cache_all - .long arm1022_flush_user_cache_range - .long arm1022_coherent_kern_range - .long arm1022_coherent_user_range - .long arm1022_flush_kern_dcache_area - .long arm1022_dma_map_area - .long arm1022_dma_unmap_area - .long arm1022_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm1022 .align 5 ENTRY(cpu_arm1022_dcache_clean_area) @@ -441,43 +432,14 @@ arm1022_crval: crval clear=0x00007f3f, mmuset=0x00003935, ucset=0x00001930 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm1022_processor_functions, #object -arm1022_processor_functions: - .word v4t_early_abort - .word legacy_pabort - .word cpu_arm1022_proc_init - .word cpu_arm1022_proc_fin - .word cpu_arm1022_reset - .word cpu_arm1022_do_idle - .word cpu_arm1022_dcache_clean_area - .word cpu_arm1022_switch_mm - .word cpu_arm1022_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm1022_processor_functions, . - arm1022_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm1022, dabort=v4t_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm1022_name, #object -cpu_arm1022_name: - .asciz "ARM1022" - .size cpu_arm1022_name, . - cpu_arm1022_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + string cpu_arm1022_name, "ARM1022" .align -- cgit v1.2.3 From 5c9369bc2efe7d68f4dfdaa449f915f7cf6a8275 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:18:11 +0100 Subject: ARM: mm: proc-arm1026: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm1026.S | 53 ++++++---------------------------------------- 1 file changed, 7 insertions(+), 46 deletions(-) diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S index 413684660aad..678a1ceafed2 100644 --- a/arch/arm/mm/proc-arm1026.S +++ b/arch/arm/mm/proc-arm1026.S @@ -333,17 +333,8 @@ ENTRY(arm1026_dma_unmap_area) mov pc, lr ENDPROC(arm1026_dma_unmap_area) -ENTRY(arm1026_cache_fns) - .long arm1026_flush_icache_all - .long arm1026_flush_kern_cache_all - .long arm1026_flush_user_cache_all - .long arm1026_flush_user_cache_range - .long arm1026_coherent_kern_range - .long arm1026_coherent_user_range - .long arm1026_flush_kern_dcache_area - .long arm1026_dma_map_area - .long arm1026_dma_unmap_area - .long arm1026_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm1026 .align 5 ENTRY(cpu_arm1026_dcache_clean_area) @@ -436,45 +427,15 @@ arm1026_crval: crval clear=0x00007f3f, mmuset=0x00003935, ucset=0x00001934 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm1026_processor_functions, #object -arm1026_processor_functions: - .word v5t_early_abort - .word legacy_pabort - .word cpu_arm1026_proc_init - .word cpu_arm1026_proc_fin - .word cpu_arm1026_reset - .word cpu_arm1026_do_idle - .word cpu_arm1026_dcache_clean_area - .word cpu_arm1026_switch_mm - .word cpu_arm1026_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm1026_processor_functions, . - arm1026_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm1026, dabort=v5t_early_abort, pabort=legacy_pabort .section .rodata - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5tej" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name + string cpu_arch_name, "armv5tej" + string cpu_elf_name, "v5" .align - - .type cpu_arm1026_name, #object -cpu_arm1026_name: - .asciz "ARM1026EJ-S" - .size cpu_arm1026_name, . - cpu_arm1026_name - + string cpu_arm1026_name, "ARM1026EJ-S" .align .section ".proc.info.init", #alloc, #execinstr -- cgit v1.2.3 From c3be06eb587fedafe1efd33783d376157f96e5a6 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:18:31 +0100 Subject: ARM: mm: proc-arm6_7: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm6_7.S | 166 +++++++++------------------------------------- 1 file changed, 32 insertions(+), 134 deletions(-) diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index 5f79dc4ce3fb..ebc0ca7f1a15 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -269,159 +269,57 @@ __arm7_setup: mov r0, #0 __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm6_processor_functions, #object -ENTRY(arm6_processor_functions) - .word cpu_arm6_data_abort - .word legacy_pabort - .word cpu_arm6_proc_init - .word cpu_arm6_proc_fin - .word cpu_arm6_reset - .word cpu_arm6_do_idle - .word cpu_arm6_dcache_clean_area - .word cpu_arm6_switch_mm - .word cpu_arm6_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm6_processor_functions, . - arm6_processor_functions - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm7_processor_functions, #object -ENTRY(arm7_processor_functions) - .word cpu_arm7_data_abort - .word legacy_pabort - .word cpu_arm7_proc_init - .word cpu_arm7_proc_fin - .word cpu_arm7_reset - .word cpu_arm7_do_idle - .word cpu_arm7_dcache_clean_area - .word cpu_arm7_switch_mm - .word cpu_arm7_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm7_processor_functions, . - arm7_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm6, dabort=cpu_arm6_data_abort, pabort=legacy_pabort + define_processor_functions arm7, dabort=cpu_arm7_data_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: .asciz "armv3" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: .asciz "v3" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm6_name, #object -cpu_arm6_name: .asciz "ARM6" - .size cpu_arm6_name, . - cpu_arm6_name - - .type cpu_arm610_name, #object -cpu_arm610_name: - .asciz "ARM610" - .size cpu_arm610_name, . - cpu_arm610_name - - .type cpu_arm7_name, #object -cpu_arm7_name: .asciz "ARM7" - .size cpu_arm7_name, . - cpu_arm7_name - - .type cpu_arm710_name, #object -cpu_arm710_name: - .asciz "ARM710" - .size cpu_arm710_name, . - cpu_arm710_name + string cpu_arch_name, "armv3" + string cpu_elf_name, "v3" + string cpu_arm6_name, "ARM6" + string cpu_arm610_name, "ARM610" + string cpu_arm7_name, "ARM7" + string cpu_arm710_name, "ARM710" .align .section ".proc.info.init", #alloc, #execinstr - .type __arm6_proc_info, #object -__arm6_proc_info: - .long 0x41560600 - .long 0xfffffff0 - .long 0x00000c1e +.macro arm67_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, \ + cpu_mm_mmu_flags:req, cpu_flush:req, cpu_proc_funcs:req + .type __\name\()_proc_info, #object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask + .long \cpu_mm_mmu_flags .long PMD_TYPE_SECT | \ PMD_BIT4 | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - b __arm6_setup + b \cpu_flush .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP | HWCAP_26BIT - .long cpu_arm6_name - .long arm6_processor_functions + .long \cpu_name + .long \cpu_proc_funcs .long v3_tlb_fns .long v3_user_fns .long v3_cache_fns - .size __arm6_proc_info, . - __arm6_proc_info - - .type __arm610_proc_info, #object -__arm610_proc_info: - .long 0x41560610 - .long 0xfffffff0 - .long 0x00000c1e - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __arm6_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_26BIT - .long cpu_arm610_name - .long arm6_processor_functions - .long v3_tlb_fns - .long v3_user_fns - .long v3_cache_fns - .size __arm610_proc_info, . - __arm610_proc_info - - .type __arm7_proc_info, #object -__arm7_proc_info: - .long 0x41007000 - .long 0xffffff00 - .long 0x00000c1e - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __arm7_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_26BIT - .long cpu_arm7_name - .long arm7_processor_functions - .long v3_tlb_fns - .long v3_user_fns - .long v3_cache_fns - .size __arm7_proc_info, . - __arm7_proc_info - - .type __arm710_proc_info, #object -__arm710_proc_info: - .long 0x41007100 - .long 0xfff8ff00 - .long PMD_TYPE_SECT | \ + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm + + arm67_proc_info arm6, 0x41560600, 0xfffffff0, cpu_arm6_name, \ + 0x00000c1e, __arm6_setup, arm6_processor_functions + arm67_proc_info arm610, 0x41560610, 0xfffffff0, cpu_arm610_name, \ + 0x00000c1e, __arm6_setup, arm6_processor_functions + arm67_proc_info arm7, 0x41007000, 0xffffff00, cpu_arm7_name, \ + 0x00000c1e, __arm7_setup, arm7_processor_functions + arm67_proc_info arm710, 0x41007100, 0xfff8ff00, cpu_arm710_name, \ + PMD_TYPE_SECT | \ PMD_SECT_BUFFERABLE | \ PMD_SECT_CACHEABLE | \ PMD_BIT4 | \ PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __arm7_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_26BIT - .long cpu_arm710_name - .long arm7_processor_functions - .long v3_tlb_fns - .long v3_user_fns - .long v3_cache_fns - .size __arm710_proc_info, . - __arm710_proc_info + PMD_SECT_AP_READ, \ + __arm7_setup, arm7_processor_functions -- cgit v1.2.3 From 449870b1de24d967a571b0e38cd2635c49af2785 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:18:56 +0100 Subject: ARM: mm: proc-arm720: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm720.S | 85 ++++++++++------------------------------------- 1 file changed, 17 insertions(+), 68 deletions(-) diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S index 7a06e5964f59..55f4e290665a 100644 --- a/arch/arm/mm/proc-arm720.S +++ b/arch/arm/mm/proc-arm720.S @@ -169,46 +169,15 @@ arm720_crval: crval clear=0x00002f3f, mmuset=0x0000213d, ucset=0x00000130 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm720_processor_functions, #object -ENTRY(arm720_processor_functions) - .word v4t_late_abort - .word legacy_pabort - .word cpu_arm720_proc_init - .word cpu_arm720_proc_fin - .word cpu_arm720_reset - .word cpu_arm720_do_idle - .word cpu_arm720_dcache_clean_area - .word cpu_arm720_switch_mm - .word cpu_arm720_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm720_processor_functions, . - arm720_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm720, dabort=v4t_late_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm710_name, #object -cpu_arm710_name: - .asciz "ARM710T" - .size cpu_arm710_name, . - cpu_arm710_name - - .type cpu_arm720_name, #object -cpu_arm720_name: - .asciz "ARM720T" - .size cpu_arm720_name, . - cpu_arm720_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm710_name, "ARM710T" + string cpu_arm720_name, "ARM720T" .align @@ -218,10 +187,11 @@ cpu_arm720_name: .section ".proc.info.init", #alloc, #execinstr - .type __arm710_proc_info, #object -__arm710_proc_info: - .long 0x41807100 @ cpu_val - .long 0xffffff00 @ cpu_mask +.macro arm720_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cpu_flush:req + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long PMD_TYPE_SECT | \ PMD_SECT_BUFFERABLE | \ PMD_SECT_CACHEABLE | \ @@ -232,38 +202,17 @@ __arm710_proc_info: PMD_BIT4 | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - b __arm710_setup @ cpu_flush + b \cpu_flush @ cpu_flush .long cpu_arch_name @ arch_name .long cpu_elf_name @ elf_name .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB @ elf_hwcap - .long cpu_arm710_name @ name + .long \cpu_name .long arm720_processor_functions .long v4_tlb_fns .long v4wt_user_fns .long v4_cache_fns - .size __arm710_proc_info, . - __arm710_proc_info + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm - .type __arm720_proc_info, #object -__arm720_proc_info: - .long 0x41807200 @ cpu_val - .long 0xffffff00 @ cpu_mask - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __arm720_setup @ cpu_flush - .long cpu_arch_name @ arch_name - .long cpu_elf_name @ elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB @ elf_hwcap - .long cpu_arm720_name @ name - .long arm720_processor_functions - .long v4_tlb_fns - .long v4wt_user_fns - .long v4_cache_fns - .size __arm720_proc_info, . - __arm720_proc_info + arm720_proc_info arm710, 0x41807100, 0xffffff00, cpu_arm710_name, __arm710_setup + arm720_proc_info arm720, 0x41807200, 0xffffff00, cpu_arm720_name, __arm720_setup -- cgit v1.2.3 From 4cc1f0fa06529aaba6c48d06b4257576474a9d33 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:19:11 +0100 Subject: ARM: mm: proc-arm740: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm740.S | 42 +++++++----------------------------------- 1 file changed, 7 insertions(+), 35 deletions(-) diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index 6f9d12effee1..4506be3adda6 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -17,6 +17,8 @@ #include #include +#include "proc-macros.S" + .text /* * cpu_arm740_proc_init() @@ -115,42 +117,14 @@ __arm740_setup: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm740_processor_functions, #object -ENTRY(arm740_processor_functions) - .word v4t_late_abort - .word legacy_pabort - .word cpu_arm740_proc_init - .word cpu_arm740_proc_fin - .word cpu_arm740_reset - .word cpu_arm740_do_idle - .word cpu_arm740_dcache_clean_area - .word cpu_arm740_switch_mm - .word 0 @ cpu_*_set_pte - .word 0 - .word 0 - .word 0 - .size arm740_processor_functions, . - arm740_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm740, dabort=v4t_late_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm740_name, #object -cpu_arm740_name: - .ascii "ARM740T" - .size cpu_arm740_name, . - cpu_arm740_name + string cpu_arch_name, "armv4" + string cpu_elf_name, "v4" + string cpu_arm740_name, "ARM740T" .align @@ -170,5 +144,3 @@ __arm740_proc_info: .long 0 .long v3_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info - - -- cgit v1.2.3 From fd10e2725efba154fb610845d846fc03155203f3 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:19:26 +0100 Subject: ARM: mm: proc-arm7tdmi: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm7tdmi.S | 216 ++++++++------------------------------------ 1 file changed, 39 insertions(+), 177 deletions(-) diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index 537ffcb0646d..7e0e1fe4ed4d 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -17,6 +17,8 @@ #include #include +#include "proc-macros.S" + .text /* * cpu_arm7tdmi_proc_init() @@ -55,197 +57,57 @@ __arm7tdmi_setup: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm7tdmi_processor_functions, #object -ENTRY(arm7tdmi_processor_functions) - .word v4t_late_abort - .word legacy_pabort - .word cpu_arm7tdmi_proc_init - .word cpu_arm7tdmi_proc_fin - .word cpu_arm7tdmi_reset - .word cpu_arm7tdmi_do_idle - .word cpu_arm7tdmi_dcache_clean_area - .word cpu_arm7tdmi_switch_mm - .word 0 @ cpu_*_set_pte - .word 0 - .word 0 - .word 0 - .size arm7tdmi_processor_functions, . - arm7tdmi_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm7tdmi, dabort=v4t_late_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm7tdmi_name, #object -cpu_arm7tdmi_name: - .asciz "ARM7TDMI" - .size cpu_arm7tdmi_name, . - cpu_arm7tdmi_name - - .type cpu_triscenda7_name, #object -cpu_triscenda7_name: - .asciz "Triscend-A7x" - .size cpu_triscenda7_name, . - cpu_triscenda7_name - - .type cpu_at91_name, #object -cpu_at91_name: - .asciz "Atmel-AT91M40xxx" - .size cpu_at91_name, . - cpu_at91_name - - .type cpu_s3c3410_name, #object -cpu_s3c3410_name: - .asciz "Samsung-S3C3410" - .size cpu_s3c3410_name, . - cpu_s3c3410_name - - .type cpu_s3c44b0x_name, #object -cpu_s3c44b0x_name: - .asciz "Samsung-S3C44B0x" - .size cpu_s3c44b0x_name, . - cpu_s3c44b0x_name - - .type cpu_s3c4510b, #object -cpu_s3c4510b_name: - .asciz "Samsung-S3C4510B" - .size cpu_s3c4510b_name, . - cpu_s3c4510b_name - - .type cpu_s3c4530_name, #object -cpu_s3c4530_name: - .asciz "Samsung-S3C4530" - .size cpu_s3c4530_name, . - cpu_s3c4530_name - - .type cpu_netarm_name, #object -cpu_netarm_name: - .asciz "NETARM" - .size cpu_netarm_name, . - cpu_netarm_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm7tdmi_name, "ARM7TDMI" + string cpu_triscenda7_name, "Triscend-A7x" + string cpu_at91_name, "Atmel-AT91M40xxx" + string cpu_s3c3410_name, "Samsung-S3C3410" + string cpu_s3c44b0x_name, "Samsung-S3C44B0x" + string cpu_s3c4510b_name, "Samsung-S3C4510B" + string cpu_s3c4530_name, "Samsung-S3C4530" + string cpu_netarm_name, "NETARM" .align .section ".proc.info.init", #alloc, #execinstr - .type __arm7tdmi_proc_info, #object -__arm7tdmi_proc_info: - .long 0x41007700 - .long 0xfff8ff00 - .long 0 - .long 0 - b __arm7tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_26BIT - .long cpu_arm7tdmi_name - .long arm7tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __arm7tdmi_proc_info, . - __arm7tdmi_proc_info - - .type __triscenda7_proc_info, #object -__triscenda7_proc_info: - .long 0x0001d2ff - .long 0x0001ffff - .long 0 - .long 0 - b __arm7tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_triscenda7_name - .long arm7tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __triscenda7_proc_info, . - __triscenda7_proc_info - - .type __at91_proc_info, #object -__at91_proc_info: - .long 0x14000040 - .long 0xfff000e0 - .long 0 - .long 0 - b __arm7tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_at91_name - .long arm7tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __at91_proc_info, . - __at91_proc_info - - .type __s3c4510b_proc_info, #object -__s3c4510b_proc_info: - .long 0x36365000 - .long 0xfffff000 - .long 0 - .long 0 - b __arm7tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_s3c4510b_name - .long arm7tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __s3c4510b_proc_info, . - __s3c4510b_proc_info - - .type __s3c4530_proc_info, #object -__s3c4530_proc_info: - .long 0x4c000000 - .long 0xfff000e0 - .long 0 - .long 0 - b __arm7tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_s3c4530_name - .long arm7tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __s3c4530_proc_info, . - __s3c4530_proc_info - - .type __s3c3410_proc_info, #object -__s3c3410_proc_info: - .long 0x34100000 - .long 0xffff0000 - .long 0 - .long 0 - b __arm7tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_s3c3410_name - .long arm7tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __s3c3410_proc_info, . - __s3c3410_proc_info - - .type __s3c44b0x_proc_info, #object -__s3c44b0x_proc_info: - .long 0x44b00000 - .long 0xffff0000 +.macro arm7tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, \ + extra_hwcaps=0 + .type __\name\()_proc_info, #object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long 0 .long 0 b __arm7tdmi_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_s3c44b0x_name + .long HWCAP_SWP | HWCAP_26BIT | ( \extra_hwcaps ) + .long \cpu_name .long arm7tdmi_processor_functions .long 0 .long 0 .long v4_cache_fns - .size __s3c44b0x_proc_info, . - __s3c44b0x_proc_info + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm + + arm7tdmi_proc_info arm7tdmi, 0x41007700, 0xfff8ff00, \ + cpu_arm7tdmi_name + arm7tdmi_proc_info triscenda7, 0x0001d2ff, 0x0001ffff, \ + cpu_triscenda7_name, extra_hwcaps=HWCAP_THUMB + arm7tdmi_proc_info at91, 0x14000040, 0xfff000e0, \ + cpu_at91_name, extra_hwcaps=HWCAP_THUMB + arm7tdmi_proc_info s3c4510b, 0x36365000, 0xfffff000, \ + cpu_s3c4510b_name, extra_hwcaps=HWCAP_THUMB + arm7tdmi_proc_info s3c4530, 0x4c000000, 0xfff000e0, \ + cpu_s3c4530_name, extra_hwcaps=HWCAP_THUMB + arm7tdmi_proc_info s3c3410, 0x34100000, 0xffff0000, \ + cpu_s3c3410_name, extra_hwcaps=HWCAP_THUMB + arm7tdmi_proc_info s3c44b0x, 0x44b00000, 0xffff0000, \ + cpu_s3c44b0x_name, extra_hwcaps=HWCAP_THUMB -- cgit v1.2.3 From 68f5e1acb527b3c64a0252ef84b3827bfb48ec00 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:19:48 +0100 Subject: ARM: mm: proc-arm920: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm920.S | 53 +++++++---------------------------------------- 1 file changed, 7 insertions(+), 46 deletions(-) diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index bf8a1d1cccb6..0dea376feaaa 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -315,18 +315,8 @@ ENTRY(arm920_dma_unmap_area) mov pc, lr ENDPROC(arm920_dma_unmap_area) -ENTRY(arm920_cache_fns) - .long arm920_flush_icache_all - .long arm920_flush_kern_cache_all - .long arm920_flush_user_cache_all - .long arm920_flush_user_cache_range - .long arm920_coherent_kern_range - .long arm920_coherent_user_range - .long arm920_flush_kern_dcache_area - .long arm920_dma_map_area - .long arm920_dma_unmap_area - .long arm920_dma_flush_range - + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm920 #endif @@ -450,43 +440,14 @@ arm920_crval: crval clear=0x00003f3f, mmuset=0x00003135, ucset=0x00001130 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm920_processor_functions, #object -arm920_processor_functions: - .word v4t_early_abort - .word legacy_pabort - .word cpu_arm920_proc_init - .word cpu_arm920_proc_fin - .word cpu_arm920_reset - .word cpu_arm920_do_idle - .word cpu_arm920_dcache_clean_area - .word cpu_arm920_switch_mm - .word cpu_arm920_set_pte_ext - .word cpu_arm920_suspend_size - .word cpu_arm920_do_suspend - .word cpu_arm920_do_resume - .size arm920_processor_functions, . - arm920_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm920, dabort=v4t_early_abort, pabort=legacy_pabort, suspend=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm920_name, #object -cpu_arm920_name: - .asciz "ARM920T" - .size cpu_arm920_name, . - cpu_arm920_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm920_name, "ARM920T" .align -- cgit v1.2.3 From f3e7383f2a97879cfd21a427350ceac1cfd1f9bc Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:20:07 +0100 Subject: ARM: mm: proc-arm922: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm922.S | 53 +++++++---------------------------------------- 1 file changed, 7 insertions(+), 46 deletions(-) diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index 95ba1fc56e4d..490e18833857 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -317,18 +317,8 @@ ENTRY(arm922_dma_unmap_area) mov pc, lr ENDPROC(arm922_dma_unmap_area) -ENTRY(arm922_cache_fns) - .long arm922_flush_icache_all - .long arm922_flush_kern_cache_all - .long arm922_flush_user_cache_all - .long arm922_flush_user_cache_range - .long arm922_coherent_kern_range - .long arm922_coherent_user_range - .long arm922_flush_kern_dcache_area - .long arm922_dma_map_area - .long arm922_dma_unmap_area - .long arm922_dma_flush_range - + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm922 #endif @@ -420,43 +410,14 @@ arm922_crval: crval clear=0x00003f3f, mmuset=0x00003135, ucset=0x00001130 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm922_processor_functions, #object -arm922_processor_functions: - .word v4t_early_abort - .word legacy_pabort - .word cpu_arm922_proc_init - .word cpu_arm922_proc_fin - .word cpu_arm922_reset - .word cpu_arm922_do_idle - .word cpu_arm922_dcache_clean_area - .word cpu_arm922_switch_mm - .word cpu_arm922_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm922_processor_functions, . - arm922_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm922, dabort=v4t_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm922_name, #object -cpu_arm922_name: - .asciz "ARM922T" - .size cpu_arm922_name, . - cpu_arm922_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm922_name, "ARM922T" .align -- cgit v1.2.3 From 6c240aec6fdcafd55905ae0b61d5047252da92d4 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:20:31 +0100 Subject: ARM: mm: proc-arm925: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm925.S | 88 +++++++++-------------------------------------- 1 file changed, 16 insertions(+), 72 deletions(-) diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 541e4774eea1..51d494be057e 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -372,17 +372,8 @@ ENTRY(arm925_dma_unmap_area) mov pc, lr ENDPROC(arm925_dma_unmap_area) -ENTRY(arm925_cache_fns) - .long arm925_flush_icache_all - .long arm925_flush_kern_cache_all - .long arm925_flush_user_cache_all - .long arm925_flush_user_cache_range - .long arm925_coherent_kern_range - .long arm925_coherent_user_range - .long arm925_flush_kern_dcache_area - .long arm925_dma_map_area - .long arm925_dma_unmap_area - .long arm925_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm925 ENTRY(cpu_arm925_dcache_clean_area) #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH @@ -487,52 +478,24 @@ arm925_crval: crval clear=0x00007f3f, mmuset=0x0000313d, ucset=0x00001130 __INITDATA - -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm925_processor_functions, #object -arm925_processor_functions: - .word v4t_early_abort - .word legacy_pabort - .word cpu_arm925_proc_init - .word cpu_arm925_proc_fin - .word cpu_arm925_reset - .word cpu_arm925_do_idle - .word cpu_arm925_dcache_clean_area - .word cpu_arm925_switch_mm - .word cpu_arm925_set_pte_ext - .word 0 - .word 0 - .word 0 - .size arm925_processor_functions, . - arm925_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm925, dabort=v4t_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm925_name, #object -cpu_arm925_name: - .asciz "ARM925T" - .size cpu_arm925_name, . - cpu_arm925_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm925_name, "ARM925T" .align .section ".proc.info.init", #alloc, #execinstr - .type __arm925_proc_info,#object -__arm925_proc_info: - .long 0x54029250 - .long 0xfffffff0 +.macro arm925_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long PMD_TYPE_SECT | \ PMD_BIT4 | \ PMD_SECT_AP_WRITE | \ @@ -550,27 +513,8 @@ __arm925_proc_info: .long v4wbi_tlb_fns .long v4wb_user_fns .long arm925_cache_fns - .size __arm925_proc_info, . - __arm925_proc_info + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm - .type __arm915_proc_info,#object -__arm915_proc_info: - .long 0x54029150 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __arm925_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB - .long cpu_arm925_name - .long arm925_processor_functions - .long v4wbi_tlb_fns - .long v4wb_user_fns - .long arm925_cache_fns - .size __arm925_proc_info, . - __arm925_proc_info + arm925_proc_info arm925, 0x54029250, 0xfffffff0, cpu_arm925_name + arm925_proc_info arm915, 0x54029150, 0xfffffff0, cpu_arm925_name -- cgit v1.2.3 From be90da45a97ac833d92eb9cd8b06df3bc5cf561b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:20:46 +0100 Subject: ARM: mm: proc-arm926: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm926.S | 51 +++++++---------------------------------------- 1 file changed, 7 insertions(+), 44 deletions(-) diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 0ed85d930c09..b2f9bde8ecef 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -335,17 +335,8 @@ ENTRY(arm926_dma_unmap_area) mov pc, lr ENDPROC(arm926_dma_unmap_area) -ENTRY(arm926_cache_fns) - .long arm926_flush_icache_all - .long arm926_flush_kern_cache_all - .long arm926_flush_user_cache_all - .long arm926_flush_user_cache_range - .long arm926_coherent_kern_range - .long arm926_coherent_user_range - .long arm926_flush_kern_dcache_area - .long arm926_dma_map_area - .long arm926_dma_unmap_area - .long arm926_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm926 ENTRY(cpu_arm926_dcache_clean_area) #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH @@ -475,42 +466,14 @@ arm926_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm926_processor_functions, #object -arm926_processor_functions: - .word v5tj_early_abort - .word legacy_pabort - .word cpu_arm926_proc_init - .word cpu_arm926_proc_fin - .word cpu_arm926_reset - .word cpu_arm926_do_idle - .word cpu_arm926_dcache_clean_area - .word cpu_arm926_switch_mm - .word cpu_arm926_set_pte_ext - .word cpu_arm926_suspend_size - .word cpu_arm926_do_suspend - .word cpu_arm926_do_resume - .size arm926_processor_functions, . - arm926_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm926, dabort=v5tj_early_abort, pabort=legacy_pabort, suspend=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5tej" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm926_name, #object -cpu_arm926_name: - .asciz "ARM926EJ-S" - .size cpu_arm926_name, . - cpu_arm926_name + string cpu_arch_name, "armv5tej" + string cpu_elf_name, "v5" + string cpu_arm926_name, "ARM926EJ-S" .align -- cgit v1.2.3 From b3755801479a7b6c61dec5e49897486805d003a5 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:21:02 +0100 Subject: ARM: mm: proc-arm940: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm940.S | 51 +++++++---------------------------------------- 1 file changed, 7 insertions(+), 44 deletions(-) diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S index 26aea3f71c26..ac750d506153 100644 --- a/arch/arm/mm/proc-arm940.S +++ b/arch/arm/mm/proc-arm940.S @@ -264,17 +264,8 @@ ENTRY(arm940_dma_unmap_area) mov pc, lr ENDPROC(arm940_dma_unmap_area) -ENTRY(arm940_cache_fns) - .long arm940_flush_icache_all - .long arm940_flush_kern_cache_all - .long arm940_flush_user_cache_all - .long arm940_flush_user_cache_range - .long arm940_coherent_kern_range - .long arm940_coherent_user_range - .long arm940_flush_kern_dcache_area - .long arm940_dma_map_area - .long arm940_dma_unmap_area - .long arm940_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm940 __CPUINIT @@ -348,42 +339,14 @@ __arm940_setup: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm940_processor_functions, #object -ENTRY(arm940_processor_functions) - .word nommu_early_abort - .word legacy_pabort - .word cpu_arm940_proc_init - .word cpu_arm940_proc_fin - .word cpu_arm940_reset - .word cpu_arm940_do_idle - .word cpu_arm940_dcache_clean_area - .word cpu_arm940_switch_mm - .word 0 @ cpu_*_set_pte - .word 0 - .word 0 - .word 0 - .size arm940_processor_functions, . - arm940_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm940, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" -.type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm940_name, #object -cpu_arm940_name: - .ascii "ARM940T" - .size cpu_arm940_name, . - cpu_arm940_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm940_name, "ARM940T" .align -- cgit v1.2.3 From b1b9892bcd08e5f4dd3c632852639707b24063f4 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:21:17 +0100 Subject: ARM: mm: proc-arm946: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm946.S | 53 +++++++---------------------------------------- 1 file changed, 7 insertions(+), 46 deletions(-) diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S index 8063345406fe..f8f7ea34bfc5 100644 --- a/arch/arm/mm/proc-arm946.S +++ b/arch/arm/mm/proc-arm946.S @@ -306,18 +306,8 @@ ENTRY(arm946_dma_unmap_area) mov pc, lr ENDPROC(arm946_dma_unmap_area) -ENTRY(arm946_cache_fns) - .long arm946_flush_icache_all - .long arm946_flush_kern_cache_all - .long arm946_flush_user_cache_all - .long arm946_flush_user_cache_range - .long arm946_coherent_kern_range - .long arm946_coherent_user_range - .long arm946_flush_kern_dcache_area - .long arm946_dma_map_area - .long arm946_dma_unmap_area - .long arm946_dma_flush_range - + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions arm946 ENTRY(cpu_arm946_dcache_clean_area) #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH @@ -403,43 +393,14 @@ __arm946_setup: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm946_processor_functions, #object -ENTRY(arm946_processor_functions) - .word nommu_early_abort - .word legacy_pabort - .word cpu_arm946_proc_init - .word cpu_arm946_proc_fin - .word cpu_arm946_reset - .word cpu_arm946_do_idle - - .word cpu_arm946_dcache_clean_area - .word cpu_arm946_switch_mm - .word 0 @ cpu_*_set_pte - .word 0 - .word 0 - .word 0 - .size arm946_processor_functions, . - arm946_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm946, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5t" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm946_name, #object -cpu_arm946_name: - .ascii "ARM946E-S" - .size cpu_arm946_name, . - cpu_arm946_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5t" + string cpu_arm946_name, "ARM946E-S" .align -- cgit v1.2.3 From b4a19f03c4d73c3aa5e08ce8fd3c78426c766ea7 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:21:28 +0100 Subject: ARM: mm: proc-arm9tdmi: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-arm9tdmi.S | 78 +++++++++++---------------------------------- 1 file changed, 18 insertions(+), 60 deletions(-) diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index 546b54da1005..2120f9e2af7f 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -17,6 +17,8 @@ #include #include +#include "proc-macros.S" + .text /* * cpu_arm9tdmi_proc_init() @@ -55,82 +57,38 @@ __arm9tdmi_setup: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type arm9tdmi_processor_functions, #object -ENTRY(arm9tdmi_processor_functions) - .word nommu_early_abort - .word legacy_pabort - .word cpu_arm9tdmi_proc_init - .word cpu_arm9tdmi_proc_fin - .word cpu_arm9tdmi_reset - .word cpu_arm9tdmi_do_idle - .word cpu_arm9tdmi_dcache_clean_area - .word cpu_arm9tdmi_switch_mm - .word 0 @ cpu_*_set_pte - .word 0 - .word 0 - .word 0 - .size arm9tdmi_processor_functions, . - arm9tdmi_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions arm9tdmi, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4t" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_arm9tdmi_name, #object -cpu_arm9tdmi_name: - .asciz "ARM9TDMI" - .size cpu_arm9tdmi_name, . - cpu_arm9tdmi_name - - .type cpu_p2001_name, #object -cpu_p2001_name: - .asciz "P2001" - .size cpu_p2001_name, . - cpu_p2001_name + string cpu_arch_name, "armv4t" + string cpu_elf_name, "v4" + string cpu_arm9tdmi_name, "ARM9TDMI" + string cpu_p2001_name, "P2001" .align .section ".proc.info.init", #alloc, #execinstr - .type __arm9tdmi_proc_info, #object -__arm9tdmi_proc_info: - .long 0x41009900 - .long 0xfff8ff00 +.macro arm9tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req + .type __\name\()_proc_info, #object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long 0 .long 0 b __arm9tdmi_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_arm9tdmi_name + .long \cpu_name .long arm9tdmi_processor_functions .long 0 .long 0 .long v4_cache_fns - .size __arm9tdmi_proc_info, . - __arm9tdmi_proc_info + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm - .type __p2001_proc_info, #object -__p2001_proc_info: - .long 0x41029000 - .long 0xffffffff - .long 0 - .long 0 - b __arm9tdmi_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT - .long cpu_p2001_name - .long arm9tdmi_processor_functions - .long 0 - .long 0 - .long v4_cache_fns - .size __p2001_proc_info, . - __p2001_proc_info + arm9tdmi_proc_info arm9tdmi, 0x41009900, 0xfff8ff00, cpu_arm9tdmi_name + arm9tdmi_proc_info p2001, 0x41029000, 0xffffffff, cpu_p2001_name -- cgit v1.2.3 From d6ed10ce39d364189fd09c6e9252d85f35d5f9fe Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:21:50 +0100 Subject: ARM: mm: proc-fa526: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-fa526.S | 38 +++++--------------------------------- 1 file changed, 5 insertions(+), 33 deletions(-) diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S index fc2a4ae15cf4..4c7a5710472b 100644 --- a/arch/arm/mm/proc-fa526.S +++ b/arch/arm/mm/proc-fa526.S @@ -180,42 +180,14 @@ fa526_cr1_set: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type fa526_processor_functions, #object -fa526_processor_functions: - .word v4_early_abort - .word legacy_pabort - .word cpu_fa526_proc_init - .word cpu_fa526_proc_fin - .word cpu_fa526_reset - .word cpu_fa526_do_idle - .word cpu_fa526_dcache_clean_area - .word cpu_fa526_switch_mm - .word cpu_fa526_set_pte_ext - .word 0 - .word 0 - .word 0 - .size fa526_processor_functions, . - fa526_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions fa526, dabort=v4_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_fa526_name, #object -cpu_fa526_name: - .asciz "FA526" - .size cpu_fa526_name, . - cpu_fa526_name + string cpu_arch_name, "armv4" + string cpu_elf_name, "v4" + string cpu_fa526_name, "FA526" .align -- cgit v1.2.3 From e43b670e24de9531f847d1891e7487bffd57017b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:22:12 +0100 Subject: ARM: mm: proc-feroceon: Use the new processor struct macros Signed-off-by: Dave Martin Acked-by: Nicolas Pitre --- arch/arm/mm/proc-feroceon.S | 202 +++++++++++--------------------------------- 1 file changed, 49 insertions(+), 153 deletions(-) diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index d3883eed7a4a..8a6c2f78c1c3 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -411,29 +411,28 @@ ENTRY(feroceon_dma_unmap_area) mov pc, lr ENDPROC(feroceon_dma_unmap_area) -ENTRY(feroceon_cache_fns) - .long feroceon_flush_icache_all - .long feroceon_flush_kern_cache_all - .long feroceon_flush_user_cache_all - .long feroceon_flush_user_cache_range - .long feroceon_coherent_kern_range - .long feroceon_coherent_user_range - .long feroceon_flush_kern_dcache_area - .long feroceon_dma_map_area - .long feroceon_dma_unmap_area - .long feroceon_dma_flush_range - -ENTRY(feroceon_range_cache_fns) - .long feroceon_flush_icache_all - .long feroceon_flush_kern_cache_all - .long feroceon_flush_user_cache_all - .long feroceon_flush_user_cache_range - .long feroceon_coherent_kern_range - .long feroceon_coherent_user_range - .long feroceon_range_flush_kern_dcache_area - .long feroceon_range_dma_map_area - .long feroceon_dma_unmap_area - .long feroceon_range_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions feroceon + +.macro range_alias basename + .globl feroceon_range_\basename + .type feroceon_range_\basename , %function + .equ feroceon_range_\basename , feroceon_\basename +.endm + +/* + * Most of the cache functions are unchanged for this case. + * Export suitable alias symbols for the unchanged functions: + */ + range_alias flush_icache_all + range_alias flush_user_cache_all + range_alias flush_kern_cache_all + range_alias flush_user_cache_range + range_alias coherent_kern_range + range_alias coherent_user_range + range_alias dma_unmap_area + + define_cache_functions feroceon_range .align 5 ENTRY(cpu_feroceon_dcache_clean_area) @@ -539,93 +538,27 @@ feroceon_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type feroceon_processor_functions, #object -feroceon_processor_functions: - .word v5t_early_abort - .word legacy_pabort - .word cpu_feroceon_proc_init - .word cpu_feroceon_proc_fin - .word cpu_feroceon_reset - .word cpu_feroceon_do_idle - .word cpu_feroceon_dcache_clean_area - .word cpu_feroceon_switch_mm - .word cpu_feroceon_set_pte_ext - .word 0 - .word 0 - .word 0 - .size feroceon_processor_functions, . - feroceon_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions feroceon, dabort=v5t_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_feroceon_name, #object -cpu_feroceon_name: - .asciz "Feroceon" - .size cpu_feroceon_name, . - cpu_feroceon_name - - .type cpu_88fr531_name, #object -cpu_88fr531_name: - .asciz "Feroceon 88FR531-vd" - .size cpu_88fr531_name, . - cpu_88fr531_name - - .type cpu_88fr571_name, #object -cpu_88fr571_name: - .asciz "Feroceon 88FR571-vd" - .size cpu_88fr571_name, . - cpu_88fr571_name - - .type cpu_88fr131_name, #object -cpu_88fr131_name: - .asciz "Feroceon 88FR131" - .size cpu_88fr131_name, . - cpu_88fr131_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + string cpu_feroceon_name, "Feroceon" + string cpu_88fr531_name, "Feroceon 88FR531-vd" + string cpu_88fr571_name, "Feroceon 88FR571-vd" + string cpu_88fr131_name, "Feroceon 88FR131" .align .section ".proc.info.init", #alloc, #execinstr -#ifdef CONFIG_CPU_FEROCEON_OLD_ID - .type __feroceon_old_id_proc_info,#object -__feroceon_old_id_proc_info: - .long 0x41009260 - .long 0xff00fff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __feroceon_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_feroceon_name - .long feroceon_processor_functions - .long v4wbi_tlb_fns - .long feroceon_user_fns - .long feroceon_cache_fns - .size __feroceon_old_id_proc_info, . - __feroceon_old_id_proc_info -#endif - - .type __88fr531_proc_info,#object -__88fr531_proc_info: - .long 0x56055310 - .long 0xfffffff0 +.macro feroceon_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache:req + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long PMD_TYPE_SECT | \ PMD_SECT_BUFFERABLE | \ PMD_SECT_CACHEABLE | \ @@ -640,59 +573,22 @@ __88fr531_proc_info: .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_88fr531_name + .long \cpu_name .long feroceon_processor_functions .long v4wbi_tlb_fns .long feroceon_user_fns - .long feroceon_cache_fns - .size __88fr531_proc_info, . - __88fr531_proc_info + .long \cache + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm - .type __88fr571_proc_info,#object -__88fr571_proc_info: - .long 0x56155710 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __feroceon_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_88fr571_name - .long feroceon_processor_functions - .long v4wbi_tlb_fns - .long feroceon_user_fns - .long feroceon_range_cache_fns - .size __88fr571_proc_info, . - __88fr571_proc_info +#ifdef CONFIG_CPU_FEROCEON_OLD_ID + feroceon_proc_info feroceon_old_id, 0x41009260, 0xff00fff0, \ + cpu_name=cpu_feroceon_name, cache=feroceon_cache_fns +#endif - .type __88fr131_proc_info,#object -__88fr131_proc_info: - .long 0x56251310 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_BIT4 | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __feroceon_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_88fr131_name - .long feroceon_processor_functions - .long v4wbi_tlb_fns - .long feroceon_user_fns - .long feroceon_range_cache_fns - .size __88fr131_proc_info, . - __88fr131_proc_info + feroceon_proc_info 88fr531, 0x56055310, 0xfffffff0, cpu_88fr531_name, \ + cache=feroceon_cache_fns + feroceon_proc_info 88fr571, 0x56155710, 0xfffffff0, cpu_88fr571_name, \ + cache=feroceon_range_cache_fns + feroceon_proc_info 88fr131, 0x56251310, 0xfffffff0, cpu_88fr131_name, \ + cache=feroceon_range_cache_fns -- cgit v1.2.3 From a39a32187b71f8a693f3d128b483a2428941e83a Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:22:29 +0100 Subject: ARM: mm: proc-mohawk: Use the new processor struct macros This patch also defines a suitable flush_icache_all implementation which would otherwise be missing, resulting in a link failure. Thanks to Nicolas Pitre for suggesting the code for this. Signed-off-by: Dave Martin Signed-off-by: Nicolas Pitre --- arch/arm/mm/proc-mohawk.S | 61 ++++++++++++++--------------------------------- 1 file changed, 18 insertions(+), 43 deletions(-) diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 9d4f2ae63370..db52b0fb14a0 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -92,6 +92,17 @@ ENTRY(cpu_mohawk_do_idle) mcr p15, 0, r0, c7, c0, 4 @ wait for interrupt mov pc, lr +/* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(mohawk_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(mohawk_flush_icache_all) + /* * flush_user_cache_all() * @@ -288,16 +299,8 @@ ENTRY(mohawk_dma_unmap_area) mov pc, lr ENDPROC(mohawk_dma_unmap_area) -ENTRY(mohawk_cache_fns) - .long mohawk_flush_kern_cache_all - .long mohawk_flush_user_cache_all - .long mohawk_flush_user_cache_range - .long mohawk_coherent_kern_range - .long mohawk_coherent_user_range - .long mohawk_flush_kern_dcache_area - .long mohawk_dma_map_area - .long mohawk_dma_unmap_area - .long mohawk_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions mohawk ENTRY(cpu_mohawk_dcache_clean_area) 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry @@ -373,42 +376,14 @@ mohawk_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - .type mohawk_processor_functions, #object -mohawk_processor_functions: - .word v5t_early_abort - .word legacy_pabort - .word cpu_mohawk_proc_init - .word cpu_mohawk_proc_fin - .word cpu_mohawk_reset - .word cpu_mohawk_do_idle - .word cpu_mohawk_dcache_clean_area - .word cpu_mohawk_switch_mm - .word cpu_mohawk_set_pte_ext - .word 0 - .word 0 - .word 0 - .size mohawk_processor_functions, . - mohawk_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions mohawk, dabort=v5t_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_mohawk_name, #object -cpu_mohawk_name: - .asciz "Marvell 88SV331x" - .size cpu_mohawk_name, . - cpu_mohawk_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + string cpu_mohawk_name, "Marvell 88SV331x" .align -- cgit v1.2.3 From 5973ba5886366bbcc7c911911d151b9ae13f2edb Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:25:11 +0100 Subject: ARM: mm: proc-sa110: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-sa110.S | 39 +++++---------------------------------- 1 file changed, 5 insertions(+), 34 deletions(-) diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S index 46f09ed16b98..d50ada26edd6 100644 --- a/arch/arm/mm/proc-sa110.S +++ b/arch/arm/mm/proc-sa110.S @@ -187,43 +187,14 @@ sa110_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - - .type sa110_processor_functions, #object -ENTRY(sa110_processor_functions) - .word v4_early_abort - .word legacy_pabort - .word cpu_sa110_proc_init - .word cpu_sa110_proc_fin - .word cpu_sa110_reset - .word cpu_sa110_do_idle - .word cpu_sa110_dcache_clean_area - .word cpu_sa110_switch_mm - .word cpu_sa110_set_pte_ext - .word 0 - .word 0 - .word 0 - .size sa110_processor_functions, . - sa110_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions sa110, dabort=v4_early_abort, pabort=legacy_pabort .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_sa110_name, #object -cpu_sa110_name: - .asciz "StrongARM-110" - .size cpu_sa110_name, . - cpu_sa110_name + string cpu_arch_name, "armv4" + string cpu_elf_name, "v4" + string cpu_sa110_name, "StrongARM-110" .align -- cgit v1.2.3 From f58d59f6c59397b8a1381207c58189034b904879 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:25:30 +0100 Subject: ARM: mm: proc-sa1100: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-sa1100.S | 84 ++++++++++------------------------------------- 1 file changed, 17 insertions(+), 67 deletions(-) diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 184a9c997e36..c7e08cab55a8 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -235,60 +235,29 @@ sa1100_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - /* * SA1100 and SA1110 share the same function calls */ - .type sa1100_processor_functions, #object -ENTRY(sa1100_processor_functions) - .word v4_early_abort - .word legacy_pabort - .word cpu_sa1100_proc_init - .word cpu_sa1100_proc_fin - .word cpu_sa1100_reset - .word cpu_sa1100_do_idle - .word cpu_sa1100_dcache_clean_area - .word cpu_sa1100_switch_mm - .word cpu_sa1100_set_pte_ext - .word cpu_sa1100_suspend_size - .word cpu_sa1100_do_suspend - .word cpu_sa1100_do_resume - .size sa1100_processor_functions, . - sa1100_processor_functions - - .section ".rodata" - - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv4" - .size cpu_arch_name, . - cpu_arch_name - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v4" - .size cpu_elf_name, . - cpu_elf_name + @ define struct processor (see and proc-macros.S) + define_processor_functions sa1100, dabort=v4_early_abort, pabort=legacy_pabort, suspend=1 - .type cpu_sa1100_name, #object -cpu_sa1100_name: - .asciz "StrongARM-1100" - .size cpu_sa1100_name, . - cpu_sa1100_name + .section ".rodata" - .type cpu_sa1110_name, #object -cpu_sa1110_name: - .asciz "StrongARM-1110" - .size cpu_sa1110_name, . - cpu_sa1110_name + string cpu_arch_name, "armv4" + string cpu_elf_name, "v4" + string cpu_sa1100_name, "StrongARM-1100" + string cpu_sa1110_name, "StrongARM-1110" .align .section ".proc.info.init", #alloc, #execinstr - .type __sa1100_proc_info,#object -__sa1100_proc_info: - .long 0x4401a110 - .long 0xfffffff0 +.macro sa1100_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long PMD_TYPE_SECT | \ PMD_SECT_BUFFERABLE | \ PMD_SECT_CACHEABLE | \ @@ -301,32 +270,13 @@ __sa1100_proc_info: .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT | HWCAP_FAST_MULT - .long cpu_sa1100_name + .long \cpu_name .long sa1100_processor_functions .long v4wb_tlb_fns .long v4_mc_user_fns .long v4wb_cache_fns - .size __sa1100_proc_info, . - __sa1100_proc_info + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm - .type __sa1110_proc_info,#object -__sa1110_proc_info: - .long 0x6901b110 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __sa1100_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT | HWCAP_FAST_MULT - .long cpu_sa1110_name - .long sa1100_processor_functions - .long v4wb_tlb_fns - .long v4_mc_user_fns - .long v4wb_cache_fns - .size __sa1110_proc_info, . - __sa1110_proc_info + sa1100_proc_info sa1100, 0x4401a110, 0xfffffff0, cpu_sa1100_name + sa1100_proc_info sa1110, 0x6901b110, 0xfffffff0, cpu_sa1110_name -- cgit v1.2.3 From 7b7dc6e8885b863beef189ade5971ff14781a971 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:25:46 +0100 Subject: ARM: mm: proc-v6: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-v6.S | 34 +++++----------------------------- 1 file changed, 5 insertions(+), 29 deletions(-) diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 1d2b8451bf25..5ec15431cf12 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -169,11 +169,7 @@ cpu_resume_l1_flags: #define cpu_v6_do_resume 0 #endif - - .type cpu_v6_name, #object -cpu_v6_name: - .asciz "ARMv6-compatible processor" - .size cpu_v6_name, . - cpu_v6_name + string cpu_v6_name, "ARMv6-compatible processor" .align @@ -239,33 +235,13 @@ v6_crval: __INITDATA - .type v6_processor_functions, #object -ENTRY(v6_processor_functions) - .word v6_early_abort - .word v6_pabort - .word cpu_v6_proc_init - .word cpu_v6_proc_fin - .word cpu_v6_reset - .word cpu_v6_do_idle - .word cpu_v6_dcache_clean_area - .word cpu_v6_switch_mm - .word cpu_v6_set_pte_ext - .word cpu_v6_suspend_size - .word cpu_v6_do_suspend - .word cpu_v6_do_resume - .size v6_processor_functions, . - v6_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions v6, dabort=v6_early_abort, pabort=v6_pabort, suspend=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv6" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v6" - .size cpu_elf_name, . - cpu_elf_name + string cpu_arch_name, "armv6" + string cpu_elf_name, "v6" .align .section ".proc.info.init", #alloc, #execinstr -- cgit v1.2.3 From 78a8f3c365b8851eb9862c54425e95bfd523f22d Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:26:19 +0100 Subject: ARM: mm: proc-v7: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-v7.S | 31 +++++-------------------------- 1 file changed, 5 insertions(+), 26 deletions(-) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 089c0b5e454f..a2e1ee87a2c4 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -173,8 +173,7 @@ ENTRY(cpu_v7_set_pte_ext) mov pc, lr ENDPROC(cpu_v7_set_pte_ext) -cpu_v7_name: - .ascii "ARMv7 Processor" + string cpu_v7_name, "ARMv7 Processor" .align /* @@ -411,33 +410,13 @@ __v7_setup_stack: __INITDATA - .type v7_processor_functions, #object -ENTRY(v7_processor_functions) - .word v7_early_abort - .word v7_pabort - .word cpu_v7_proc_init - .word cpu_v7_proc_fin - .word cpu_v7_reset - .word cpu_v7_do_idle - .word cpu_v7_dcache_clean_area - .word cpu_v7_switch_mm - .word cpu_v7_set_pte_ext - .word cpu_v7_suspend_size - .word cpu_v7_do_suspend - .word cpu_v7_do_resume - .size v7_processor_functions, . - v7_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv7" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v7" - .size cpu_elf_name, . - cpu_elf_name + string cpu_arch_name, "armv7" + string cpu_elf_name, "v7" .align .section ".proc.info.init", #alloc, #execinstr -- cgit v1.2.3 From c21898f9f02f8d54d09905ea4ce3a47592900ec4 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:26:38 +0100 Subject: ARM: mm: proc-xsc3: Use new generic struct definition macros Signed-off-by: Dave Martin --- arch/arm/mm/proc-xsc3.S | 90 ++++++++++--------------------------------------- 1 file changed, 17 insertions(+), 73 deletions(-) diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 596213699f37..1508f9bc526a 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -335,17 +335,8 @@ ENTRY(xsc3_dma_unmap_area) mov pc, lr ENDPROC(xsc3_dma_unmap_area) -ENTRY(xsc3_cache_fns) - .long xsc3_flush_icache_all - .long xsc3_flush_kern_cache_all - .long xsc3_flush_user_cache_all - .long xsc3_flush_user_cache_range - .long xsc3_coherent_kern_range - .long xsc3_coherent_user_range - .long xsc3_flush_kern_dcache_area - .long xsc3_dma_map_area - .long xsc3_dma_unmap_area - .long xsc3_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions xsc3 ENTRY(cpu_xsc3_dcache_clean_area) 1: mcr p15, 0, r0, c7, c10, 1 @ clean L1 D line @@ -503,52 +494,24 @@ xsc3_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - - .type xsc3_processor_functions, #object -ENTRY(xsc3_processor_functions) - .word v5t_early_abort - .word legacy_pabort - .word cpu_xsc3_proc_init - .word cpu_xsc3_proc_fin - .word cpu_xsc3_reset - .word cpu_xsc3_do_idle - .word cpu_xsc3_dcache_clean_area - .word cpu_xsc3_switch_mm - .word cpu_xsc3_set_pte_ext - .word cpu_xsc3_suspend_size - .word cpu_xsc3_do_suspend - .word cpu_xsc3_do_resume - .size xsc3_processor_functions, . - xsc3_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions xsc3, dabort=v5t_early_abort, pabort=legacy_pabort, suspend=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_xsc3_name, #object -cpu_xsc3_name: - .asciz "XScale-V3 based processor" - .size cpu_xsc3_name, . - cpu_xsc3_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + string cpu_xsc3_name, "XScale-V3 based processor" .align .section ".proc.info.init", #alloc, #execinstr - .type __xsc3_proc_info,#object -__xsc3_proc_info: - .long 0x69056000 - .long 0xffffe000 +.macro xsc3_proc_info name:req, cpu_val:req, cpu_mask:req + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask .long PMD_TYPE_SECT | \ PMD_SECT_BUFFERABLE | \ PMD_SECT_CACHEABLE | \ @@ -566,29 +529,10 @@ __xsc3_proc_info: .long v4wbi_tlb_fns .long xsc3_mc_user_fns .long xsc3_cache_fns - .size __xsc3_proc_info, . - __xsc3_proc_info + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm -/* Note: PXA935 changed its implementor ID from Intel to Marvell */ + xsc3_proc_info xsc3, 0x69056000, 0xffffe000 - .type __xsc3_pxa935_proc_info,#object -__xsc3_pxa935_proc_info: - .long 0x56056000 - .long 0xffffe000 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xsc3_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_xsc3_name - .long xsc3_processor_functions - .long v4wbi_tlb_fns - .long xsc3_mc_user_fns - .long xsc3_cache_fns - .size __xsc3_pxa935_proc_info, . - __xsc3_pxa935_proc_info +/* Note: PXA935 changed its implementor ID from Intel to Marvell */ + xsc3_proc_info xsc3_pxa935, 0x56056000, 0xffffe000 -- cgit v1.2.3 From ab1a746da9dd19e30a98d9744d5c7dc6df597fb0 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:26:56 +0100 Subject: ARM: mm: proc-xscale: Use new generic struct definition macros Without this patch, xscale_80200_A0_A1 is missing the icache_flush_all entry, which would result in the wrong functions being called at run-time. This patch re-uses xscale_icache_flush_all for xscale_80200_A0_A1_cache_fns. Signed-off-by: Dave Martin --- arch/arm/mm/proc-xscale.S | 507 +++++++--------------------------------------- 1 file changed, 76 insertions(+), 431 deletions(-) diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 42af97664c9d..76a804605010 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -390,12 +390,12 @@ ENDPROC(xscale_dma_map_area) * - size - size of region * - dir - DMA direction */ -ENTRY(xscale_dma_a0_map_area) +ENTRY(xscale_80200_A0_A1_dma_map_area) add r1, r1, r0 teq r2, #DMA_TO_DEVICE beq xscale_dma_clean_range b xscale_dma_flush_range -ENDPROC(xscale_dma_a0_map_area) +ENDPROC(xscale_80200_A0_A1_dma_map_area) /* * dma_unmap_area(start, size, dir) @@ -407,17 +407,8 @@ ENTRY(xscale_dma_unmap_area) mov pc, lr ENDPROC(xscale_dma_unmap_area) -ENTRY(xscale_cache_fns) - .long xscale_flush_icache_all - .long xscale_flush_kern_cache_all - .long xscale_flush_user_cache_all - .long xscale_flush_user_cache_range - .long xscale_coherent_kern_range - .long xscale_coherent_user_range - .long xscale_flush_kern_dcache_area - .long xscale_dma_map_area - .long xscale_dma_unmap_area - .long xscale_dma_flush_range + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions xscale /* * On stepping A0/A1 of the 80200, invalidating D-cache by line doesn't @@ -432,16 +423,28 @@ ENTRY(xscale_cache_fns) * revision January 22, 2003, available at: * http://www.intel.com/design/iio/specupdt/273415.htm */ -ENTRY(xscale_80200_A0_A1_cache_fns) - .long xscale_flush_kern_cache_all - .long xscale_flush_user_cache_all - .long xscale_flush_user_cache_range - .long xscale_coherent_kern_range - .long xscale_coherent_user_range - .long xscale_flush_kern_dcache_area - .long xscale_dma_a0_map_area - .long xscale_dma_unmap_area - .long xscale_dma_flush_range +.macro a0_alias basename + .globl xscale_80200_A0_A1_\basename + .type xscale_80200_A0_A1_\basename , %function + .equ xscale_80200_A0_A1_\basename , xscale_\basename +.endm + +/* + * Most of the cache functions are unchanged for these processor revisions. + * Export suitable alias symbols for the unchanged functions: + */ + a0_alias flush_icache_all + a0_alias flush_user_cache_all + a0_alias flush_kern_cache_all + a0_alias flush_user_cache_range + a0_alias coherent_kern_range + a0_alias coherent_user_range + a0_alias flush_kern_dcache_area + a0_alias dma_flush_range + a0_alias dma_unmap_area + + @ define struct cpu_cache_fns (see and proc-macros.S) + define_cache_functions xscale_80200_A0_A1 ENTRY(cpu_xscale_dcache_clean_area) 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry @@ -587,432 +590,74 @@ xscale_crval: __INITDATA -/* - * Purpose : Function pointers used to access above functions - all calls - * come through these - */ - - .type xscale_processor_functions, #object -ENTRY(xscale_processor_functions) - .word v5t_early_abort - .word legacy_pabort - .word cpu_xscale_proc_init - .word cpu_xscale_proc_fin - .word cpu_xscale_reset - .word cpu_xscale_do_idle - .word cpu_xscale_dcache_clean_area - .word cpu_xscale_switch_mm - .word cpu_xscale_set_pte_ext - .word cpu_xscale_suspend_size - .word cpu_xscale_do_suspend - .word cpu_xscale_do_resume - .size xscale_processor_functions, . - xscale_processor_functions + @ define struct processor (see and proc-macros.S) + define_processor_functions xscale, dabort=v5t_early_abort, pabort=legacy_pabort, suspend=1 .section ".rodata" - .type cpu_arch_name, #object -cpu_arch_name: - .asciz "armv5te" - .size cpu_arch_name, . - cpu_arch_name - - .type cpu_elf_name, #object -cpu_elf_name: - .asciz "v5" - .size cpu_elf_name, . - cpu_elf_name - - .type cpu_80200_A0_A1_name, #object -cpu_80200_A0_A1_name: - .asciz "XScale-80200 A0/A1" - .size cpu_80200_A0_A1_name, . - cpu_80200_A0_A1_name - - .type cpu_80200_name, #object -cpu_80200_name: - .asciz "XScale-80200" - .size cpu_80200_name, . - cpu_80200_name - - .type cpu_80219_name, #object -cpu_80219_name: - .asciz "XScale-80219" - .size cpu_80219_name, . - cpu_80219_name - - .type cpu_8032x_name, #object -cpu_8032x_name: - .asciz "XScale-IOP8032x Family" - .size cpu_8032x_name, . - cpu_8032x_name - - .type cpu_8033x_name, #object -cpu_8033x_name: - .asciz "XScale-IOP8033x Family" - .size cpu_8033x_name, . - cpu_8033x_name - - .type cpu_pxa250_name, #object -cpu_pxa250_name: - .asciz "XScale-PXA250" - .size cpu_pxa250_name, . - cpu_pxa250_name - - .type cpu_pxa210_name, #object -cpu_pxa210_name: - .asciz "XScale-PXA210" - .size cpu_pxa210_name, . - cpu_pxa210_name - - .type cpu_ixp42x_name, #object -cpu_ixp42x_name: - .asciz "XScale-IXP42x Family" - .size cpu_ixp42x_name, . - cpu_ixp42x_name - - .type cpu_ixp43x_name, #object -cpu_ixp43x_name: - .asciz "XScale-IXP43x Family" - .size cpu_ixp43x_name, . - cpu_ixp43x_name - - .type cpu_ixp46x_name, #object -cpu_ixp46x_name: - .asciz "XScale-IXP46x Family" - .size cpu_ixp46x_name, . - cpu_ixp46x_name - - .type cpu_ixp2400_name, #object -cpu_ixp2400_name: - .asciz "XScale-IXP2400" - .size cpu_ixp2400_name, . - cpu_ixp2400_name - - .type cpu_ixp2800_name, #object -cpu_ixp2800_name: - .asciz "XScale-IXP2800" - .size cpu_ixp2800_name, . - cpu_ixp2800_name - - .type cpu_pxa255_name, #object -cpu_pxa255_name: - .asciz "XScale-PXA255" - .size cpu_pxa255_name, . - cpu_pxa255_name - - .type cpu_pxa270_name, #object -cpu_pxa270_name: - .asciz "XScale-PXA270" - .size cpu_pxa270_name, . - cpu_pxa270_name + string cpu_arch_name, "armv5te" + string cpu_elf_name, "v5" + + string cpu_80200_A0_A1_name, "XScale-80200 A0/A1" + string cpu_80200_name, "XScale-80200" + string cpu_80219_name, "XScale-80219" + string cpu_8032x_name, "XScale-IOP8032x Family" + string cpu_8033x_name, "XScale-IOP8033x Family" + string cpu_pxa250_name, "XScale-PXA250" + string cpu_pxa210_name, "XScale-PXA210" + string cpu_ixp42x_name, "XScale-IXP42x Family" + string cpu_ixp43x_name, "XScale-IXP43x Family" + string cpu_ixp46x_name, "XScale-IXP46x Family" + string cpu_ixp2400_name, "XScale-IXP2400" + string cpu_ixp2800_name, "XScale-IXP2800" + string cpu_pxa255_name, "XScale-PXA255" + string cpu_pxa270_name, "XScale-PXA270" .align .section ".proc.info.init", #alloc, #execinstr - .type __80200_A0_A1_proc_info,#object -__80200_A0_A1_proc_info: - .long 0x69052000 - .long 0xfffffffe - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_80200_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_80200_A0_A1_cache_fns - .size __80200_A0_A1_proc_info, . - __80200_A0_A1_proc_info - - .type __80200_proc_info,#object -__80200_proc_info: - .long 0x69052000 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ +.macro xscale_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache + .type __\name\()_proc_info,#object +__\name\()_proc_info: + .long \cpu_val + .long \cpu_mask + .long PMD_TYPE_SECT | \ PMD_SECT_BUFFERABLE | \ PMD_SECT_CACHEABLE | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ + .long PMD_TYPE_SECT | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ b __xscale_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_80200_name + .long \cpu_name .long xscale_processor_functions .long v4wbi_tlb_fns .long xscale_mc_user_fns - .long xscale_cache_fns - .size __80200_proc_info, . - __80200_proc_info - - .type __80219_proc_info,#object -__80219_proc_info: - .long 0x69052e20 - .long 0xffffffe0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_80219_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __80219_proc_info, . - __80219_proc_info - - .type __8032x_proc_info,#object -__8032x_proc_info: - .long 0x69052420 - .long 0xfffff7e0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_8032x_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __8032x_proc_info, . - __8032x_proc_info - - .type __8033x_proc_info,#object -__8033x_proc_info: - .long 0x69054010 - .long 0xfffffd30 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_8033x_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __8033x_proc_info, . - __8033x_proc_info - - .type __pxa250_proc_info,#object -__pxa250_proc_info: - .long 0x69052100 - .long 0xfffff7f0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_pxa250_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __pxa250_proc_info, . - __pxa250_proc_info - - .type __pxa210_proc_info,#object -__pxa210_proc_info: - .long 0x69052120 - .long 0xfffff3f0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_pxa210_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __pxa210_proc_info, . - __pxa210_proc_info - - .type __ixp2400_proc_info, #object -__ixp2400_proc_info: - .long 0x69054190 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_ixp2400_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __ixp2400_proc_info, . - __ixp2400_proc_info - - .type __ixp2800_proc_info, #object -__ixp2800_proc_info: - .long 0x690541a0 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_ixp2800_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __ixp2800_proc_info, . - __ixp2800_proc_info - - .type __ixp42x_proc_info, #object -__ixp42x_proc_info: - .long 0x690541c0 - .long 0xffffffc0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_ixp42x_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __ixp42x_proc_info, . - __ixp42x_proc_info - - .type __ixp43x_proc_info, #object -__ixp43x_proc_info: - .long 0x69054040 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_ixp43x_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __ixp43x_proc_info, . - __ixp43x_proc_info - - .type __ixp46x_proc_info, #object -__ixp46x_proc_info: - .long 0x69054200 - .long 0xffffff00 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_ixp46x_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __ixp46x_proc_info, . - __ixp46x_proc_info - - .type __pxa255_proc_info,#object -__pxa255_proc_info: - .long 0x69052d00 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_pxa255_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __pxa255_proc_info, . - __pxa255_proc_info - - .type __pxa270_proc_info,#object -__pxa270_proc_info: - .long 0x69054110 - .long 0xfffffff0 - .long PMD_TYPE_SECT | \ - PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - .long PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - b __xscale_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP - .long cpu_pxa270_name - .long xscale_processor_functions - .long v4wbi_tlb_fns - .long xscale_mc_user_fns - .long xscale_cache_fns - .size __pxa270_proc_info, . - __pxa270_proc_info - + .ifb \cache + .long xscale_cache_fns + .else + .long \cache + .endif + .size __\name\()_proc_info, . - __\name\()_proc_info +.endm + + xscale_proc_info 80200_A0_A1, 0x69052000, 0xfffffffe, cpu_80200_name, \ + cache=xscale_80200_A0_A1_cache_fns + xscale_proc_info 80200, 0x69052000, 0xfffffff0, cpu_80200_name + xscale_proc_info 80219, 0x69052e20, 0xffffffe0, cpu_80219_name + xscale_proc_info 8032x, 0x69052420, 0xfffff7e0, cpu_8032x_name + xscale_proc_info 8033x, 0x69054010, 0xfffffd30, cpu_8033x_name + xscale_proc_info pxa250, 0x69052100, 0xfffff7f0, cpu_pxa250_name + xscale_proc_info pxa210, 0x69052120, 0xfffff3f0, cpu_pxa210_name + xscale_proc_info ixp2400, 0x69054190, 0xfffffff0, cpu_ixp2400_name + xscale_proc_info ixp2800, 0x690541a0, 0xfffffff0, cpu_ixp2800_name + xscale_proc_info ixp42x, 0x690541c0, 0xffffffc0, cpu_ixp42x_name + xscale_proc_info ixp43x, 0x69054040, 0xfffffff0, cpu_ixp43x_name + xscale_proc_info ixp46x, 0x69054200, 0xffffff00, cpu_ixp46x_name + xscale_proc_info pxa255, 0x69052d00, 0xfffffff0, cpu_pxa255_name + xscale_proc_info pxa270, 0x69054110, 0xfffffff0, cpu_pxa270_name -- cgit v1.2.3 From 27eebe4cc98c739298b271609d8d064a31f32522 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:28:50 +0100 Subject: ARM: mm: tlb-fa: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-fa.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/tlb-fa.S b/arch/arm/mm/tlb-fa.S index 9694f1f6f485..7a2e56c5d89a 100644 --- a/arch/arm/mm/tlb-fa.S +++ b/arch/arm/mm/tlb-fa.S @@ -67,9 +67,5 @@ ENTRY(fa_flush_kern_tlb_range) __INITDATA - .type fa_tlb_fns, #object -ENTRY(fa_tlb_fns) - .long fa_flush_user_tlb_range - .long fa_flush_kern_tlb_range - .long fa_tlb_flags - .size fa_tlb_fns, . - fa_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions fa, fa_tlb_flags -- cgit v1.2.3 From d7b84d2438ece9bcf680ea184c8d5cf34239699d Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:29:04 +0100 Subject: ARM: mm: tlb-v3: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-v3.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/tlb-v3.S b/arch/arm/mm/tlb-v3.S index c10786ec8e0a..d253995ec4ca 100644 --- a/arch/arm/mm/tlb-v3.S +++ b/arch/arm/mm/tlb-v3.S @@ -44,9 +44,5 @@ ENTRY(v3_flush_kern_tlb_range) __INITDATA - .type v3_tlb_fns, #object -ENTRY(v3_tlb_fns) - .long v3_flush_user_tlb_range - .long v3_flush_kern_tlb_range - .long v3_tlb_flags - .size v3_tlb_fns, . - v3_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions v3, v3_tlb_flags -- cgit v1.2.3 From f249a6425a977314e4c2e35cab350fd600780386 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:29:19 +0100 Subject: ARM: mm: tlb-v4: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-v4.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/tlb-v4.S b/arch/arm/mm/tlb-v4.S index d6c94457c2b9..17a025ade573 100644 --- a/arch/arm/mm/tlb-v4.S +++ b/arch/arm/mm/tlb-v4.S @@ -57,9 +57,5 @@ ENTRY(v4_flush_user_tlb_range) __INITDATA - .type v4_tlb_fns, #object -ENTRY(v4_tlb_fns) - .long v4_flush_user_tlb_range - .long v4_flush_kern_tlb_range - .long v4_tlb_flags - .size v4_tlb_fns, . - v4_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions v4, v4_tlb_flags -- cgit v1.2.3 From 2284ece2d6c1958dc0166aa3e9db0d0ee923ccb7 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:30:11 +0100 Subject: ARM: mm: tlb-v4wb: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-v4wb.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/tlb-v4wb.S b/arch/arm/mm/tlb-v4wb.S index cb829ca7845d..c04598fa4d4a 100644 --- a/arch/arm/mm/tlb-v4wb.S +++ b/arch/arm/mm/tlb-v4wb.S @@ -69,9 +69,5 @@ ENTRY(v4wb_flush_kern_tlb_range) __INITDATA - .type v4wb_tlb_fns, #object -ENTRY(v4wb_tlb_fns) - .long v4wb_flush_user_tlb_range - .long v4wb_flush_kern_tlb_range - .long v4wb_tlb_flags - .size v4wb_tlb_fns, . - v4wb_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions v4wb, v4wb_tlb_flags -- cgit v1.2.3 From ca560963675949d026314756221a95fcc38e2df1 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:30:39 +0100 Subject: ARM: mm: tlb-v4wbi: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-v4wbi.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/tlb-v4wbi.S b/arch/arm/mm/tlb-v4wbi.S index 60cfc4a25dd5..1f6062b6c1c1 100644 --- a/arch/arm/mm/tlb-v4wbi.S +++ b/arch/arm/mm/tlb-v4wbi.S @@ -60,9 +60,5 @@ ENTRY(v4wbi_flush_kern_tlb_range) __INITDATA - .type v4wbi_tlb_fns, #object -ENTRY(v4wbi_tlb_fns) - .long v4wbi_flush_user_tlb_range - .long v4wbi_flush_kern_tlb_range - .long v4wbi_tlb_flags - .size v4wbi_tlb_fns, . - v4wbi_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions v4wbi, v4wbi_tlb_flags -- cgit v1.2.3 From 3b7f39fa9ad4e19fd87fb1e98a53b4f1700b5d0b Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:31:01 +0100 Subject: ARM: mm: tlb-v6: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-v6.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S index 73d7d89b04c4..a685944735c9 100644 --- a/arch/arm/mm/tlb-v6.S +++ b/arch/arm/mm/tlb-v6.S @@ -90,9 +90,5 @@ ENTRY(v6wbi_flush_kern_tlb_range) __INIT - .type v6wbi_tlb_fns, #object -ENTRY(v6wbi_tlb_fns) - .long v6wbi_flush_user_tlb_range - .long v6wbi_flush_kern_tlb_range - .long v6wbi_tlb_flags - .size v6wbi_tlb_fns, . - v6wbi_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions v6wbi, v6wbi_tlb_flags -- cgit v1.2.3 From 2ba564b90f4c53d7a25cdcf12c6fa15028db7bc9 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Thu, 23 Jun 2011 17:31:16 +0100 Subject: ARM: mm: tlb-v7: Use the new processor struct macros Signed-off-by: Dave Martin --- arch/arm/mm/tlb-v7.S | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index 53cd5b454673..ebd4290ce1e7 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -85,10 +85,5 @@ ENDPROC(v7wbi_flush_kern_tlb_range) __INIT - .type v7wbi_tlb_fns, #object -ENTRY(v7wbi_tlb_fns) - .long v7wbi_flush_user_tlb_range - .long v7wbi_flush_kern_tlb_range - ALT_SMP(.long v7wbi_tlb_flags_smp) - ALT_UP(.long v7wbi_tlb_flags_up) - .size v7wbi_tlb_fns, . - v7wbi_tlb_fns + /* define struct cpu_tlb_fns (see and proc-macros.S) */ + define_tlb_functions v7wbi, v7wbi_tlb_flags_up, flags_smp=v7wbi_tlb_flags_smp -- cgit v1.2.3 From 194a7f720f6f009867a01b760f311b68f1e81872 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 3 Jun 2011 14:09:37 +0100 Subject: ARM: hwcaps: use shifts instead of hardcoded constants The HWCAP numbers are defined as constants, each one being a power of 2. This has become slightly unwieldy now that we have reached 32k. This patch changes the HWCAP defines to use (1 << n) instead of coding the constant directly. The values remain unchanged. Signed-off-by: Will Deacon --- arch/arm/include/asm/hwcap.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h index c1062c317103..81512db2b628 100644 --- a/arch/arm/include/asm/hwcap.h +++ b/arch/arm/include/asm/hwcap.h @@ -4,22 +4,22 @@ /* * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP */ -#define HWCAP_SWP 1 -#define HWCAP_HALF 2 -#define HWCAP_THUMB 4 -#define HWCAP_26BIT 8 /* Play it safe */ -#define HWCAP_FAST_MULT 16 -#define HWCAP_FPA 32 -#define HWCAP_VFP 64 -#define HWCAP_EDSP 128 -#define HWCAP_JAVA 256 -#define HWCAP_IWMMXT 512 -#define HWCAP_CRUNCH 1024 -#define HWCAP_THUMBEE 2048 -#define HWCAP_NEON 4096 -#define HWCAP_VFPv3 8192 -#define HWCAP_VFPv3D16 16384 -#define HWCAP_TLS 32768 +#define HWCAP_SWP (1 << 0) +#define HWCAP_HALF (1 << 1) +#define HWCAP_THUMB (1 << 2) +#define HWCAP_26BIT (1 << 3) /* Play it safe */ +#define HWCAP_FAST_MULT (1 << 4) +#define HWCAP_FPA (1 << 5) +#define HWCAP_VFP (1 << 6) +#define HWCAP_EDSP (1 << 7) +#define HWCAP_JAVA (1 << 8) +#define HWCAP_IWMMXT (1 << 9) +#define HWCAP_CRUNCH (1 << 10) +#define HWCAP_THUMBEE (1 << 11) +#define HWCAP_NEON (1 << 12) +#define HWCAP_VFPv3 (1 << 13) +#define HWCAP_VFPv3D16 (1 << 14) +#define HWCAP_TLS (1 << 15) #if defined(__KERNEL__) && !defined(__ASSEMBLY__) /* -- cgit v1.2.3 From 254cdf8ec39653d19cce71b6622f38a6b62ac3a8 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 3 Jun 2011 14:15:22 +0100 Subject: ARM: hwcaps: add new HWCAP defines for ARMv7-A Modern ARMv7-A cores can optionally implement these new hardware features: - VFPv4: The latest version of the ARMv7 vector floating-point extensions, including hardware support for fused multiple accumulate. D16 or D32 variants may be implemented. - Integer divide: The SDIV and UDIV instructions provide signed and unsigned integer division in hardware. When implemented, these instructions may be available in either both Thumb and ARM, or Thumb only. This patch adds new HWCAP defines to describe these new features. The integer divide capabilities are split into two bits for ARM and Thumb respectively. Whilst HWCAP_IDIVA should never be set if HWCAP_IDIVT is clear, separating the bits makes it easier to interpret from userspace. Signed-off-by: Will Deacon --- arch/arm/include/asm/hwcap.h | 4 ++++ arch/arm/kernel/setup.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h index 81512db2b628..c93a22a8b924 100644 --- a/arch/arm/include/asm/hwcap.h +++ b/arch/arm/include/asm/hwcap.h @@ -20,6 +20,10 @@ #define HWCAP_VFPv3 (1 << 13) #define HWCAP_VFPv3D16 (1 << 14) #define HWCAP_TLS (1 << 15) +#define HWCAP_VFPv4 (1 << 16) +#define HWCAP_IDIVA (1 << 17) +#define HWCAP_IDIVT (1 << 18) +#define HWCAP_IDIV (HWCAP_IDIVA | HWCAP_IDIVT) #if defined(__KERNEL__) && !defined(__ASSEMBLY__) /* diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ed11fb08b05a..699df68fc840 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -977,6 +977,10 @@ static const char *hwcap_str[] = { "neon", "vfpv3", "vfpv3d16", + "tls", + "vfpv4", + "idiva", + "idivt", NULL }; -- cgit v1.2.3 From 18b9dc130c33de2d1fd46bd668e67d0e1a544b16 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 8 Jun 2011 11:42:43 +0100 Subject: ARM: vfp: add VFPv4 capability detection and populate elf_hwcap The presence of VFPv4 cannot be detected simply by looking at the FPSID subarchitecture field, as a value >= 2 signifies the architecture as VFPv3 or later. This patch reads from MVFR1 to check whether or not the fused multiply accumulate instructions are supported. Since these are introduced with VFPv4, this tells us what we need to know. Signed-off-by: Will Deacon --- arch/arm/vfp/vfpmodule.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index f25e7ec89416..650d90be0f9f 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -582,7 +582,6 @@ static int __init vfp_init(void) elf_hwcap |= HWCAP_VFPv3D16; } #endif -#ifdef CONFIG_NEON /* * Check for the presence of the Advanced SIMD * load/store instructions, integer and single @@ -590,10 +589,13 @@ static int __init vfp_init(void) * for NEON if the hardware has the MVFR registers. */ if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) { +#ifdef CONFIG_NEON if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100) elf_hwcap |= HWCAP_NEON; - } #endif + if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000) + elf_hwcap |= HWCAP_VFPv4; + } } return 0; } -- cgit v1.2.3 From dc939cd835d0e2d3ff4197d6e2c017d269616d20 Mon Sep 17 00:00:00 2001 From: Pawel Moll Date: Fri, 20 May 2011 14:39:28 +0100 Subject: ARM: proc: convert v7 proc infos into a common macro As most of the proc info content is common across all v7 processors, this patch converts existing A9 and generic v7 descriptions into a macro (allowing extra flags in future). Signed-off-by: Pawel Moll Signed-off-by: Will Deacon --- arch/arm/mm/proc-v7.S | 67 ++++++++++++++++++--------------------------------- 1 file changed, 24 insertions(+), 43 deletions(-) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index a2e1ee87a2c4..a759ccafeaca 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -421,33 +421,36 @@ __v7_setup_stack: .section ".proc.info.init", #alloc, #execinstr - .type __v7_ca9mp_proc_info, #object -__v7_ca9mp_proc_info: - .long 0x410fc090 @ Required ID value - .long 0xff0ffff0 @ Mask for ID - ALT_SMP(.long \ - PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ | \ - PMD_FLAGS_SMP) - ALT_UP(.long \ - PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ | \ - PMD_FLAGS_UP) - .long PMD_TYPE_SECT | \ - PMD_SECT_XN | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - W(b) __v7_ca9mp_setup + /* + * Standard v7 proc info content + */ +.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0 + ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \ + PMD_FLAGS_SMP | \mm_mmuflags) + ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \ + PMD_FLAGS_UP | \mm_mmuflags) + .long PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \io_mmuflags + W(b) \initfunc .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \ + HWCAP_EDSP | HWCAP_TLS | \hwcaps .long cpu_v7_name .long v7_processor_functions .long v7wbi_tlb_fns .long v6_user_fns .long v7_cache_fns +.endm + + /* + * ARM Ltd. Cortex A9 processor. + */ + .type __v7_ca9mp_proc_info, #object +__v7_ca9mp_proc_info: + .long 0x410fc090 + .long 0xff0ffff0 + __v7_proc __v7_ca9mp_setup .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info /* @@ -457,27 +460,5 @@ __v7_ca9mp_proc_info: __v7_proc_info: .long 0x000f0000 @ Required ID value .long 0x000f0000 @ Mask for ID - ALT_SMP(.long \ - PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ | \ - PMD_FLAGS_SMP) - ALT_UP(.long \ - PMD_TYPE_SECT | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ | \ - PMD_FLAGS_UP) - .long PMD_TYPE_SECT | \ - PMD_SECT_XN | \ - PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ - W(b) __v7_setup - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS - .long cpu_v7_name - .long v7_processor_functions - .long v7wbi_tlb_fns - .long v6_user_fns - .long v7_cache_fns + __v7_proc __v7_setup .size __v7_proc_info, . - __v7_proc_info -- cgit v1.2.3 From 15eb169bfec291faf25b158cfa9842b72f7803ad Mon Sep 17 00:00:00 2001 From: Pawel Moll Date: Fri, 20 May 2011 14:39:29 +0100 Subject: ARM: proc: add Cortex-A5 proc info This patch adds processor info for ARM Ltd. Cortex A5, which has SCU initialisation procedure identical to A9. Signed-off-by: Pawel Moll Signed-off-by: Will Deacon --- arch/arm/mm/proc-v7.S | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index a759ccafeaca..3185da27a537 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -278,6 +278,7 @@ cpu_resume_l1_flags: * It is assumed that: * - cache type register is implemented */ +__v7_ca5mp_setup: __v7_ca9mp_setup: #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, r0, c1, c0, 1) @@ -443,6 +444,16 @@ __v7_setup_stack: .long v7_cache_fns .endm + /* + * ARM Ltd. Cortex A5 processor. + */ + .type __v7_ca5mp_proc_info, #object +__v7_ca5mp_proc_info: + .long 0x410fc050 + .long 0xff0ffff0 + __v7_proc __v7_ca5mp_setup + .size __v7_ca5mp_proc_info, . - __v7_ca5mp_proc_info + /* * ARM Ltd. Cortex A9 processor. */ -- cgit v1.2.3 From 7665d9d2df2eb26284467c2f8591004bd511c75f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 12 Jan 2011 17:10:45 +0000 Subject: ARM: proc: add proc info for Cortex-A15MP using classic page tables Multicore implementations of the Cortex-A15 require bit 6 of the auxiliary control register to be set in order for cache and TLB maintenance operations to be broadcast between CPUs. This patch adds a new proc_info structure for Cortex-A15, which enables the SMP bit during setup and includes the new HWCAP for integer division. Signed-off-by: Will Deacon --- arch/arm/mm/proc-v7.S | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3185da27a537..593285419e75 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -280,12 +280,18 @@ cpu_resume_l1_flags: */ __v7_ca5mp_setup: __v7_ca9mp_setup: + mov r10, #(1 << 0) @ TLB ops broadcasting + b 1f +__v7_ca15mp_setup: + mov r10, #0 +1: #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, r0, c1, c0, 1) ALT_UP(mov r0, #(1 << 6)) @ fake it for UP tst r0, #(1 << 6) @ SMP/nAMP mode enabled? - orreq r0, r0, #(1 << 6) | (1 << 0) @ Enable SMP/nAMP mode and - mcreq p15, 0, r0, c1, c0, 1 @ TLB ops broadcasting + orreq r0, r0, #(1 << 6) @ Enable SMP/nAMP mode + orreq r0, r0, r10 @ Enable CPU-specific SMP bits + mcreq p15, 0, r0, c1, c0, 1 #endif __v7_setup: adr r12, __v7_setup_stack @ the local stack @@ -464,6 +470,16 @@ __v7_ca9mp_proc_info: __v7_proc __v7_ca9mp_setup .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info + /* + * ARM Ltd. Cortex A15 processor. + */ + .type __v7_ca15mp_proc_info, #object +__v7_ca15mp_proc_info: + .long 0x410fc0f0 + .long 0xff0ffff0 + __v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV + .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info + /* * Match any ARMv7 processor core. */ -- cgit v1.2.3 From 7b35fa47eecd0c746924a6d6c2a897d2cec778ba Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 3 Jun 2011 17:38:49 +0100 Subject: ARM: perf: remove confusing comment from v7 perf events backend The comment about measuring TLB misses and refills in the ARMv7 perf backend makes little sense and refers loosely to raw counters that should be used instead. This patch removes the comments to avoid any confusion. Signed-off-by: Will Deacon --- arch/arm/kernel/perf_event_v7.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 4960686afb58..554eba3dbf65 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -207,11 +207,6 @@ static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] }, }, [C(DTLB)] = { - /* - * Only ITLB misses and DTLB refills are supported. - * If users want the DTLB refills misses a raw counter - * must be used. - */ [C(OP_READ)] = { [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, @@ -323,11 +318,6 @@ static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] }, }, [C(DTLB)] = { - /* - * Only ITLB misses and DTLB refills are supported. - * If users want the DTLB refills misses a raw counter - * must be used. - */ [C(OP_READ)] = { [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, -- cgit v1.2.3 From 6d4eaf991c654af54a19c0fa48e0ad62cefbc37c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 19 Jan 2011 14:15:34 +0000 Subject: ARM: perf: add PMUv2 common event definitions The PMUv2 specification reserves a number of event encodings for common events. This patch adds these events to the common event enumeration in preparation for PMUv2 cores, such as Cortex-A15. Acked-by: Jean Pihet Signed-off-by: Will Deacon --- arch/arm/kernel/perf_event_v7.c | 35 +++++++++++++++++++++++++---------- 1 file changed, 25 insertions(+), 10 deletions(-) diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 554eba3dbf65..01b1145f07e5 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -17,17 +17,23 @@ */ #ifdef CONFIG_CPU_V7 -/* Common ARMv7 event types */ +/* + * Common ARMv7 event types + * + * Note: An implementation may not be able to count all of these events + * but the encodings are considered to be `reserved' in the case that + * they are not available. + */ enum armv7_perf_types { ARMV7_PERFCTR_PMNC_SW_INCR = 0x00, ARMV7_PERFCTR_IFETCH_MISS = 0x01, ARMV7_PERFCTR_ITLB_MISS = 0x02, - ARMV7_PERFCTR_DCACHE_REFILL = 0x03, - ARMV7_PERFCTR_DCACHE_ACCESS = 0x04, + ARMV7_PERFCTR_DCACHE_REFILL = 0x03, /* L1 */ + ARMV7_PERFCTR_DCACHE_ACCESS = 0x04, /* L1 */ ARMV7_PERFCTR_DTLB_REFILL = 0x05, ARMV7_PERFCTR_DREAD = 0x06, ARMV7_PERFCTR_DWRITE = 0x07, - + ARMV7_PERFCTR_INSTR_EXECUTED = 0x08, ARMV7_PERFCTR_EXC_TAKEN = 0x09, ARMV7_PERFCTR_EXC_EXECUTED = 0x0A, ARMV7_PERFCTR_CID_WRITE = 0x0B, @@ -39,21 +45,30 @@ enum armv7_perf_types { */ ARMV7_PERFCTR_PC_WRITE = 0x0C, ARMV7_PERFCTR_PC_IMM_BRANCH = 0x0D, + ARMV7_PERFCTR_PC_PROC_RETURN = 0x0E, ARMV7_PERFCTR_UNALIGNED_ACCESS = 0x0F, + + /* These events are defined by the PMUv2 supplement (ARM DDI 0457A). */ ARMV7_PERFCTR_PC_BRANCH_MIS_PRED = 0x10, ARMV7_PERFCTR_CLOCK_CYCLES = 0x11, - - ARMV7_PERFCTR_PC_BRANCH_MIS_USED = 0x12, + ARMV7_PERFCTR_PC_BRANCH_PRED = 0x12, + ARMV7_PERFCTR_MEM_ACCESS = 0x13, + ARMV7_PERFCTR_L1_ICACHE_ACCESS = 0x14, + ARMV7_PERFCTR_L1_DCACHE_WB = 0x15, + ARMV7_PERFCTR_L2_DCACHE_ACCESS = 0x16, + ARMV7_PERFCTR_L2_DCACHE_REFILL = 0x17, + ARMV7_PERFCTR_L2_DCACHE_WB = 0x18, + ARMV7_PERFCTR_BUS_ACCESS = 0x19, + ARMV7_PERFCTR_MEMORY_ERROR = 0x1A, + ARMV7_PERFCTR_INSTR_SPEC = 0x1B, + ARMV7_PERFCTR_TTBR_WRITE = 0x1C, + ARMV7_PERFCTR_BUS_CYCLES = 0x1D, ARMV7_PERFCTR_CPU_CYCLES = 0xFF }; /* ARMv7 Cortex-A8 specific event types */ enum armv7_a8_perf_types { - ARMV7_PERFCTR_INSTR_EXECUTED = 0x08, - - ARMV7_PERFCTR_PC_PROC_RETURN = 0x0E, - ARMV7_PERFCTR_WRITE_BUFFER_FULL = 0x40, ARMV7_PERFCTR_L2_STORE_MERGED = 0x41, ARMV7_PERFCTR_L2_STORE_BUFF = 0x42, -- cgit v1.2.3 From 0c205cbe20654616e2f8389c0c1ff707d9dccb63 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 3 Jun 2011 17:40:15 +0100 Subject: ARM: perf: add support for the Cortex-A5 PMU This patch adds support for the Cortex-A5 PMU to the ARMv7 perf-event backend. Signed-off-by: Will Deacon --- arch/arm/include/asm/perf_event.h | 1 + arch/arm/kernel/perf_event.c | 3 + arch/arm/kernel/perf_event_v7.c | 146 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 150 insertions(+) diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index c4aa4e8c6af9..207bd3c79ab6 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -24,6 +24,7 @@ enum arm_perf_pmu_ids { ARM_PERF_PMU_ID_V6MP, ARM_PERF_PMU_ID_CA8, ARM_PERF_PMU_ID_CA9, + ARM_PERF_PMU_ID_CA5, ARM_NUM_PMU_IDS, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index d53c0abc4dd3..df4e517687bf 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -660,6 +660,9 @@ init_hw_perf_events(void) case 0xC090: /* Cortex-A9 */ armpmu = armv7_a9_pmu_init(); break; + case 0xC050: /* Cortex-A5 */ + armpmu = armv7_a5_pmu_init(); + break; } /* Intel CPUs [xscale]. */ } else if (0x69 == implementor) { diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 01b1145f07e5..db1d6c4a32ac 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -153,6 +153,21 @@ enum armv7_a9_perf_types { ARMV7_PERFCTR_PLE_RQST_PROG = 0xA5 }; +/* ARMv7 Cortex-A5 specific event types */ +enum armv7_a5_perf_types { + ARMV7_PERFCTR_IRQ_TAKEN = 0x86, + ARMV7_PERFCTR_FIQ_TAKEN = 0x87, + + ARMV7_PERFCTR_EXT_MEM_RQST = 0xc0, + ARMV7_PERFCTR_NC_EXT_MEM_RQST = 0xc1, + ARMV7_PERFCTR_PREFETCH_LINEFILL = 0xc2, + ARMV7_PERFCTR_PREFETCH_LINEFILL_DROP = 0xc3, + ARMV7_PERFCTR_ENTER_READ_ALLOC = 0xc4, + ARMV7_PERFCTR_READ_ALLOC = 0xc5, + + ARMV7_PERFCTR_STALL_SB_FULL = 0xc9, +}; + /* * Cortex-A8 HW events mapping * @@ -378,6 +393,122 @@ static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] }, }; +/* + * Cortex-A5 HW events mapping + */ +static const unsigned armv7_a5_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, +}; + +static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_DCACHE_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_DCACHE_ACCESS, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_DCACHE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_PREFETCH_LINEFILL, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PREFETCH_LINEFILL_DROP, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS, + }, + /* + * The prefetch counters don't differentiate between the I + * side and the D side. + */ + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_PREFETCH_LINEFILL, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PREFETCH_LINEFILL_DROP, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + /* * Perf Events counters */ @@ -910,6 +1041,16 @@ static const struct arm_pmu *__init armv7_a9_pmu_init(void) armv7pmu.num_events = armv7_read_num_pmnc_events(); return &armv7pmu; } + +static const struct arm_pmu *__init armv7_a5_pmu_init(void) +{ + armv7pmu.id = ARM_PERF_PMU_ID_CA5; + armv7pmu.name = "ARMv7 Cortex-A5"; + armv7pmu.cache_map = &armv7_a5_perf_cache_map; + armv7pmu.event_map = &armv7_a5_perf_map; + armv7pmu.num_events = armv7_read_num_pmnc_events(); + return &armv7pmu; +} #else static const struct arm_pmu *__init armv7_a8_pmu_init(void) { @@ -920,4 +1061,9 @@ static const struct arm_pmu *__init armv7_a9_pmu_init(void) { return NULL; } + +static const struct arm_pmu *__init armv7_a5_pmu_init(void) +{ + return NULL; +} #endif /* CONFIG_CPU_V7 */ -- cgit v1.2.3 From 14abd038a7a209193c58ee7dde01ef4bf1523a91 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 19 Jan 2011 14:24:38 +0000 Subject: ARM: perf: add support for the Cortex-A15 PMU This patch adds support for the Cortex-A15 PMU to the ARMv7 perf-event backend. Signed-off-by: Will Deacon --- arch/arm/include/asm/perf_event.h | 1 + arch/arm/kernel/perf_event.c | 3 + arch/arm/kernel/perf_event_v7.c | 153 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 157 insertions(+) diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index 207bd3c79ab6..0f8e3827a89b 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -25,6 +25,7 @@ enum arm_perf_pmu_ids { ARM_PERF_PMU_ID_CA8, ARM_PERF_PMU_ID_CA9, ARM_PERF_PMU_ID_CA5, + ARM_PERF_PMU_ID_CA15, ARM_NUM_PMU_IDS, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index df4e517687bf..262ea67f60ae 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -663,6 +663,9 @@ init_hw_perf_events(void) case 0xC050: /* Cortex-A5 */ armpmu = armv7_a5_pmu_init(); break; + case 0xC0F0: /* Cortex-A15 */ + armpmu = armv7_a15_pmu_init(); + break; } /* Intel CPUs [xscale]. */ } else if (0x69 == implementor) { diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index db1d6c4a32ac..963317896c80 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -168,6 +168,24 @@ enum armv7_a5_perf_types { ARMV7_PERFCTR_STALL_SB_FULL = 0xc9, }; +/* ARMv7 Cortex-A15 specific event types */ +enum armv7_a15_perf_types { + ARMV7_PERFCTR_L1_DCACHE_READ_ACCESS = 0x40, + ARMV7_PERFCTR_L1_DCACHE_WRITE_ACCESS = 0x41, + ARMV7_PERFCTR_L1_DCACHE_READ_REFILL = 0x42, + ARMV7_PERFCTR_L1_DCACHE_WRITE_REFILL = 0x43, + + ARMV7_PERFCTR_L1_DTLB_READ_REFILL = 0x4C, + ARMV7_PERFCTR_L1_DTLB_WRITE_REFILL = 0x4D, + + ARMV7_PERFCTR_L2_DCACHE_READ_ACCESS = 0x50, + ARMV7_PERFCTR_L2_DCACHE_WRITE_ACCESS = 0x51, + ARMV7_PERFCTR_L2_DCACHE_READ_REFILL = 0x52, + ARMV7_PERFCTR_L2_DCACHE_WRITE_REFILL = 0x53, + + ARMV7_PERFCTR_SPEC_PC_WRITE = 0x76, +}; + /* * Cortex-A8 HW events mapping * @@ -509,6 +527,126 @@ static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] }, }; +/* + * Cortex-A15 HW events mapping + */ +static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_SPEC_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, +}; + +static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_L1_DCACHE_READ_ACCESS, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_L1_DCACHE_READ_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_L1_DCACHE_WRITE_ACCESS, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_L1_DCACHE_WRITE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + /* + * Not all performance counters differentiate between read + * and write accesses/misses so we're not always strictly + * correct, but it's the best we can do. Writes and reads get + * combined in these cases. + */ + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_L2_DCACHE_READ_ACCESS, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_L2_DCACHE_READ_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] + = ARMV7_PERFCTR_L2_DCACHE_WRITE_ACCESS, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_L2_DCACHE_WRITE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_L1_DTLB_READ_REFILL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_L1_DTLB_WRITE_REFILL, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(RESULT_MISS)] + = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + /* * Perf Events counters */ @@ -1051,6 +1189,16 @@ static const struct arm_pmu *__init armv7_a5_pmu_init(void) armv7pmu.num_events = armv7_read_num_pmnc_events(); return &armv7pmu; } + +static const struct arm_pmu *__init armv7_a15_pmu_init(void) +{ + armv7pmu.id = ARM_PERF_PMU_ID_CA15; + armv7pmu.name = "ARMv7 Cortex-A15"; + armv7pmu.cache_map = &armv7_a15_perf_cache_map; + armv7pmu.event_map = &armv7_a15_perf_map; + armv7pmu.num_events = armv7_read_num_pmnc_events(); + return &armv7pmu; +} #else static const struct arm_pmu *__init armv7_a8_pmu_init(void) { @@ -1066,4 +1214,9 @@ static const struct arm_pmu *__init armv7_a5_pmu_init(void) { return NULL; } + +static const struct arm_pmu *__init armv7_a15_pmu_init(void) +{ + return NULL; +} #endif /* CONFIG_CPU_V7 */ -- cgit v1.2.3 From f4daf06fc23b99df5ca5b3e892428b91e148cc52 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 6 Jun 2011 12:27:34 +0100 Subject: ARM: proc: add definition of cpu_reset for ARMv6 and ARMv7 cores This patch adds simple definitions of cpu_reset for ARMv6 and ARMv7 cores, which disable the MMU via the SCTLR. Signed-off-by: Will Deacon --- arch/arm/mm/proc-v6.S | 5 +++++ arch/arm/mm/proc-v7.S | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 5ec15431cf12..aedf3c5dbe4e 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -56,6 +56,11 @@ ENTRY(cpu_v6_proc_fin) */ .align 5 ENTRY(cpu_v6_reset) + mrc p15, 0, r1, c1, c0, 0 @ ctrl register + bic r1, r1, #0x1 @ ...............m + mcr p15, 0, r1, c1, c0, 0 @ disable MMU + mov r1, #0 + mcr p15, 0, r1, c7, c5, 4 @ ISB mov pc, r0 /* diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 593285419e75..54d1a63517c5 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -58,9 +58,16 @@ ENDPROC(cpu_v7_proc_fin) * to what would be the reset vector. * * - loc - location to jump to for soft reset + * + * This code must be executed using a flat identity mapping with + * caches disabled. */ .align 5 ENTRY(cpu_v7_reset) + mrc p15, 0, r1, c1, c0, 0 @ ctrl register + bic r1, r1, #0x1 @ ...............m + mcr p15, 0, r1, c1, c0, 0 @ disable MMU + isb mov pc, r0 ENDPROC(cpu_v7_reset) -- cgit v1.2.3 From c1f2d9991046769aa14a904ea2bf5434daf86262 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 5 Jul 2011 23:59:56 +0100 Subject: ARM: ensure tag tables are const Nothing should ever modify a tag table entry, so mark these const. Acked-by: Nicolas Pitre Tested-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/include/asm/setup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index ee2ad8ae07af..c3b5c796d819 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -187,7 +187,7 @@ struct tagtable { #define __tag __used __attribute__((__section__(".taglist.init"))) #define __tagtable(tag, fn) \ -static struct tagtable __tagtable_##fn __tag = { tag, fn } +static const struct tagtable __tagtable_##fn __tag = { tag, fn } /* * Memory map description -- cgit v1.2.3 From 3002b41bc6e5d66f7c1b5fd604f8f413e9bb37a5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 26 May 2011 11:40:54 +0100 Subject: ARM: decompressor: use better output sections Place read-only data in a .rodata output section, and the compressed piggy data in .piggydata. Place the .got.plt section before the .got section as is standard ELF practise. This allows the piggydata to be more easily extracted from the compressed vmlinux file for verification purposes. Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/boot/compressed/vmlinux.lds.in | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in index ea80abe78844..4e728834a1b9 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.in +++ b/arch/arm/boot/compressed/vmlinux.lds.in @@ -33,20 +33,24 @@ SECTIONS *(.text.*) *(.fixup) *(.gnu.warning) + *(.glue_7t) + *(.glue_7) + } + .rodata : { *(.rodata) *(.rodata.*) - *(.glue_7) - *(.glue_7t) + } + .piggydata : { *(.piggydata) - . = ALIGN(4); } + . = ALIGN(4); _etext = .; + .got.plt : { *(.got.plt) } _got_start = .; .got : { *(.got) } _got_end = .; - .got.plt : { *(.got.plt) } _edata = .; . = BSS_START; -- cgit v1.2.3 From 39df88872f64b8a7c438861460063eadf2ba9011 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 26 May 2011 11:25:33 +0100 Subject: ARM: vmlinux.lds: move discarded sections to beginning Rather than scattering the discarded sections throughout the linker file, move them to the start. Acked-by: Nicolas Pitre Tested-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/kernel/vmlinux.lds.S | 47 ++++++++++++++++++++----------------------- 1 file changed, 22 insertions(+), 25 deletions(-) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index e5287f21badc..cb46a9bad4f5 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -38,6 +38,28 @@ jiffies = jiffies_64 + 4; SECTIONS { + /* + * unwind exit sections must be discarded before the rest of the + * unwind sections get included. + */ + /DISCARD/ : { + *(.ARM.exidx.exit.text) + *(.ARM.extab.exit.text) + ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text)) + ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text)) +#ifndef CONFIG_HOTPLUG + *(.ARM.exidx.devexit.text) + *(.ARM.extab.devexit.text) +#endif +#ifndef CONFIG_MMU + *(.fixup) + *(__ex_table) +#endif +#ifndef CONFIG_SMP_ON_UP + *(.alt.smp.init) +#endif + } + #ifdef CONFIG_XIP_KERNEL . = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR); #else @@ -89,25 +111,6 @@ SECTIONS __init_end = .; #endif - /* - * unwind exit sections must be discarded before the rest of the - * unwind sections get included. - */ - /DISCARD/ : { - *(.ARM.exidx.exit.text) - *(.ARM.extab.exit.text) - ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text)) - ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text)) -#ifndef CONFIG_HOTPLUG - *(.ARM.exidx.devexit.text) - *(.ARM.extab.devexit.text) -#endif -#ifndef CONFIG_MMU - *(.fixup) - *(__ex_table) -#endif - } - .text : { /* Real text segment */ _text = .; /* Text and read-only data */ __exception_text_start = .; @@ -270,12 +273,6 @@ SECTIONS /* Default discards */ DISCARDS - -#ifndef CONFIG_SMP_ON_UP - /DISCARD/ : { - *(.alt.smp.init) - } -#endif } /* -- cgit v1.2.3 From 1604d79d372bcf0cf1aebcbdee251bd0f3d56665 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 5 Jul 2011 22:56:41 +0100 Subject: ARM: vmlinux.lds: rearrange .init output section Keep the various linker tables as separate output sections rather than combining them together into one big .init section. This makes the 'vmlinux' easier to see what is placed where. Acked-by: Nicolas Pitre Tested-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/kernel/vmlinux.lds.S | 47 ++++++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 18 deletions(-) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index cb46a9bad4f5..c8bb9b77c2ea 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -65,48 +65,59 @@ SECTIONS #else . = PAGE_OFFSET + TEXT_OFFSET; #endif - - .init : { /* Init code and data */ + .head.text : { _stext = .; - _sinittext = .; - HEAD_TEXT - INIT_TEXT - ARM_EXIT_KEEP(EXIT_TEXT) - _einittext = .; + HEAD_TEXT + } + INIT_TEXT_SECTION(8) + .exit.text : { + ARM_EXIT_KEEP(EXIT_TEXT) + } + .init.proc.info : { ARM_CPU_DISCARD(PROC_INFO) + } + .init.arch.info : { __arch_info_begin = .; - *(.arch.info.init) + *(.arch.info.init) __arch_info_end = .; + } + .init.tagtable : { __tagtable_begin = .; - *(.taglist.init) + *(.taglist.init) __tagtable_end = .; + } #ifdef CONFIG_SMP_ON_UP + .init.smpalt : { __smpalt_begin = .; - *(.alt.smp.init) + *(.alt.smp.init) __smpalt_end = .; + } #endif - + .init.pv_table : { __pv_table_begin = .; - *(.pv_table) + *(.pv_table) __pv_table_end = .; - + } + .init.data : { +#ifndef CONFIG_XIP_KERNEL + INIT_DATA +#endif INIT_SETUP(16) - INIT_CALLS CON_INITCALL SECURITY_INITCALL INIT_RAM_FS - + } #ifndef CONFIG_XIP_KERNEL - __init_begin = _stext; - INIT_DATA + .exit.data : { ARM_EXIT_KEEP(EXIT_DATA) -#endif } +#endif PERCPU_SECTION(32) #ifndef CONFIG_XIP_KERNEL + __init_begin = _stext; . = ALIGN(PAGE_SIZE); __init_end = .; #endif -- cgit v1.2.3 From 43fc9d2fa5585adfadd0fdc06a20626727cf985a Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 6 Jul 2011 00:01:20 +0100 Subject: ARM: vmlinux.lds: remove .rodata/.rodata1 from main .text segment RODATA() already handles these sections, so allow it to take care of them for us. Acked-by: Nicolas Pitre Tested-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/kernel/vmlinux.lds.S | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index c8bb9b77c2ea..fa812d03ff47 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -136,8 +136,6 @@ SECTIONS *(.fixup) #endif *(.gnu.warning) - *(.rodata) - *(.rodata.*) *(.glue_7) *(.glue_7t) . = ALIGN(4); -- cgit v1.2.3 From 3835d69a6c7048a28d0aea3cb8403d5e83a0f867 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 6 Jul 2011 10:39:34 +0100 Subject: ARM: vmlinux.lds: move init sections between text and data sections Place the init sections between the text and data sections. This means all code is grouped together at the beginning of the kernel image, and all data is at the end of the image. This avoids problems with the 24-bit branch instruction relocations becoming invalid with large initramfs images. Acked-by: Nicolas Pitre Tested-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/kernel/vmlinux.lds.S | 96 +++++++++++++++++++++---------------------- arch/arm/mm/init.c | 4 +- 2 files changed, 50 insertions(+), 50 deletions(-) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index fa812d03ff47..18574b7dbc14 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -69,6 +69,53 @@ SECTIONS _stext = .; HEAD_TEXT } + .text : { /* Real text segment */ + _text = .; /* Text and read-only data */ + __exception_text_start = .; + *(.exception.text) + __exception_text_end = .; + IRQENTRY_TEXT + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT +#ifdef CONFIG_MMU + *(.fixup) +#endif + *(.gnu.warning) + *(.glue_7) + *(.glue_7t) + . = ALIGN(4); + *(.got) /* Global offset table */ + ARM_CPU_KEEP(PROC_INFO) + } + + RO_DATA(PAGE_SIZE) + +#ifdef CONFIG_ARM_UNWIND + /* + * Stack unwinding tables + */ + . = ALIGN(8); + .ARM.unwind_idx : { + __start_unwind_idx = .; + *(.ARM.exidx*) + __stop_unwind_idx = .; + } + .ARM.unwind_tab : { + __start_unwind_tab = .; + *(.ARM.extab*) + __stop_unwind_tab = .; + } +#endif + + _etext = .; /* End of text and rodata section */ + +#ifndef CONFIG_XIP_KERNEL + . = ALIGN(PAGE_SIZE); + __init_begin = .; +#endif + INIT_TEXT_SECTION(8) .exit.text : { ARM_EXIT_KEEP(EXIT_TEXT) @@ -116,58 +163,11 @@ SECTIONS PERCPU_SECTION(32) -#ifndef CONFIG_XIP_KERNEL - __init_begin = _stext; - . = ALIGN(PAGE_SIZE); - __init_end = .; -#endif - - .text : { /* Real text segment */ - _text = .; /* Text and read-only data */ - __exception_text_start = .; - *(.exception.text) - __exception_text_end = .; - IRQENTRY_TEXT - TEXT_TEXT - SCHED_TEXT - LOCK_TEXT - KPROBES_TEXT -#ifdef CONFIG_MMU - *(.fixup) -#endif - *(.gnu.warning) - *(.glue_7) - *(.glue_7t) - . = ALIGN(4); - *(.got) /* Global offset table */ - ARM_CPU_KEEP(PROC_INFO) - } - - RO_DATA(PAGE_SIZE) - -#ifdef CONFIG_ARM_UNWIND - /* - * Stack unwinding tables - */ - . = ALIGN(8); - .ARM.unwind_idx : { - __start_unwind_idx = .; - *(.ARM.exidx*) - __stop_unwind_idx = .; - } - .ARM.unwind_tab : { - __start_unwind_tab = .; - *(.ARM.extab*) - __stop_unwind_tab = .; - } -#endif - - _etext = .; /* End of text and rodata section */ - #ifdef CONFIG_XIP_KERNEL __data_loc = ALIGN(4); /* location in binary */ . = PAGE_OFFSET + TEXT_OFFSET; #else + __init_end = .; . = ALIGN(THREAD_SIZE); __data_loc = .; #endif diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index c19571c40a21..b8e891243153 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -639,8 +639,8 @@ void __init mem_init(void) " pkmap : 0x%08lx - 0x%08lx (%4ld MB)\n" #endif " modules : 0x%08lx - 0x%08lx (%4ld MB)\n" - " .init : 0x%p" " - 0x%p" " (%4d kB)\n" " .text : 0x%p" " - 0x%p" " (%4d kB)\n" + " .init : 0x%p" " - 0x%p" " (%4d kB)\n" " .data : 0x%p" " - 0x%p" " (%4d kB)\n" " .bss : 0x%p" " - 0x%p" " (%4d kB)\n", @@ -662,8 +662,8 @@ void __init mem_init(void) #endif MLM(MODULES_VADDR, MODULES_END), - MLK_ROUNDUP(__init_begin, __init_end), MLK_ROUNDUP(_text, _etext), + MLK_ROUNDUP(__init_begin, __init_end), MLK_ROUNDUP(_sdata, _edata), MLK_ROUNDUP(__bss_start, __bss_stop)); -- cgit v1.2.3 From e2f81844efa2d44d326bef48e1c9e48926162bc6 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 6 Jul 2011 10:53:22 +0100 Subject: ARM: vmlinux.lds: use _text and _stext the same way as x86 x86 uses _text to mark the start of the kernel image including the head text, and _stext to mark the start of the .text section. Change our vmlinux.lds to conform. An audit of the places which use _stext and _text in arch/arm indicates no users of either symbol are impacted by this change. It does mean a slight change to /proc/iomem output. Acked-by: Nicolas Pitre Tested-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/kernel/vmlinux.lds.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 18574b7dbc14..bf977f8514f6 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -66,11 +66,11 @@ SECTIONS . = PAGE_OFFSET + TEXT_OFFSET; #endif .head.text : { - _stext = .; + _text = .; HEAD_TEXT } .text : { /* Real text segment */ - _text = .; /* Text and read-only data */ + _stext = .; /* Text and read-only data */ __exception_text_start = .; *(.exception.text) __exception_text_end = .; -- cgit v1.2.3 From 54d525735140e930d87c5afd1b0b3393ffdac021 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 7 Jul 2011 18:43:36 +0100 Subject: ARM: 6996/1: mm: Poison freed init memory Poisoning __init marked memory can be useful when tracking down obscure memory corruption bugs. Therefore, poison init memory with 0xe7fddef0 to catch bugs earlier. The poison value is an undefined instruction in ARM mode and branch to an undefined instruction in Thumb mode. Signed-off-by: Stephen Boyd Acked-by: Nicolas Pitre Signed-off-by: Russell King --- arch/arm/mm/init.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2c2cce9cd8c8..fdc87f9bda55 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -416,6 +416,17 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s) return pages; } +/* + * Poison init memory with an undefined instruction (ARM) or a branch to an + * undefined instruction (Thumb). + */ +static inline void poison_init_mem(void *s, size_t count) +{ + u32 *p = (u32 *)s; + while ((count = count - 4)) + *p++ = 0xe7fddef0; +} + static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn) { @@ -696,11 +707,13 @@ void free_initmem(void) #ifdef CONFIG_HAVE_TCM extern char __tcm_start, __tcm_end; + poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start); totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)), __phys_to_pfn(__pa(&__tcm_end)), "TCM link"); #endif + poison_init_mem(__init_begin, __init_end - __init_begin); if (!machine_is_integrator() && !machine_is_cintegrator()) totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)), __phys_to_pfn(__pa(__init_end)), @@ -713,10 +726,12 @@ static int keep_initrd; void free_initrd_mem(unsigned long start, unsigned long end) { - if (!keep_initrd) + if (!keep_initrd) { + poison_init_mem((void *)start, PAGE_ALIGN(end) - start); totalram_pages += free_area(__phys_to_pfn(__pa(start)), __phys_to_pfn(__pa(end)), "initrd"); + } } static int __init keepinitrd_setup(char *__unused) -- cgit v1.2.3 From 3973c337759cd201773a0ecc7b6f39f1ea2a6287 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 8 Jul 2011 14:02:21 +0100 Subject: ARM: dmabounce: simplify dma_set_mask() Simplify the dmabounce specific code in dma_set_mask(). We can just omit setting the dma mask if dmabounce is enabled (we will have already set dma mask via callbacks when the device is created in that case.) Signed-off-by: Russell King --- arch/arm/include/asm/dma-mapping.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 4ad25337f927..94662f4c9ea7 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -133,18 +133,12 @@ static inline int dma_supported(struct device *dev, u64 mask) static inline int dma_set_mask(struct device *dev, u64 dma_mask) { -#ifdef CONFIG_DMABOUNCE - if (dev->archdata.dmabounce) { - if (dma_mask >= ISA_DMA_THRESHOLD) - return 0; - else - return -EIO; - } -#endif if (!dev->dma_mask || !dma_supported(dev, dma_mask)) return -EIO; +#ifndef CONFIG_DMABOUNCE *dev->dma_mask = dma_mask; +#endif return 0; } -- cgit v1.2.3 From c7e89b16eb90e7bdf0d71bd5ba265ce8d424f30b Mon Sep 17 00:00:00 2001 From: Heechul Yun Date: Fri, 8 Jul 2011 13:32:34 +0100 Subject: ARM: 6995/2: mm: remove unnecessary cache flush on v6 copypage Originally introduced to maintain coherency between icache and dcache in v6 nonaliasing mode. This is now handled by __sync_icache_dcache since c0177800, therefore unnecessary in this function. Signed-off-by: Heechul Yun Acked-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/mm/copypage-v6.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index bdba6c65c901..63cca0097130 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -41,7 +41,6 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to, kfrom = kmap_atomic(from, KM_USER0); kto = kmap_atomic(to, KM_USER1); copy_page(kto, kfrom); - __cpuc_flush_dcache_area(kto, PAGE_SIZE); kunmap_atomic(kto, KM_USER1); kunmap_atomic(kfrom, KM_USER0); } -- cgit v1.2.3 From af61bdf035e2e4dd646b37b270bd558188a127c0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 9 Jul 2011 13:44:04 +0100 Subject: ARM: vfp: rename last_VFP_context to vfp_current_hw_state Rename the slightly confusing 'last_VFP_context' variable to be more descriptive of what it actually is. This variable stores a pointer to the current owner's vfpstate structure for the context held in the VFP hardware. Signed-off-by: Russell King --- arch/arm/vfp/vfphw.S | 10 +++++----- arch/arm/vfp/vfpmodule.c | 36 +++++++++++++++++++++--------------- 2 files changed, 26 insertions(+), 20 deletions(-) diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 9897dcfc16d6..c75443e204b2 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -77,9 +77,9 @@ ENTRY(vfp_support_entry) bne look_for_VFP_exceptions @ VFP is already enabled DBGSTR1 "enable %x", r10 - ldr r3, last_VFP_context_address + ldr r3, vfp_current_hw_state_address orr r1, r1, #FPEXC_EN @ user FPEXC has the enable bit set - ldr r4, [r3, r11, lsl #2] @ last_VFP_context pointer + ldr r4, [r3, r11, lsl #2] @ vfp_current_hw_state pointer bic r5, r1, #FPEXC_EX @ make sure exceptions are disabled cmp r4, r10 beq check_for_exception @ we are returning to the same @@ -116,7 +116,7 @@ ENTRY(vfp_support_entry) no_old_VFP_process: DBGSTR1 "load state %p", r10 - str r10, [r3, r11, lsl #2] @ update the last_VFP_context pointer + str r10, [r3, r11, lsl #2] @ update the vfp_current_hw_state pointer @ Load the saved state back into the VFP VFPFLDMIA r10, r5 @ reload the working registers while @ FPEXC is in a safe state @@ -207,8 +207,8 @@ ENTRY(vfp_save_state) ENDPROC(vfp_save_state) .align -last_VFP_context_address: - .word last_VFP_context +vfp_current_hw_state_address: + .word vfp_current_hw_state .macro tbl_branch, base, tmp, shift #ifdef CONFIG_THUMB2_KERNEL diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index f25e7ec89416..3640351171b8 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -33,7 +33,13 @@ void vfp_support_entry(void); void vfp_null_entry(void); void (*vfp_vector)(void) = vfp_null_entry; -union vfp_state *last_VFP_context[NR_CPUS]; + +/* + * The pointer to the vfpstate structure of the thread which currently + * owns the context held in the VFP hardware, or NULL if the hardware + * context is invalid. + */ +union vfp_state *vfp_current_hw_state[NR_CPUS]; /* * Dual-use variable. @@ -57,12 +63,12 @@ static void vfp_thread_flush(struct thread_info *thread) /* * Disable VFP to ensure we initialize it first. We must ensure - * that the modification of last_VFP_context[] and hardware disable + * that the modification of vfp_current_hw_state[] and hardware disable * are done for the same CPU and without preemption. */ cpu = get_cpu(); - if (last_VFP_context[cpu] == vfp) - last_VFP_context[cpu] = NULL; + if (vfp_current_hw_state[cpu] == vfp) + vfp_current_hw_state[cpu] = NULL; fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); put_cpu(); } @@ -73,8 +79,8 @@ static void vfp_thread_exit(struct thread_info *thread) union vfp_state *vfp = &thread->vfpstate; unsigned int cpu = get_cpu(); - if (last_VFP_context[cpu] == vfp) - last_VFP_context[cpu] = NULL; + if (vfp_current_hw_state[cpu] == vfp) + vfp_current_hw_state[cpu] = NULL; put_cpu(); } @@ -129,9 +135,9 @@ static int vfp_notifier(struct notifier_block *self, unsigned long cmd, void *v) * case the thread migrates to a different CPU. The * restoring is done lazily. */ - if ((fpexc & FPEXC_EN) && last_VFP_context[cpu]) { - vfp_save_state(last_VFP_context[cpu], fpexc); - last_VFP_context[cpu]->hard.cpu = cpu; + if ((fpexc & FPEXC_EN) && vfp_current_hw_state[cpu]) { + vfp_save_state(vfp_current_hw_state[cpu], fpexc); + vfp_current_hw_state[cpu]->hard.cpu = cpu; } /* * Thread migration, just force the reloading of the @@ -139,7 +145,7 @@ static int vfp_notifier(struct notifier_block *self, unsigned long cmd, void *v) * contain stale data. */ if (thread->vfpstate.hard.cpu != cpu) - last_VFP_context[cpu] = NULL; + vfp_current_hw_state[cpu] = NULL; #endif /* @@ -415,7 +421,7 @@ static int vfp_pm_suspend(void) } /* clear any information we had about last context state */ - memset(last_VFP_context, 0, sizeof(last_VFP_context)); + memset(vfp_current_hw_state, 0, sizeof(vfp_current_hw_state)); return 0; } @@ -451,7 +457,7 @@ void vfp_sync_hwstate(struct thread_info *thread) * If the thread we're interested in is the current owner of the * hardware VFP state, then we need to save its state. */ - if (last_VFP_context[cpu] == &thread->vfpstate) { + if (vfp_current_hw_state[cpu] == &thread->vfpstate) { u32 fpexc = fmrx(FPEXC); /* @@ -473,7 +479,7 @@ void vfp_flush_hwstate(struct thread_info *thread) * If the thread we're interested in is the current owner of the * hardware VFP state, then we need to save its state. */ - if (last_VFP_context[cpu] == &thread->vfpstate) { + if (vfp_current_hw_state[cpu] == &thread->vfpstate) { u32 fpexc = fmrx(FPEXC); fmxr(FPEXC, fpexc & ~FPEXC_EN); @@ -482,7 +488,7 @@ void vfp_flush_hwstate(struct thread_info *thread) * Set the context to NULL to force a reload the next time * the thread uses the VFP. */ - last_VFP_context[cpu] = NULL; + vfp_current_hw_state[cpu] = NULL; } #ifdef CONFIG_SMP @@ -514,7 +520,7 @@ static int vfp_hotplug(struct notifier_block *b, unsigned long action, { if (action == CPU_DYING || action == CPU_DYING_FROZEN) { unsigned int cpu = (long)hcpu; - last_VFP_context[cpu] = NULL; + vfp_current_hw_state[cpu] = NULL; } else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN) vfp_enable(NULL); return NOTIFY_OK; -- cgit v1.2.3 From 08409c33d6fdb43fa19d7dbdafd4f280b7835592 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 9 Jul 2011 14:24:36 +0100 Subject: ARM: vfp: rename check_exception to vfp_hw_state_valid Rename this branch to more accurately reflect why its taken, rather than what the following code does. It is the only caller of this code. This helps to clarify following changes, yet this change results in no actual code change. Document the VFP hardware state at the target of this branch. Signed-off-by: Russell King --- arch/arm/vfp/vfphw.S | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index c75443e204b2..404538ae591d 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -81,11 +81,8 @@ ENTRY(vfp_support_entry) orr r1, r1, #FPEXC_EN @ user FPEXC has the enable bit set ldr r4, [r3, r11, lsl #2] @ vfp_current_hw_state pointer bic r5, r1, #FPEXC_EX @ make sure exceptions are disabled - cmp r4, r10 - beq check_for_exception @ we are returning to the same - @ process, so the registers are - @ still there. In this case, we do - @ not want to drop a pending exception. + cmp r4, r10 @ this thread owns the hw context? + beq vfp_hw_state_valid VFPFMXR FPEXC, r5 @ enable VFP, disable any pending @ exceptions, so we can get at the @@ -132,7 +129,8 @@ no_old_VFP_process: #endif VFPFMXR FPSCR, r5 @ restore status -check_for_exception: +@ The context stored in the VFP hardware is up to date with this thread +vfp_hw_state_valid: tst r1, #FPEXC_EX bne process_exception @ might as well handle the pending @ exception before retrying branch -- cgit v1.2.3 From f8f2a8522a88aacd62a310ce49e8dac530d1b403 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 9 Jul 2011 16:09:43 +0100 Subject: ARM: vfp: fix a hole in VFP thread migration Fix a hole in the VFP thread migration. Lets define two threads. Thread 1, we'll call 'interesting_thread' which is a thread which is running on CPU0, using VFP (so vfp_current_hw_state[0] = &interesting_thread->vfpstate) and gets migrated off to CPU1, where it continues execution of VFP instructions. Thread 2, we'll call 'new_cpu0_thread' which is the thread which takes over on CPU0. This has also been using VFP, and last used VFP on CPU0, but doesn't use it again. The following code will be executed twice: cpu = thread->cpu; /* * On SMP, if VFP is enabled, save the old state in * case the thread migrates to a different CPU. The * restoring is done lazily. */ if ((fpexc & FPEXC_EN) && vfp_current_hw_state[cpu]) { vfp_save_state(vfp_current_hw_state[cpu], fpexc); vfp_current_hw_state[cpu]->hard.cpu = cpu; } /* * Thread migration, just force the reloading of the * state on the new CPU in case the VFP registers * contain stale data. */ if (thread->vfpstate.hard.cpu != cpu) vfp_current_hw_state[cpu] = NULL; The first execution will be on CPU0 to switch away from 'interesting_thread'. interesting_thread->cpu will be 0. So, vfp_current_hw_state[0] points at interesting_thread->vfpstate. The hardware state will be saved, along with the CPU number (0) that it was executing on. 'thread' will be 'new_cpu0_thread' with new_cpu0_thread->cpu = 0. Also, because it was executing on CPU0, new_cpu0_thread->vfpstate.hard.cpu = 0, and so the thread migration check is not triggered. This means that vfp_current_hw_state[0] remains pointing at interesting_thread. The second execution will be on CPU1 to switch _to_ 'interesting_thread'. So, 'thread' will be 'interesting_thread' and interesting_thread->cpu now will be 1. The previous thread executing on CPU1 is not relevant to this so we shall ignore that. We get to the thread migration check. Here, we discover that interesting_thread->vfpstate.hard.cpu = 0, yet interesting_thread->cpu is now 1, indicating thread migration. We set vfp_current_hw_state[1] to NULL. So, at this point vfp_current_hw_state[] contains the following: [0] = &interesting_thread->vfpstate [1] = NULL Our interesting thread now executes a VFP instruction, takes a fault which loads the state into the VFP hardware. Now, through the assembly we now have: [0] = &interesting_thread->vfpstate [1] = &interesting_thread->vfpstate CPU1 stops due to ptrace (and so saves its VFP state) using the thread switch code above), and CPU0 calls vfp_sync_hwstate(). if (vfp_current_hw_state[cpu] == &thread->vfpstate) { vfp_save_state(&thread->vfpstate, fpexc | FPEXC_EN); BANG, we corrupt interesting_thread's VFP state by overwriting the more up-to-date state saved by CPU1 with the old VFP state from CPU0. Fix this by ensuring that we have sane semantics for the various state describing variables: 1. vfp_current_hw_state[] points to the current owner of the context information stored in each CPUs hardware, or NULL if that state information is invalid. 2. thread->vfpstate.hard.cpu always contains the most recent CPU number which the state was loaded into or NR_CPUS if no CPU owns the state. So, for a particular CPU to be a valid owner of the VFP state for a particular thread t, two things must be true: vfp_current_hw_state[cpu] == &t->vfpstate && t->vfpstate.hard.cpu == cpu. and that is valid from the moment a CPU loads the saved VFP context into the hardware. This gives clear and consistent semantics to interpreting these variables. This patch also fixes thread copying, ensuring that t->vfpstate.hard.cpu is invalidated, otherwise CPU0 may believe it was the last owner. The hole can happen thus: - thread1 runs on CPU2 using VFP, migrates to CPU3, exits and thread_info freed. - New thread allocated from a previously running thread on CPU2, reusing memory for thread1 and copying vfp.hard.cpu. At this point, the following are true: new_thread1->vfpstate.hard.cpu == 2 &new_thread1->vfpstate == vfp_current_hw_state[2] Lastly, this also addresses thread flushing in a similar way to thread copying. Hole is: - thread runs on CPU0, using VFP, migrates to CPU1 but does not use VFP. - thread calls execve(), so thread flush happens, leaving vfp_current_hw_state[0] intact. This vfpstate is memset to 0 causing thread->vfpstate.hard.cpu = 0. - thread migrates back to CPU0 before using VFP. At this point, the following are true: thread->vfpstate.hard.cpu == 0 &thread->vfpstate == vfp_current_hw_state[0] Signed-off-by: Russell King --- arch/arm/kernel/asm-offsets.c | 3 ++ arch/arm/vfp/vfphw.S | 43 +++++++++++++++---- arch/arm/vfp/vfpmodule.c | 98 +++++++++++++++++++++++-------------------- 3 files changed, 89 insertions(+), 55 deletions(-) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 927522cfc12e..16baba2e4369 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -59,6 +59,9 @@ int main(void) DEFINE(TI_TP_VALUE, offsetof(struct thread_info, tp_value)); DEFINE(TI_FPSTATE, offsetof(struct thread_info, fpstate)); DEFINE(TI_VFPSTATE, offsetof(struct thread_info, vfpstate)); +#ifdef CONFIG_SMP + DEFINE(VFP_CPU, offsetof(union vfp_state, hard.cpu)); +#endif #ifdef CONFIG_ARM_THUMBEE DEFINE(TI_THUMBEE_STATE, offsetof(struct thread_info, thumbee_state)); #endif diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 404538ae591d..2d30c7f6edd3 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -82,19 +82,22 @@ ENTRY(vfp_support_entry) ldr r4, [r3, r11, lsl #2] @ vfp_current_hw_state pointer bic r5, r1, #FPEXC_EX @ make sure exceptions are disabled cmp r4, r10 @ this thread owns the hw context? +#ifndef CONFIG_SMP + @ For UP, checking that this thread owns the hw context is + @ sufficient to determine that the hardware state is valid. beq vfp_hw_state_valid + @ On UP, we lazily save the VFP context. As a different + @ thread wants ownership of the VFP hardware, save the old + @ state if there was a previous (valid) owner. + VFPFMXR FPEXC, r5 @ enable VFP, disable any pending @ exceptions, so we can get at the @ rest of it -#ifndef CONFIG_SMP - @ Save out the current registers to the old thread state - @ No need for SMP since this is not done lazily - DBGSTR1 "save old state %p", r4 - cmp r4, #0 - beq no_old_VFP_process + cmp r4, #0 @ if the vfp_current_hw_state is NULL + beq vfp_reload_hw @ then the hw state needs reloading VFPFSTMIA r4, r5 @ save the working registers VFPFMRX r5, FPSCR @ current status #ifndef CONFIG_CPU_FEROCEON @@ -107,11 +110,33 @@ ENTRY(vfp_support_entry) 1: #endif stmia r4, {r1, r5, r6, r8} @ save FPEXC, FPSCR, FPINST, FPINST2 - @ and point r4 at the word at the - @ start of the register dump +vfp_reload_hw: + +#else + @ For SMP, if this thread does not own the hw context, then we + @ need to reload it. No need to save the old state as on SMP, + @ we always save the state when we switch away from a thread. + bne vfp_reload_hw + + @ This thread has ownership of the current hardware context. + @ However, it may have been migrated to another CPU, in which + @ case the saved state is newer than the hardware context. + @ Check this by looking at the CPU number which the state was + @ last loaded onto. + ldr ip, [r10, #VFP_CPU] + teq ip, r11 + beq vfp_hw_state_valid + +vfp_reload_hw: + @ We're loading this threads state into the VFP hardware. Update + @ the CPU number which contains the most up to date VFP context. + str r11, [r10, #VFP_CPU] + + VFPFMXR FPEXC, r5 @ enable VFP, disable any pending + @ exceptions, so we can get at the + @ rest of it #endif -no_old_VFP_process: DBGSTR1 "load state %p", r10 str r10, [r3, r11, lsl #2] @ update the vfp_current_hw_state pointer @ Load the saved state back into the VFP diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 3640351171b8..08ff93fa533c 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -34,19 +34,52 @@ void vfp_null_entry(void); void (*vfp_vector)(void) = vfp_null_entry; +/* + * Dual-use variable. + * Used in startup: set to non-zero if VFP checks fail + * After startup, holds VFP architecture + */ +unsigned int VFP_arch; + /* * The pointer to the vfpstate structure of the thread which currently * owns the context held in the VFP hardware, or NULL if the hardware * context is invalid. + * + * For UP, this is sufficient to tell which thread owns the VFP context. + * However, for SMP, we also need to check the CPU number stored in the + * saved state too to catch migrations. */ union vfp_state *vfp_current_hw_state[NR_CPUS]; /* - * Dual-use variable. - * Used in startup: set to non-zero if VFP checks fail - * After startup, holds VFP architecture + * Is 'thread's most up to date state stored in this CPUs hardware? + * Must be called from non-preemptible context. */ -unsigned int VFP_arch; +static bool vfp_state_in_hw(unsigned int cpu, struct thread_info *thread) +{ +#ifdef CONFIG_SMP + if (thread->vfpstate.hard.cpu != cpu) + return false; +#endif + return vfp_current_hw_state[cpu] == &thread->vfpstate; +} + +/* + * Force a reload of the VFP context from the thread structure. We do + * this by ensuring that access to the VFP hardware is disabled, and + * clear last_VFP_context. Must be called from non-preemptible context. + */ +static void vfp_force_reload(unsigned int cpu, struct thread_info *thread) +{ + if (vfp_state_in_hw(cpu, thread)) { + fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); + vfp_current_hw_state[cpu] = NULL; + } +#ifdef CONFIG_SMP + thread->vfpstate.hard.cpu = NR_CPUS; +#endif +} /* * Per-thread VFP initialization. @@ -60,6 +93,9 @@ static void vfp_thread_flush(struct thread_info *thread) vfp->hard.fpexc = FPEXC_EN; vfp->hard.fpscr = FPSCR_ROUND_NEAREST; +#ifdef CONFIG_SMP + vfp->hard.cpu = NR_CPUS; +#endif /* * Disable VFP to ensure we initialize it first. We must ensure @@ -90,6 +126,9 @@ static void vfp_thread_copy(struct thread_info *thread) vfp_sync_hwstate(parent); thread->vfpstate = parent->vfpstate; +#ifdef CONFIG_SMP + thread->vfpstate.hard.cpu = NR_CPUS; +#endif } /* @@ -135,17 +174,8 @@ static int vfp_notifier(struct notifier_block *self, unsigned long cmd, void *v) * case the thread migrates to a different CPU. The * restoring is done lazily. */ - if ((fpexc & FPEXC_EN) && vfp_current_hw_state[cpu]) { + if ((fpexc & FPEXC_EN) && vfp_current_hw_state[cpu]) vfp_save_state(vfp_current_hw_state[cpu], fpexc); - vfp_current_hw_state[cpu]->hard.cpu = cpu; - } - /* - * Thread migration, just force the reloading of the - * state on the new CPU in case the VFP registers - * contain stale data. - */ - if (thread->vfpstate.hard.cpu != cpu) - vfp_current_hw_state[cpu] = NULL; #endif /* @@ -449,15 +479,15 @@ static void vfp_pm_init(void) static inline void vfp_pm_init(void) { } #endif /* CONFIG_PM */ +/* + * Ensure that the VFP state stored in 'thread->vfpstate' is up to date + * with the hardware state. + */ void vfp_sync_hwstate(struct thread_info *thread) { unsigned int cpu = get_cpu(); - /* - * If the thread we're interested in is the current owner of the - * hardware VFP state, then we need to save its state. - */ - if (vfp_current_hw_state[cpu] == &thread->vfpstate) { + if (vfp_state_in_hw(cpu, thread)) { u32 fpexc = fmrx(FPEXC); /* @@ -471,36 +501,13 @@ void vfp_sync_hwstate(struct thread_info *thread) put_cpu(); } +/* Ensure that the thread reloads the hardware VFP state on the next use. */ void vfp_flush_hwstate(struct thread_info *thread) { unsigned int cpu = get_cpu(); - /* - * If the thread we're interested in is the current owner of the - * hardware VFP state, then we need to save its state. - */ - if (vfp_current_hw_state[cpu] == &thread->vfpstate) { - u32 fpexc = fmrx(FPEXC); + vfp_force_reload(cpu, thread); - fmxr(FPEXC, fpexc & ~FPEXC_EN); - - /* - * Set the context to NULL to force a reload the next time - * the thread uses the VFP. - */ - vfp_current_hw_state[cpu] = NULL; - } - -#ifdef CONFIG_SMP - /* - * For SMP we still have to take care of the case where the thread - * migrates to another CPU and then back to the original CPU on which - * the last VFP user is still the same thread. Mark the thread VFP - * state as belonging to a non-existent CPU so that the saved one will - * be reloaded in the above case. - */ - thread->vfpstate.hard.cpu = NR_CPUS; -#endif put_cpu(); } @@ -519,8 +526,7 @@ static int vfp_hotplug(struct notifier_block *b, unsigned long action, void *hcpu) { if (action == CPU_DYING || action == CPU_DYING_FROZEN) { - unsigned int cpu = (long)hcpu; - vfp_current_hw_state[cpu] = NULL; + vfp_force_reload((long)hcpu, current_thread_info()); } else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN) vfp_enable(NULL); return NOTIFY_OK; -- cgit v1.2.3 From 19dad35fe0f10df8f0524f98037469e3a0dd1ec2 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 9 Jul 2011 17:41:33 +0100 Subject: ARM: vfp: ensure that thread flushing works if preempted Prevent a preemption event causing the initialized VFP state being overwritten by ensuring that the VFP hardware access is disabled prior to starting initialization. We can then do this in safety while still allowing preemption to occur. Signed-off-by: Russell King --- arch/arm/vfp/vfpmodule.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 08ff93fa533c..0a96f71f0abd 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -89,24 +89,27 @@ static void vfp_thread_flush(struct thread_info *thread) union vfp_state *vfp = &thread->vfpstate; unsigned int cpu; - memset(vfp, 0, sizeof(union vfp_state)); - - vfp->hard.fpexc = FPEXC_EN; - vfp->hard.fpscr = FPSCR_ROUND_NEAREST; -#ifdef CONFIG_SMP - vfp->hard.cpu = NR_CPUS; -#endif - /* * Disable VFP to ensure we initialize it first. We must ensure - * that the modification of vfp_current_hw_state[] and hardware disable - * are done for the same CPU and without preemption. + * that the modification of vfp_current_hw_state[] and hardware + * disable are done for the same CPU and without preemption. + * + * Do this first to ensure that preemption won't overwrite our + * state saving should access to the VFP be enabled at this point. */ cpu = get_cpu(); if (vfp_current_hw_state[cpu] == vfp) vfp_current_hw_state[cpu] = NULL; fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); put_cpu(); + + memset(vfp, 0, sizeof(union vfp_state)); + + vfp->hard.fpexc = FPEXC_EN; + vfp->hard.fpscr = FPSCR_ROUND_NEAREST; +#ifdef CONFIG_SMP + vfp->hard.cpu = NR_CPUS; +#endif } static void vfp_thread_exit(struct thread_info *thread) -- cgit v1.2.3 From 022ae537b23cb14a391565e9ad9e9945f4b17138 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 8 Jul 2011 21:26:59 +0100 Subject: ARM: dma: replace ISA_DMA_THRESHOLD with a variable ISA_DMA_THRESHOLD has been unused by non-arch code, so lets now get rid of it from ARM by replacing it with arm_dma_zone_mask. Move dma_supported() and dma_set_mask() out of line, and have dma_supported() check this new variable instead. Signed-off-by: Russell King --- arch/arm/include/asm/dma-mapping.h | 29 ++--------------------------- arch/arm/include/asm/memory.h | 12 ------------ arch/arm/mm/dma-mapping.c | 35 ++++++++++++++++++++++++++++++++--- arch/arm/mm/init.c | 10 ++++++++++ arch/arm/mm/mm.h | 6 ++++++ 5 files changed, 50 insertions(+), 42 deletions(-) diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 94662f4c9ea7..7a21d0bf7134 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -115,33 +115,8 @@ static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off, ___dma_page_dev_to_cpu(page, off, size, dir); } -/* - * Return whether the given device DMA address mask can be supported - * properly. For example, if your device can only drive the low 24-bits - * during bus mastering, then you would pass 0x00ffffff as the mask - * to this function. - * - * FIXME: This should really be a platform specific issue - we should - * return false if GFP_DMA allocations may not satisfy the supplied 'mask'. - */ -static inline int dma_supported(struct device *dev, u64 mask) -{ - if (mask < ISA_DMA_THRESHOLD) - return 0; - return 1; -} - -static inline int dma_set_mask(struct device *dev, u64 dma_mask) -{ - if (!dev->dma_mask || !dma_supported(dev, dma_mask)) - return -EIO; - -#ifndef CONFIG_DMABOUNCE - *dev->dma_mask = dma_mask; -#endif - - return 0; -} +extern int dma_supported(struct device *, u64); +extern int dma_set_mask(struct device *, u64); /* * DMA errors are defined by all-bits-set in the DMA address. diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index af44a8fb3480..b8de516e600e 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -203,18 +203,6 @@ static inline unsigned long __phys_to_virt(unsigned long x) #define PHYS_OFFSET PLAT_PHYS_OFFSET #endif -/* - * The DMA mask corresponding to the maximum bus address allocatable - * using GFP_DMA. The default here places no restriction on DMA - * allocations. This must be the smallest DMA mask in the system, - * so a successful GFP_DMA allocation will always satisfy this. - */ -#ifndef ARM_DMA_ZONE_SIZE -#define ISA_DMA_THRESHOLD (0xffffffffULL) -#else -#define ISA_DMA_THRESHOLD (PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1) -#endif - /* * PFNs are used to describe any physical page; this means * PFN 0 == physical address 0. diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 82a093cee09a..0a0a1e7c20d2 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -25,9 +25,11 @@ #include #include +#include "mm.h" + static u64 get_coherent_dma_mask(struct device *dev) { - u64 mask = ISA_DMA_THRESHOLD; + u64 mask = (u64)arm_dma_limit; if (dev) { mask = dev->coherent_dma_mask; @@ -41,10 +43,10 @@ static u64 get_coherent_dma_mask(struct device *dev) return 0; } - if ((~mask) & ISA_DMA_THRESHOLD) { + if ((~mask) & (u64)arm_dma_limit) { dev_warn(dev, "coherent DMA mask %#llx is smaller " "than system GFP_DMA mask %#llx\n", - mask, (unsigned long long)ISA_DMA_THRESHOLD); + mask, (u64)arm_dma_limit); return 0; } } @@ -657,6 +659,33 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } EXPORT_SYMBOL(dma_sync_sg_for_device); +/* + * Return whether the given device DMA address mask can be supported + * properly. For example, if your device can only drive the low 24-bits + * during bus mastering, then you would pass 0x00ffffff as the mask + * to this function. + */ +int dma_supported(struct device *dev, u64 mask) +{ + if (mask < (u64)arm_dma_limit) + return 0; + return 1; +} +EXPORT_SYMBOL(dma_supported); + +int dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (!dev->dma_mask || !dma_supported(dev, dma_mask)) + return -EIO; + +#ifndef CONFIG_DMABOUNCE + *dev->dma_mask = dma_mask; +#endif + + return 0; +} +EXPORT_SYMBOL(dma_set_mask); + #define PREALLOC_DMA_DEBUG_ENTRIES 4096 static int __init dma_debug_do_init(void) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index c19571c40a21..17d6cd0c57ed 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -212,6 +212,14 @@ static void __init arm_bootmem_init(unsigned long start_pfn, } #ifdef CONFIG_ZONE_DMA +/* + * The DMA mask corresponding to the maximum bus address allocatable + * using GFP_DMA. The default here places no restriction on DMA + * allocations. This must be the smallest DMA mask in the system, + * so a successful GFP_DMA allocation will always satisfy this. + */ +u32 arm_dma_limit; + static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, unsigned long dma_size) { @@ -278,6 +286,8 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, */ arm_adjust_dma_zone(zone_size, zhole_size, ARM_DMA_ZONE_SIZE >> PAGE_SHIFT); + + arm_dma_limit = PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1; #endif free_area_init_node(0, zone_size, min, zhole_size); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 5b3d7d543659..010566799c80 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -23,5 +23,11 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page #endif +#ifdef CONFIG_ZONE_DMA +extern u32 arm_dma_limit; +#else +#define arm_dma_limit ((u32)~0) +#endif + void __init bootmem_init(void); void arm_mm_memblock_reserve(void); -- cgit v1.2.3 From 594810621d9605dd40b6ce42e2e188a7dd6ba27c Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 18 Mar 2011 17:32:44 +0000 Subject: ARM: Thumb-2: Fix exception return sequence to restore stack correctly The implementation of svc_exit didn't take into account any stack hole created by svc_entry; as happens with the undef handler when kprobes are configured. The fix is to read the saved value of SP rather than trying to calculate it. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/entry-header.S | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 051166c2a932..83e29adced6c 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -121,15 +121,13 @@ .endm #else /* CONFIG_THUMB2_KERNEL */ .macro svc_exit, rpsr + ldr lr, [sp, #S_SP] @ top of the stack + ldrd r0, r1, [sp, #S_LR] @ calling lr and pc clrex @ clear the exclusive monitor - ldr r0, [sp, #S_SP] @ top of the stack - ldr r1, [sp, #S_PC] @ return address - tst r0, #4 @ orig stack 8-byte aligned? - stmdb r0, {r1, \rpsr} @ rfe context + stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context ldmia sp, {r0 - r12} - ldr lr, [sp, #S_LR] - addeq sp, sp, #S_FRAME_SIZE - 8 @ aligned - addne sp, sp, #S_FRAME_SIZE - 4 @ not aligned + mov sp, lr + ldr lr, [sp], #4 rfeia sp! .endm -- cgit v1.2.3 From 592201a9f154cdd5db59304d1369e94d8b551803 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 26 Mar 2011 19:19:07 +0000 Subject: ARM: Thumb-2: Support Thumb-2 in undefined instruction handler This patch allows undef_hook's to be specified for 32-bit Thumb instructions and also to be used for thumb kernel-side code. 32-bit Thumb instructions are specified in the form: ((first_half << 16 ) | second_half) which matches the layout used by the ARM ARM. ptrace was handling 32-bit Thumb instructions by hooking the first halfword and manually checking the second half. This method would be broken by this patch so it is migrated to make use of the new Thumb-2 support. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/include/asm/ptrace.h | 8 ++++++++ arch/arm/kernel/ptrace.c | 28 +++------------------------- arch/arm/kernel/traps.c | 17 ++++++++++++++++- 3 files changed, 27 insertions(+), 26 deletions(-) diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index 312d10877bd7..d484871698da 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -199,6 +199,14 @@ extern unsigned long profile_pc(struct pt_regs *regs); #define predicate(x) ((x) & 0xf0000000) #define PREDICATE_ALWAYS 0xe0000000 +/* + * True if instr is a 32-bit thumb instruction. This works if instr + * is the first or only half-word of a thumb instruction. It also works + * when instr holds all 32-bits of a wide thumb instruction if stored + * in the form (first_half<<16)|(second_half) + */ +#define is_wide_instruction(instr) ((unsigned)(instr) >= 0xe800) + /* * kprobe-based event tracer support */ diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 97260060bf26..897ade059f58 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -228,34 +228,12 @@ static struct undef_hook thumb_break_hook = { .fn = break_trap, }; -static int thumb2_break_trap(struct pt_regs *regs, unsigned int instr) -{ - unsigned int instr2; - void __user *pc; - - /* Check the second half of the instruction. */ - pc = (void __user *)(instruction_pointer(regs) + 2); - - if (processor_mode(regs) == SVC_MODE) { - instr2 = *(u16 *) pc; - } else { - get_user(instr2, (u16 __user *)pc); - } - - if (instr2 == 0xa000) { - ptrace_break(current, regs); - return 0; - } else { - return 1; - } -} - static struct undef_hook thumb2_break_hook = { - .instr_mask = 0xffff, - .instr_val = 0xf7f0, + .instr_mask = 0xffffffff, + .instr_val = 0xf7f0a000, .cpsr_mask = PSR_T_BIT, .cpsr_val = PSR_T_BIT, - .fn = thumb2_break_trap, + .fn = break_trap, }; static int __init ptrace_break_init(void) diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 6807cb1e76dd..2d3436e9f71f 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -355,9 +355,24 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) pc = (void __user *)instruction_pointer(regs); if (processor_mode(regs) == SVC_MODE) { - instr = *(u32 *) pc; +#ifdef CONFIG_THUMB2_KERNEL + if (thumb_mode(regs)) { + instr = ((u16 *)pc)[0]; + if (is_wide_instruction(instr)) { + instr <<= 16; + instr |= ((u16 *)pc)[1]; + } + } else +#endif + instr = *(u32 *) pc; } else if (thumb_mode(regs)) { get_user(instr, (u16 __user *)pc); + if (is_wide_instruction(instr)) { + unsigned int instr2; + get_user(instr2, (u16 __user *)pc+1); + instr <<= 16; + instr |= instr2; + } } else { get_user(instr, (u32 __user *)pc); } -- cgit v1.2.3 From 691b2ff294a4787f3e54f5bb541570ac74bcb6f4 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 6 Jul 2011 10:49:07 +0100 Subject: ARM: kprobes: Rename kprobes-decode.c to kprobes-arm.c This file contains decoding and emulation functions for the ARM instruction set. As we will later be adding a file for Thumb and a file with common decoding functions, this renaming makes things clearer. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/Makefile | 3 +- arch/arm/kernel/kprobes-arm.c | 1670 ++++++++++++++++++++++++++++++++++++++ arch/arm/kernel/kprobes-decode.c | 1670 -------------------------------------- 3 files changed, 1672 insertions(+), 1671 deletions(-) create mode 100644 arch/arm/kernel/kprobes-arm.c delete mode 100644 arch/arm/kernel/kprobes-decode.c diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index a5b31af5c2b8..914c7a6f1706 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -37,7 +37,8 @@ obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o -obj-$(CONFIG_KPROBES) += kprobes.o kprobes-decode.o +obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_KPROBES) += kprobes-arm.o obj-$(CONFIG_ATAGS_PROC) += atags.o obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o obj-$(CONFIG_ARM_THUMBEE) += thumbee.o diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c new file mode 100644 index 000000000000..15eeff6aea0e --- /dev/null +++ b/arch/arm/kernel/kprobes-arm.c @@ -0,0 +1,1670 @@ +/* + * arch/arm/kernel/kprobes-decode.c + * + * Copyright (C) 2006, 2007 Motorola Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* + * We do not have hardware single-stepping on ARM, This + * effort is further complicated by the ARM not having a + * "next PC" register. Instructions that change the PC + * can't be safely single-stepped in a MP environment, so + * we have a lot of work to do: + * + * In the prepare phase: + * *) If it is an instruction that does anything + * with the CPU mode, we reject it for a kprobe. + * (This is out of laziness rather than need. The + * instructions could be simulated.) + * + * *) Otherwise, decode the instruction rewriting its + * registers to take fixed, ordered registers and + * setting a handler for it to run the instruction. + * + * In the execution phase by an instruction's handler: + * + * *) If the PC is written to by the instruction, the + * instruction must be fully simulated in software. + * + * *) Otherwise, a modified form of the instruction is + * directly executed. Its handler calls the + * instruction in insn[0]. In insn[1] is a + * "mov pc, lr" to return. + * + * Before calling, load up the reordered registers + * from the original instruction's registers. If one + * of the original input registers is the PC, compute + * and adjust the appropriate input register. + * + * After call completes, copy the output registers to + * the original instruction's original registers. + * + * We don't use a real breakpoint instruction since that + * would have us in the kernel go from SVC mode to SVC + * mode losing the link register. Instead we use an + * undefined instruction. To simplify processing, the + * undefined instruction used for kprobes must be reserved + * exclusively for kprobes use. + * + * TODO: ifdef out some instruction decoding based on architecture. + */ + +#include +#include + +#define sign_extend(x, signbit) ((x) | (0 - ((x) & (1 << (signbit))))) + +#define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25) + +#define is_r15(insn, bitpos) (((insn) & (0xf << bitpos)) == (0xf << bitpos)) + +/* + * Test if load/store instructions writeback the address register. + * if P (bit 24) == 0 or W (bit 21) == 1 + */ +#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000) + +#define PSR_fs (PSR_f|PSR_s) + +#define KPROBE_RETURN_INSTRUCTION 0xe1a0f00e /* mov pc, lr */ + +typedef long (insn_0arg_fn_t)(void); +typedef long (insn_1arg_fn_t)(long); +typedef long (insn_2arg_fn_t)(long, long); +typedef long (insn_3arg_fn_t)(long, long, long); +typedef long (insn_4arg_fn_t)(long, long, long, long); +typedef long long (insn_llret_0arg_fn_t)(void); +typedef long long (insn_llret_3arg_fn_t)(long, long, long); +typedef long long (insn_llret_4arg_fn_t)(long, long, long, long); + +union reg_pair { + long long dr; +#ifdef __LITTLE_ENDIAN + struct { long r0, r1; }; +#else + struct { long r1, r0; }; +#endif +}; + +/* + * For STR and STM instructions, an ARM core may choose to use either + * a +8 or a +12 displacement from the current instruction's address. + * Whichever value is chosen for a given core, it must be the same for + * both instructions and may not change. This function measures it. + */ + +static int str_pc_offset; + +static void __init find_str_pc_offset(void) +{ + int addr, scratch, ret; + + __asm__ ( + "sub %[ret], pc, #4 \n\t" + "str pc, %[addr] \n\t" + "ldr %[scr], %[addr] \n\t" + "sub %[ret], %[scr], %[ret] \n\t" + : [ret] "=r" (ret), [scr] "=r" (scratch), [addr] "+m" (addr)); + + str_pc_offset = ret; +} + +/* + * The insnslot_?arg_r[w]flags() functions below are to keep the + * msr -> *fn -> mrs instruction sequences indivisible so that + * the state of the CPSR flags aren't inadvertently modified + * just before or just after the call. + */ + +static inline long __kprobes +insnslot_0arg_rflags(long cpsr, insn_0arg_fn_t *fn) +{ + register long ret asm("r0"); + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret) + : [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + return ret; +} + +static inline long long __kprobes +insnslot_llret_0arg_rflags(long cpsr, insn_llret_0arg_fn_t *fn) +{ + register long ret0 asm("r0"); + register long ret1 asm("r1"); + union reg_pair fnr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret0), "=r" (ret1) + : [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + fnr.r0 = ret0; + fnr.r1 = ret1; + return fnr.dr; +} + +static inline long __kprobes +insnslot_1arg_rflags(long r0, long cpsr, insn_1arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long ret asm("r0"); + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret) + : "0" (rr0), [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + return ret; +} + +static inline long __kprobes +insnslot_2arg_rflags(long r0, long r1, long cpsr, insn_2arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long ret asm("r0"); + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret) + : "0" (rr0), "r" (rr1), + [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + return ret; +} + +static inline long __kprobes +insnslot_3arg_rflags(long r0, long r1, long r2, long cpsr, insn_3arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long rr2 asm("r2") = r2; + register long ret asm("r0"); + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret) + : "0" (rr0), "r" (rr1), "r" (rr2), + [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + return ret; +} + +static inline long long __kprobes +insnslot_llret_3arg_rflags(long r0, long r1, long r2, long cpsr, + insn_llret_3arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long rr2 asm("r2") = r2; + register long ret0 asm("r0"); + register long ret1 asm("r1"); + union reg_pair fnr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret0), "=r" (ret1) + : "0" (rr0), "r" (rr1), "r" (rr2), + [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + fnr.r0 = ret0; + fnr.r1 = ret1; + return fnr.dr; +} + +static inline long __kprobes +insnslot_4arg_rflags(long r0, long r1, long r2, long r3, long cpsr, + insn_4arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long rr2 asm("r2") = r2; + register long rr3 asm("r3") = r3; + register long ret asm("r0"); + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + : "=r" (ret) + : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), + [cpsr] "r" (cpsr), [fn] "r" (fn) + : "lr", "cc" + ); + return ret; +} + +static inline long __kprobes +insnslot_1arg_rwflags(long r0, long *cpsr, insn_1arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long ret asm("r0"); + long oldcpsr = *cpsr; + long newcpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[oldcpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + "mrs %[newcpsr], cpsr \n\t" + : "=r" (ret), [newcpsr] "=r" (newcpsr) + : "0" (rr0), [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) + : "lr", "cc" + ); + *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); + return ret; +} + +static inline long __kprobes +insnslot_2arg_rwflags(long r0, long r1, long *cpsr, insn_2arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long ret asm("r0"); + long oldcpsr = *cpsr; + long newcpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[oldcpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + "mrs %[newcpsr], cpsr \n\t" + : "=r" (ret), [newcpsr] "=r" (newcpsr) + : "0" (rr0), "r" (rr1), [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) + : "lr", "cc" + ); + *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); + return ret; +} + +static inline long __kprobes +insnslot_3arg_rwflags(long r0, long r1, long r2, long *cpsr, + insn_3arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long rr2 asm("r2") = r2; + register long ret asm("r0"); + long oldcpsr = *cpsr; + long newcpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[oldcpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + "mrs %[newcpsr], cpsr \n\t" + : "=r" (ret), [newcpsr] "=r" (newcpsr) + : "0" (rr0), "r" (rr1), "r" (rr2), + [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) + : "lr", "cc" + ); + *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); + return ret; +} + +static inline long __kprobes +insnslot_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr, + insn_4arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long rr2 asm("r2") = r2; + register long rr3 asm("r3") = r3; + register long ret asm("r0"); + long oldcpsr = *cpsr; + long newcpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[oldcpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + "mrs %[newcpsr], cpsr \n\t" + : "=r" (ret), [newcpsr] "=r" (newcpsr) + : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), + [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) + : "lr", "cc" + ); + *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); + return ret; +} + +static inline long long __kprobes +insnslot_llret_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr, + insn_llret_4arg_fn_t *fn) +{ + register long rr0 asm("r0") = r0; + register long rr1 asm("r1") = r1; + register long rr2 asm("r2") = r2; + register long rr3 asm("r3") = r3; + register long ret0 asm("r0"); + register long ret1 asm("r1"); + long oldcpsr = *cpsr; + long newcpsr; + union reg_pair fnr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[oldcpsr] \n\t" + "mov lr, pc \n\t" + "mov pc, %[fn] \n\t" + "mrs %[newcpsr], cpsr \n\t" + : "=r" (ret0), "=r" (ret1), [newcpsr] "=r" (newcpsr) + : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), + [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) + : "lr", "cc" + ); + *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); + fnr.r0 = ret0; + fnr.r1 = ret1; + return fnr.dr; +} + +/* + * To avoid the complications of mimicing single-stepping on a + * processor without a Next-PC or a single-step mode, and to + * avoid having to deal with the side-effects of boosting, we + * simulate or emulate (almost) all ARM instructions. + * + * "Simulation" is where the instruction's behavior is duplicated in + * C code. "Emulation" is where the original instruction is rewritten + * and executed, often by altering its registers. + * + * By having all behavior of the kprobe'd instruction completed before + * returning from the kprobe_handler(), all locks (scheduler and + * interrupt) can safely be released. There is no need for secondary + * breakpoints, no race with MP or preemptable kernels, nor having to + * clean up resources counts at a later time impacting overall system + * performance. By rewriting the instruction, only the minimum registers + * need to be loaded and saved back optimizing performance. + * + * Calling the insnslot_*_rwflags version of a function doesn't hurt + * anything even when the CPSR flags aren't updated by the + * instruction. It's just a little slower in return for saving + * a little space by not having a duplicate function that doesn't + * update the flags. (The same optimization can be said for + * instructions that do or don't perform register writeback) + * Also, instructions can either read the flags, only write the + * flags, or read and write the flags. To save combinations + * rather than for sheer performance, flag functions just assume + * read and write of flags. + */ + +static void __kprobes simulate_bbl(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + long iaddr = (long)p->addr; + int disp = branch_displacement(insn); + + if (insn & (1 << 24)) + regs->ARM_lr = iaddr + 4; + + regs->ARM_pc = iaddr + 8 + disp; +} + +static void __kprobes simulate_blx1(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + long iaddr = (long)p->addr; + int disp = branch_displacement(insn); + + regs->ARM_lr = iaddr + 4; + regs->ARM_pc = iaddr + 8 + disp + ((insn >> 23) & 0x2); + regs->ARM_cpsr |= PSR_T_BIT; +} + +static void __kprobes simulate_blx2bx(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rm = insn & 0xf; + long rmv = regs->uregs[rm]; + + if (insn & (1 << 5)) + regs->ARM_lr = (long)p->addr + 4; + + regs->ARM_pc = rmv & ~0x1; + regs->ARM_cpsr &= ~PSR_T_BIT; + if (rmv & 0x1) + regs->ARM_cpsr |= PSR_T_BIT; +} + +static void __kprobes simulate_mrs(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + unsigned long mask = 0xf8ff03df; /* Mask out execution state */ + regs->uregs[rd] = regs->ARM_cpsr & mask; +} + +static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rn = (insn >> 16) & 0xf; + int lbit = insn & (1 << 20); + int wbit = insn & (1 << 21); + int ubit = insn & (1 << 23); + int pbit = insn & (1 << 24); + long *addr = (long *)regs->uregs[rn]; + int reg_bit_vector; + int reg_count; + + reg_count = 0; + reg_bit_vector = insn & 0xffff; + while (reg_bit_vector) { + reg_bit_vector &= (reg_bit_vector - 1); + ++reg_count; + } + + if (!ubit) + addr -= reg_count; + addr += (!pbit == !ubit); + + reg_bit_vector = insn & 0xffff; + while (reg_bit_vector) { + int reg = __ffs(reg_bit_vector); + reg_bit_vector &= (reg_bit_vector - 1); + if (lbit) + regs->uregs[reg] = *addr++; + else + *addr++ = regs->uregs[reg]; + } + + if (wbit) { + if (!ubit) + addr -= reg_count; + addr -= (!pbit == !ubit); + regs->uregs[rn] = (long)addr; + } +} + +static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_pc = (long)p->addr + str_pc_offset; + simulate_ldm1stm1(p, regs); + regs->ARM_pc = (long)p->addr + 4; +} + +static void __kprobes simulate_mov_ipsp(struct kprobe *p, struct pt_regs *regs) +{ + regs->uregs[12] = regs->uregs[13]; +} + +static void __kprobes emulate_ldrd(struct kprobe *p, struct pt_regs *regs) +{ + insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; /* rm may be invalid, don't care. */ + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + + /* Not following the C calling convention here, so need asm(). */ + __asm__ __volatile__ ( + "ldr r0, %[rn] \n\t" + "ldr r1, %[rm] \n\t" + "msr cpsr_fs, %[cpsr]\n\t" + "mov lr, pc \n\t" + "mov pc, %[i_fn] \n\t" + "str r0, %[rn] \n\t" /* in case of writeback */ + "str r2, %[rd0] \n\t" + "str r3, %[rd1] \n\t" + : [rn] "+m" (rnv), + [rd0] "=m" (regs->uregs[rd]), + [rd1] "=m" (regs->uregs[rd+1]) + : [rm] "m" (rmv), + [cpsr] "r" (regs->ARM_cpsr), + [i_fn] "r" (i_fn) + : "r0", "r1", "r2", "r3", "lr", "cc" + ); + if (is_writeback(insn)) + regs->uregs[rn] = rnv; +} + +static void __kprobes emulate_strd(struct kprobe *p, struct pt_regs *regs) +{ + insn_4arg_fn_t *i_fn = (insn_4arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + /* rm/rmv may be invalid, don't care. */ + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; + long rnv_wb; + + rnv_wb = insnslot_4arg_rflags(rnv, rmv, regs->uregs[rd], + regs->uregs[rd+1], + regs->ARM_cpsr, i_fn); + if (is_writeback(insn)) + regs->uregs[rn] = rnv_wb; +} + +static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs) +{ + insn_llret_3arg_fn_t *i_fn = (insn_llret_3arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; + union reg_pair fnr; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + long rdv; + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; + long cpsr = regs->ARM_cpsr; + + fnr.dr = insnslot_llret_3arg_rflags(rnv, 0, rmv, cpsr, i_fn); + if (rn != 15) + regs->uregs[rn] = fnr.r0; /* Save Rn in case of writeback. */ + rdv = fnr.r1; + + if (rd == 15) { +#if __LINUX_ARM_ARCH__ >= 5 + cpsr &= ~PSR_T_BIT; + if (rdv & 0x1) + cpsr |= PSR_T_BIT; + regs->ARM_cpsr = cpsr; + rdv &= ~0x1; +#else + rdv &= ~0x2; +#endif + } + regs->uregs[rd] = rdv; +} + +static void __kprobes emulate_str(struct kprobe *p, struct pt_regs *regs) +{ + insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long iaddr = (long)p->addr; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + long rdv = (rd == 15) ? iaddr + str_pc_offset : regs->uregs[rd]; + long rnv = (rn == 15) ? iaddr + 8 : regs->uregs[rn]; + long rmv = regs->uregs[rm]; /* rm/rmv may be invalid, don't care. */ + long rnv_wb; + + rnv_wb = insnslot_3arg_rflags(rnv, rdv, rmv, regs->ARM_cpsr, i_fn); + if (rn != 15) + regs->uregs[rn] = rnv_wb; /* Save Rn in case of writeback. */ +} + +static void __kprobes emulate_sat(struct kprobe *p, struct pt_regs *regs) +{ + insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rm = insn & 0xf; + long rmv = regs->uregs[rm]; + + /* Writes Q flag */ + regs->uregs[rd] = insnslot_1arg_rwflags(rmv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes emulate_sel(struct kprobe *p, struct pt_regs *regs) +{ + insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + long rnv = regs->uregs[rn]; + long rmv = regs->uregs[rm]; + + /* Reads GE bits */ + regs->uregs[rd] = insnslot_2arg_rflags(rnv, rmv, regs->ARM_cpsr, i_fn); +} + +static void __kprobes emulate_none(struct kprobe *p, struct pt_regs *regs) +{ + insn_0arg_fn_t *i_fn = (insn_0arg_fn_t *)&p->ainsn.insn[0]; + + insnslot_0arg_rflags(regs->ARM_cpsr, i_fn); +} + +static void __kprobes emulate_nop(struct kprobe *p, struct pt_regs *regs) +{ +} + +static void __kprobes +emulate_rd12_modify(struct kprobe *p, struct pt_regs *regs) +{ + insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + long rdv = regs->uregs[rd]; + + regs->uregs[rd] = insnslot_1arg_rflags(rdv, regs->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_rd12rn0_modify(struct kprobe *p, struct pt_regs *regs) +{ + insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rn = insn & 0xf; + long rdv = regs->uregs[rd]; + long rnv = regs->uregs[rn]; + + regs->uregs[rd] = insnslot_2arg_rflags(rdv, rnv, regs->ARM_cpsr, i_fn); +} + +static void __kprobes emulate_rd12rm0(struct kprobe *p, struct pt_regs *regs) +{ + insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rm = insn & 0xf; + long rmv = regs->uregs[rm]; + + regs->uregs[rd] = insnslot_1arg_rflags(rmv, regs->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_rd12rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + long rnv = regs->uregs[rn]; + long rmv = regs->uregs[rm]; + + regs->uregs[rd] = + insnslot_2arg_rwflags(rnv, rmv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_rd16rn12rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 16) & 0xf; + int rn = (insn >> 12) & 0xf; + int rs = (insn >> 8) & 0xf; + int rm = insn & 0xf; + long rnv = regs->uregs[rn]; + long rsv = regs->uregs[rs]; + long rmv = regs->uregs[rm]; + + regs->uregs[rd] = + insnslot_3arg_rwflags(rnv, rsv, rmv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_rd16rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 16) & 0xf; + int rs = (insn >> 8) & 0xf; + int rm = insn & 0xf; + long rsv = regs->uregs[rs]; + long rmv = regs->uregs[rm]; + + regs->uregs[rd] = + insnslot_2arg_rwflags(rsv, rmv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_rdhi16rdlo12rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_llret_4arg_fn_t *i_fn = (insn_llret_4arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + union reg_pair fnr; + int rdhi = (insn >> 16) & 0xf; + int rdlo = (insn >> 12) & 0xf; + int rs = (insn >> 8) & 0xf; + int rm = insn & 0xf; + long rsv = regs->uregs[rs]; + long rmv = regs->uregs[rm]; + + fnr.dr = insnslot_llret_4arg_rwflags(regs->uregs[rdhi], + regs->uregs[rdlo], rsv, rmv, + ®s->ARM_cpsr, i_fn); + regs->uregs[rdhi] = fnr.r0; + regs->uregs[rdlo] = fnr.r1; +} + +static void __kprobes +emulate_alu_imm_rflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; + + regs->uregs[rd] = insnslot_1arg_rflags(rnv, regs->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_alu_imm_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; + + regs->uregs[rd] = insnslot_1arg_rwflags(rnv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_alu_tests_imm(struct kprobe *p, struct pt_regs *regs) +{ + insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + int rn = (insn >> 16) & 0xf; + long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; + + insnslot_1arg_rwflags(rnv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_alu_rflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; /* rn/rnv/rs/rsv may be */ + int rs = (insn >> 8) & 0xf; /* invalid, don't care. */ + int rm = insn & 0xf; + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; + long rsv = regs->uregs[rs]; + + regs->uregs[rd] = + insnslot_3arg_rflags(rnv, rmv, rsv, regs->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_alu_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; /* rn/rnv/rs/rsv may be */ + int rs = (insn >> 8) & 0xf; /* invalid, don't care. */ + int rm = insn & 0xf; + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; + long rsv = regs->uregs[rs]; + + regs->uregs[rd] = + insnslot_3arg_rwflags(rnv, rmv, rsv, ®s->ARM_cpsr, i_fn); +} + +static void __kprobes +emulate_alu_tests(struct kprobe *p, struct pt_regs *regs) +{ + insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; + kprobe_opcode_t insn = p->opcode; + long ppc = (long)p->addr + 8; + int rn = (insn >> 16) & 0xf; + int rs = (insn >> 8) & 0xf; /* rs/rsv may be invalid, don't care. */ + int rm = insn & 0xf; + long rnv = (rn == 15) ? ppc : regs->uregs[rn]; + long rmv = (rm == 15) ? ppc : regs->uregs[rm]; + long rsv = regs->uregs[rs]; + + insnslot_3arg_rwflags(rnv, rmv, rsv, ®s->ARM_cpsr, i_fn); +} + +static enum kprobe_insn __kprobes +prep_emulate_ldr_str(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + int not_imm = (insn & (1 << 26)) ? (insn & (1 << 25)) + : (~insn & (1 << 22)); + + if (is_writeback(insn) && is_r15(insn, 16)) + return INSN_REJECTED; /* Writeback to PC */ + + insn &= 0xfff00fff; + insn |= 0x00001000; /* Rn = r0, Rd = r1 */ + if (not_imm) { + insn &= ~0xf; + insn |= 2; /* Rm = r2 */ + } + asi->insn[0] = insn; + asi->insn_handler = (insn & (1 << 20)) ? emulate_ldr : emulate_str; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rd12_modify(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + + insn &= 0xffff0fff; /* Rd = r0 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rd12_modify; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rd12rn0_modify(kprobe_opcode_t insn, + struct arch_specific_insn *asi) +{ + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + + insn &= 0xffff0ff0; /* Rd = r0 */ + insn |= 0x00000001; /* Rn = r1 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rd12rn0_modify; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rd12rm0(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + + insn &= 0xffff0ff0; /* Rd = r0, Rm = r0 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rd12rm0; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rd12rn16rm0_wflags(kprobe_opcode_t insn, + struct arch_specific_insn *asi) +{ + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + + insn &= 0xfff00ff0; /* Rd = r0, Rn = r0 */ + insn |= 0x00000001; /* Rm = r1 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rd12rn16rm0_rwflags; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rd16rs8rm0_wflags(kprobe_opcode_t insn, + struct arch_specific_insn *asi) +{ + if (is_r15(insn, 16)) + return INSN_REJECTED; /* Rd is PC */ + + insn &= 0xfff0f0f0; /* Rd = r0, Rs = r0 */ + insn |= 0x00000001; /* Rm = r1 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rd16rs8rm0_rwflags; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rd16rn12rs8rm0_wflags(kprobe_opcode_t insn, + struct arch_specific_insn *asi) +{ + if (is_r15(insn, 16)) + return INSN_REJECTED; /* Rd is PC */ + + insn &= 0xfff000f0; /* Rd = r0, Rn = r0 */ + insn |= 0x00000102; /* Rs = r1, Rm = r2 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rd16rn12rs8rm0_rwflags; + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn, + struct arch_specific_insn *asi) +{ + if (is_r15(insn, 16) || is_r15(insn, 12)) + return INSN_REJECTED; /* RdHi or RdLo is PC */ + + insn &= 0xfff000f0; /* RdHi = r0, RdLo = r1 */ + insn |= 0x00001203; /* Rs = r2, Rm = r3 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_rdhi16rdlo12rs8rm0_rwflags; + return INSN_GOOD; +} + +/* + * For the instruction masking and comparisons in all the "space_*" + * functions below, Do _not_ rearrange the order of tests unless + * you're very, very sure of what you are doing. For the sake of + * efficiency, the masks for some tests sometimes assume other test + * have been done prior to them so the number of patterns to test + * for an instruction set can be as broad as possible to reduce the + * number of tests needed. + */ + +static enum kprobe_insn __kprobes +space_1111(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* memory hint : 1111 0100 x001 xxxx xxxx xxxx xxxx xxxx : */ + /* PLDI : 1111 0100 x101 xxxx xxxx xxxx xxxx xxxx : */ + /* PLDW : 1111 0101 x001 xxxx xxxx xxxx xxxx xxxx : */ + /* PLD : 1111 0101 x101 xxxx xxxx xxxx xxxx xxxx : */ + if ((insn & 0xfe300000) == 0xf4100000) { + asi->insn_handler = emulate_nop; + return INSN_GOOD_NO_SLOT; + } + + /* BLX(1) : 1111 101x xxxx xxxx xxxx xxxx xxxx xxxx : */ + if ((insn & 0xfe000000) == 0xfa000000) { + asi->insn_handler = simulate_blx1; + return INSN_GOOD_NO_SLOT; + } + + /* CPS : 1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */ + /* SETEND: 1111 0001 0000 0001 xxxx xxxx 0000 xxxx */ + + /* SRS : 1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */ + /* RFE : 1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ + + /* Coprocessor instructions... */ + /* MCRR2 : 1111 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */ + /* MRRC2 : 1111 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */ + /* LDC2 : 1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ + /* STC2 : 1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ + /* CDP2 : 1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ + /* MCR2 : 1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ + /* MRC2 : 1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ + + return INSN_REJECTED; +} + +static enum kprobe_insn __kprobes +space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* cccc 0001 0xx0 xxxx xxxx xxxx xxxx xxx0 xxxx */ + if ((insn & 0x0f900010) == 0x01000000) { + + /* MRS cpsr : cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */ + if ((insn & 0x0ff000f0) == 0x01000000) { + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + asi->insn_handler = simulate_mrs; + return INSN_GOOD_NO_SLOT; + } + + /* SMLALxy : cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */ + if ((insn & 0x0ff00090) == 0x01400080) + return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, + asi); + + /* SMULWy : cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */ + /* SMULxy : cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */ + if ((insn & 0x0ff000b0) == 0x012000a0 || + (insn & 0x0ff00090) == 0x01600080) + return prep_emulate_rd16rs8rm0_wflags(insn, asi); + + /* SMLAxy : cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx : Q */ + /* SMLAWy : cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx : Q */ + if ((insn & 0x0ff00090) == 0x01000080 || + (insn & 0x0ff000b0) == 0x01200080) + return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); + + /* BXJ : cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */ + /* MSR : cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */ + /* MRS spsr : cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */ + + /* Other instruction encodings aren't yet defined */ + return INSN_REJECTED; + } + + /* cccc 0001 0xx0 xxxx xxxx xxxx xxxx 0xx1 xxxx */ + else if ((insn & 0x0f900090) == 0x01000010) { + + /* BLX(2) : cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */ + /* BX : cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */ + if ((insn & 0x0ff000d0) == 0x01200010) { + if ((insn & 0x0ff000ff) == 0x0120003f) + return INSN_REJECTED; /* BLX pc */ + asi->insn_handler = simulate_blx2bx; + return INSN_GOOD_NO_SLOT; + } + + /* CLZ : cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */ + if ((insn & 0x0ff000f0) == 0x01600010) + return prep_emulate_rd12rm0(insn, asi); + + /* QADD : cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx :Q */ + /* QSUB : cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx :Q */ + /* QDADD : cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx :Q */ + /* QDSUB : cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx :Q */ + if ((insn & 0x0f9000f0) == 0x01000050) + return prep_emulate_rd12rn16rm0_wflags(insn, asi); + + /* BKPT : 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */ + /* SMC : cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */ + + /* Other instruction encodings aren't yet defined */ + return INSN_REJECTED; + } + + /* cccc 0000 xxxx xxxx xxxx xxxx xxxx 1001 xxxx */ + else if ((insn & 0x0f0000f0) == 0x00000090) { + + /* MUL : cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx : */ + /* MULS : cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx :cc */ + /* MLA : cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx : */ + /* MLAS : cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx :cc */ + /* UMAAL : cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx : */ + /* undef : cccc 0000 0101 xxxx xxxx xxxx 1001 xxxx : */ + /* MLS : cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx : */ + /* undef : cccc 0000 0111 xxxx xxxx xxxx 1001 xxxx : */ + /* UMULL : cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx : */ + /* UMULLS : cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx :cc */ + /* UMLAL : cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx : */ + /* UMLALS : cccc 0000 1011 xxxx xxxx xxxx 1001 xxxx :cc */ + /* SMULL : cccc 0000 1100 xxxx xxxx xxxx 1001 xxxx : */ + /* SMULLS : cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx :cc */ + /* SMLAL : cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx : */ + /* SMLALS : cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx :cc */ + if ((insn & 0x00d00000) == 0x00500000) + return INSN_REJECTED; + else if ((insn & 0x00e00000) == 0x00000000) + return prep_emulate_rd16rs8rm0_wflags(insn, asi); + else if ((insn & 0x00a00000) == 0x00200000) + return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); + else + return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, + asi); + } + + /* cccc 000x xxxx xxxx xxxx xxxx xxxx 1xx1 xxxx */ + else if ((insn & 0x0e000090) == 0x00000090) { + + /* SWP : cccc 0001 0000 xxxx xxxx xxxx 1001 xxxx */ + /* SWPB : cccc 0001 0100 xxxx xxxx xxxx 1001 xxxx */ + /* ??? : cccc 0001 0x01 xxxx xxxx xxxx 1001 xxxx */ + /* ??? : cccc 0001 0x10 xxxx xxxx xxxx 1001 xxxx */ + /* ??? : cccc 0001 0x11 xxxx xxxx xxxx 1001 xxxx */ + /* STREX : cccc 0001 1000 xxxx xxxx xxxx 1001 xxxx */ + /* LDREX : cccc 0001 1001 xxxx xxxx xxxx 1001 xxxx */ + /* STREXD: cccc 0001 1010 xxxx xxxx xxxx 1001 xxxx */ + /* LDREXD: cccc 0001 1011 xxxx xxxx xxxx 1001 xxxx */ + /* STREXB: cccc 0001 1100 xxxx xxxx xxxx 1001 xxxx */ + /* LDREXB: cccc 0001 1101 xxxx xxxx xxxx 1001 xxxx */ + /* STREXH: cccc 0001 1110 xxxx xxxx xxxx 1001 xxxx */ + /* LDREXH: cccc 0001 1111 xxxx xxxx xxxx 1001 xxxx */ + + /* LDRD : cccc 000x xxx0 xxxx xxxx xxxx 1101 xxxx */ + /* STRD : cccc 000x xxx0 xxxx xxxx xxxx 1111 xxxx */ + /* LDRH : cccc 000x xxx1 xxxx xxxx xxxx 1011 xxxx */ + /* STRH : cccc 000x xxx0 xxxx xxxx xxxx 1011 xxxx */ + /* LDRSB : cccc 000x xxx1 xxxx xxxx xxxx 1101 xxxx */ + /* LDRSH : cccc 000x xxx1 xxxx xxxx xxxx 1111 xxxx */ + if ((insn & 0x0f0000f0) == 0x01000090) { + if ((insn & 0x0fb000f0) == 0x01000090) { + /* SWP/SWPB */ + return prep_emulate_rd12rn16rm0_wflags(insn, + asi); + } else { + /* STREX/LDREX variants and unallocaed space */ + return INSN_REJECTED; + } + + } else if ((insn & 0x0e1000d0) == 0x00000d0) { + /* STRD/LDRD */ + if ((insn & 0x0000e000) == 0x0000e000) + return INSN_REJECTED; /* Rd is LR or PC */ + if (is_writeback(insn) && is_r15(insn, 16)) + return INSN_REJECTED; /* Writeback to PC */ + + insn &= 0xfff00fff; + insn |= 0x00002000; /* Rn = r0, Rd = r2 */ + if (!(insn & (1 << 22))) { + /* Register index */ + insn &= ~0xf; + insn |= 1; /* Rm = r1 */ + } + asi->insn[0] = insn; + asi->insn_handler = + (insn & (1 << 5)) ? emulate_strd : emulate_ldrd; + return INSN_GOOD; + } + + /* LDRH/STRH/LDRSB/LDRSH */ + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + return prep_emulate_ldr_str(insn, asi); + } + + /* cccc 000x xxxx xxxx xxxx xxxx xxxx xxxx xxxx */ + + /* + * ALU op with S bit and Rd == 15 : + * cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx + */ + if ((insn & 0x0e10f000) == 0x0010f000) + return INSN_REJECTED; + + /* + * "mov ip, sp" is the most common kprobe'd instruction by far. + * Check and optimize for it explicitly. + */ + if (insn == 0xe1a0c00d) { + asi->insn_handler = simulate_mov_ipsp; + return INSN_GOOD_NO_SLOT; + } + + /* + * Data processing: Immediate-shift / Register-shift + * ALU op : cccc 000x xxxx xxxx xxxx xxxx xxxx xxxx + * CPY : cccc 0001 1010 xxxx xxxx 0000 0000 xxxx + * MOV : cccc 0001 101x xxxx xxxx xxxx xxxx xxxx + * *S (bit 20) updates condition codes + * ADC/SBC/RSC reads the C flag + */ + insn &= 0xfff00ff0; /* Rn = r0, Rd = r0 */ + insn |= 0x00000001; /* Rm = r1 */ + if (insn & 0x010) { + insn &= 0xfffff0ff; /* register shift */ + insn |= 0x00000200; /* Rs = r2 */ + } + asi->insn[0] = insn; + + if ((insn & 0x0f900000) == 0x01100000) { + /* + * TST : cccc 0001 0001 xxxx xxxx xxxx xxxx xxxx + * TEQ : cccc 0001 0011 xxxx xxxx xxxx xxxx xxxx + * CMP : cccc 0001 0101 xxxx xxxx xxxx xxxx xxxx + * CMN : cccc 0001 0111 xxxx xxxx xxxx xxxx xxxx + */ + asi->insn_handler = emulate_alu_tests; + } else { + /* ALU ops which write to Rd */ + asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ + emulate_alu_rwflags : emulate_alu_rflags; + } + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* MOVW : cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */ + /* MOVT : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */ + if ((insn & 0x0fb00000) == 0x03000000) + return prep_emulate_rd12_modify(insn, asi); + + /* hints : cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */ + if ((insn & 0x0fff0000) == 0x03200000) { + unsigned op2 = insn & 0x000000ff; + if (op2 == 0x01 || op2 == 0x04) { + /* YIELD : cccc 0011 0010 0000 xxxx xxxx 0000 0001 */ + /* SEV : cccc 0011 0010 0000 xxxx xxxx 0000 0100 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_none; + return INSN_GOOD; + } else if (op2 <= 0x03) { + /* NOP : cccc 0011 0010 0000 xxxx xxxx 0000 0000 */ + /* WFE : cccc 0011 0010 0000 xxxx xxxx 0000 0010 */ + /* WFI : cccc 0011 0010 0000 xxxx xxxx 0000 0011 */ + /* + * We make WFE and WFI true NOPs to avoid stalls due + * to missing events whilst processing the probe. + */ + asi->insn_handler = emulate_nop; + return INSN_GOOD_NO_SLOT; + } + /* For DBG and unallocated hints it's safest to reject them */ + return INSN_REJECTED; + } + + /* + * MSR : cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx + * ALU op with S bit and Rd == 15 : + * cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx + */ + if ((insn & 0x0fb00000) == 0x03200000 || /* MSR */ + (insn & 0x0e10f000) == 0x0210f000) /* ALU s-bit, R15 */ + return INSN_REJECTED; + + /* + * Data processing: 32-bit Immediate + * ALU op : cccc 001x xxxx xxxx xxxx xxxx xxxx xxxx + * MOV : cccc 0011 101x xxxx xxxx xxxx xxxx xxxx + * *S (bit 20) updates condition codes + * ADC/SBC/RSC reads the C flag + */ + insn &= 0xfff00fff; /* Rn = r0 and Rd = r0 */ + asi->insn[0] = insn; + + if ((insn & 0x0f900000) == 0x03100000) { + /* + * TST : cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx + * TEQ : cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx + * CMP : cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx + * CMN : cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx + */ + asi->insn_handler = emulate_alu_tests_imm; + } else { + /* ALU ops which write to Rd */ + asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ + emulate_alu_imm_rwflags : emulate_alu_imm_rflags; + } + return INSN_GOOD; +} + +static enum kprobe_insn __kprobes +space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* SEL : cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx GE: !!! */ + if ((insn & 0x0ff000f0) == 0x068000b0) { + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + insn &= 0xfff00ff0; /* Rd = r0, Rn = r0 */ + insn |= 0x00000001; /* Rm = r1 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_sel; + return INSN_GOOD; + } + + /* SSAT : cccc 0110 101x xxxx xxxx xxxx xx01 xxxx :Q */ + /* USAT : cccc 0110 111x xxxx xxxx xxxx xx01 xxxx :Q */ + /* SSAT16 : cccc 0110 1010 xxxx xxxx xxxx 0011 xxxx :Q */ + /* USAT16 : cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx :Q */ + if ((insn & 0x0fa00030) == 0x06a00010 || + (insn & 0x0fb000f0) == 0x06a00030) { + if (is_r15(insn, 12)) + return INSN_REJECTED; /* Rd is PC */ + insn &= 0xffff0ff0; /* Rd = r0, Rm = r0 */ + asi->insn[0] = insn; + asi->insn_handler = emulate_sat; + return INSN_GOOD; + } + + /* REV : cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */ + /* REV16 : cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */ + /* RBIT : cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */ + /* REVSH : cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */ + if ((insn & 0x0ff00070) == 0x06b00030 || + (insn & 0x0ff00070) == 0x06f00030) + return prep_emulate_rd12rm0(insn, asi); + + /* ??? : cccc 0110 0000 xxxx xxxx xxxx xxx1 xxxx : */ + /* SADD16 : cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx :GE */ + /* SADDSUBX : cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx :GE */ + /* SSUBADDX : cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx :GE */ + /* SSUB16 : cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx :GE */ + /* SADD8 : cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx :GE */ + /* ??? : cccc 0110 0001 xxxx xxxx xxxx 1011 xxxx : */ + /* ??? : cccc 0110 0001 xxxx xxxx xxxx 1101 xxxx : */ + /* SSUB8 : cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx :GE */ + /* QADD16 : cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx : */ + /* QADDSUBX : cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx : */ + /* QSUBADDX : cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx : */ + /* QSUB16 : cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx : */ + /* QADD8 : cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx : */ + /* ??? : cccc 0110 0010 xxxx xxxx xxxx 1011 xxxx : */ + /* ??? : cccc 0110 0010 xxxx xxxx xxxx 1101 xxxx : */ + /* QSUB8 : cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx : */ + /* SHADD16 : cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx : */ + /* SHADDSUBX : cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx : */ + /* SHSUBADDX : cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx : */ + /* SHSUB16 : cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx : */ + /* SHADD8 : cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx : */ + /* ??? : cccc 0110 0011 xxxx xxxx xxxx 1011 xxxx : */ + /* ??? : cccc 0110 0011 xxxx xxxx xxxx 1101 xxxx : */ + /* SHSUB8 : cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx : */ + /* ??? : cccc 0110 0100 xxxx xxxx xxxx xxx1 xxxx : */ + /* UADD16 : cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx :GE */ + /* UADDSUBX : cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx :GE */ + /* USUBADDX : cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx :GE */ + /* USUB16 : cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx :GE */ + /* UADD8 : cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx :GE */ + /* ??? : cccc 0110 0101 xxxx xxxx xxxx 1011 xxxx : */ + /* ??? : cccc 0110 0101 xxxx xxxx xxxx 1101 xxxx : */ + /* USUB8 : cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx :GE */ + /* UQADD16 : cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx : */ + /* UQADDSUBX : cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx : */ + /* UQSUBADDX : cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx : */ + /* UQSUB16 : cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx : */ + /* UQADD8 : cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx : */ + /* ??? : cccc 0110 0110 xxxx xxxx xxxx 1011 xxxx : */ + /* ??? : cccc 0110 0110 xxxx xxxx xxxx 1101 xxxx : */ + /* UQSUB8 : cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx : */ + /* UHADD16 : cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx : */ + /* UHADDSUBX : cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx : */ + /* UHSUBADDX : cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx : */ + /* UHSUB16 : cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx : */ + /* UHADD8 : cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx : */ + /* ??? : cccc 0110 0111 xxxx xxxx xxxx 1011 xxxx : */ + /* ??? : cccc 0110 0111 xxxx xxxx xxxx 1101 xxxx : */ + /* UHSUB8 : cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx : */ + if ((insn & 0x0f800010) == 0x06000010) { + if ((insn & 0x00300000) == 0x00000000 || + (insn & 0x000000e0) == 0x000000a0 || + (insn & 0x000000e0) == 0x000000c0) + return INSN_REJECTED; /* Unallocated space */ + return prep_emulate_rd12rn16rm0_wflags(insn, asi); + } + + /* PKHBT : cccc 0110 1000 xxxx xxxx xxxx x001 xxxx : */ + /* PKHTB : cccc 0110 1000 xxxx xxxx xxxx x101 xxxx : */ + if ((insn & 0x0ff00030) == 0x06800010) + return prep_emulate_rd12rn16rm0_wflags(insn, asi); + + /* SXTAB16 : cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx : */ + /* SXTB16 : cccc 0110 1000 1111 xxxx xxxx 0111 xxxx : */ + /* ??? : cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx : */ + /* SXTAB : cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx : */ + /* SXTB : cccc 0110 1010 1111 xxxx xxxx 0111 xxxx : */ + /* SXTAH : cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx : */ + /* SXTH : cccc 0110 1011 1111 xxxx xxxx 0111 xxxx : */ + /* UXTAB16 : cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx : */ + /* UXTB16 : cccc 0110 1100 1111 xxxx xxxx 0111 xxxx : */ + /* ??? : cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx : */ + /* UXTAB : cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx : */ + /* UXTB : cccc 0110 1110 1111 xxxx xxxx 0111 xxxx : */ + /* UXTAH : cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx : */ + /* UXTH : cccc 0110 1111 1111 xxxx xxxx 0111 xxxx : */ + if ((insn & 0x0f8000f0) == 0x06800070) { + if ((insn & 0x00300000) == 0x00100000) + return INSN_REJECTED; /* Unallocated space */ + + if ((insn & 0x000f0000) == 0x000f0000) + return prep_emulate_rd12rm0(insn, asi); + else + return prep_emulate_rd12rn16rm0_wflags(insn, asi); + } + + /* Other instruction encodings aren't yet defined */ + return INSN_REJECTED; +} + +static enum kprobe_insn __kprobes +space_cccc_0111__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* Undef : cccc 0111 1111 xxxx xxxx xxxx 1111 xxxx */ + if ((insn & 0x0ff000f0) == 0x03f000f0) + return INSN_REJECTED; + + /* SMLALD : cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */ + /* SMLSLD : cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */ + if ((insn & 0x0ff00090) == 0x07400010) + return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, asi); + + /* SMLAD : cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx :Q */ + /* SMUAD : cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx :Q */ + /* SMLSD : cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx :Q */ + /* SMUSD : cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx : */ + /* SMMLA : cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx : */ + /* SMMUL : cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx : */ + /* USADA8 : cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx : */ + /* USAD8 : cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx : */ + if ((insn & 0x0ff00090) == 0x07000010 || + (insn & 0x0ff000d0) == 0x07500010 || + (insn & 0x0ff000f0) == 0x07800010) { + + if ((insn & 0x0000f000) == 0x0000f000) + return prep_emulate_rd16rs8rm0_wflags(insn, asi); + else + return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); + } + + /* SMMLS : cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx : */ + if ((insn & 0x0ff000d0) == 0x075000d0) + return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); + + /* SBFX : cccc 0111 101x xxxx xxxx xxxx x101 xxxx : */ + /* UBFX : cccc 0111 111x xxxx xxxx xxxx x101 xxxx : */ + if ((insn & 0x0fa00070) == 0x07a00050) + return prep_emulate_rd12rm0(insn, asi); + + /* BFI : cccc 0111 110x xxxx xxxx xxxx x001 xxxx : */ + /* BFC : cccc 0111 110x xxxx xxxx xxxx x001 1111 : */ + if ((insn & 0x0fe00070) == 0x07c00010) { + + if ((insn & 0x0000000f) == 0x0000000f) + return prep_emulate_rd12_modify(insn, asi); + else + return prep_emulate_rd12rn0_modify(insn, asi); + } + + return INSN_REJECTED; +} + +static enum kprobe_insn __kprobes +space_cccc_01xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* LDR : cccc 01xx x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* LDRB : cccc 01xx x1x1 xxxx xxxx xxxx xxxx xxxx */ + /* LDRBT : cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */ + /* LDRT : cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */ + /* STR : cccc 01xx x0x0 xxxx xxxx xxxx xxxx xxxx */ + /* STRB : cccc 01xx x1x0 xxxx xxxx xxxx xxxx xxxx */ + /* STRBT : cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */ + /* STRT : cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */ + + if ((insn & 0x00500000) == 0x00500000 && is_r15(insn, 12)) + return INSN_REJECTED; /* LDRB into PC */ + + return prep_emulate_ldr_str(insn, asi); +} + +static enum kprobe_insn __kprobes +space_cccc_100x(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* LDM(2) : cccc 100x x101 xxxx 0xxx xxxx xxxx xxxx */ + /* LDM(3) : cccc 100x x1x1 xxxx 1xxx xxxx xxxx xxxx */ + if ((insn & 0x0e708000) == 0x85000000 || + (insn & 0x0e508000) == 0x85010000) + return INSN_REJECTED; + + /* LDM(1) : cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* STM(1) : cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */ + asi->insn_handler = ((insn & 0x108000) == 0x008000) ? /* STM & R15 */ + simulate_stm1_pc : simulate_ldm1stm1; + return INSN_GOOD_NO_SLOT; +} + +static enum kprobe_insn __kprobes +space_cccc_101x(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* B : cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */ + /* BL : cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */ + asi->insn_handler = simulate_bbl; + return INSN_GOOD_NO_SLOT; +} + +static enum kprobe_insn __kprobes +space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* Coprocessor instructions... */ + /* MCRR : cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */ + /* MRRC : cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */ + /* LDC : cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ + /* STC : cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ + /* CDP : cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ + /* MCR : cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ + /* MRC : cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ + + /* SVC : cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */ + + return INSN_REJECTED; +} + +static unsigned long __kprobes __check_eq(unsigned long cpsr) +{ + return cpsr & PSR_Z_BIT; +} + +static unsigned long __kprobes __check_ne(unsigned long cpsr) +{ + return (~cpsr) & PSR_Z_BIT; +} + +static unsigned long __kprobes __check_cs(unsigned long cpsr) +{ + return cpsr & PSR_C_BIT; +} + +static unsigned long __kprobes __check_cc(unsigned long cpsr) +{ + return (~cpsr) & PSR_C_BIT; +} + +static unsigned long __kprobes __check_mi(unsigned long cpsr) +{ + return cpsr & PSR_N_BIT; +} + +static unsigned long __kprobes __check_pl(unsigned long cpsr) +{ + return (~cpsr) & PSR_N_BIT; +} + +static unsigned long __kprobes __check_vs(unsigned long cpsr) +{ + return cpsr & PSR_V_BIT; +} + +static unsigned long __kprobes __check_vc(unsigned long cpsr) +{ + return (~cpsr) & PSR_V_BIT; +} + +static unsigned long __kprobes __check_hi(unsigned long cpsr) +{ + cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return cpsr & PSR_C_BIT; +} + +static unsigned long __kprobes __check_ls(unsigned long cpsr) +{ + cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (~cpsr) & PSR_C_BIT; +} + +static unsigned long __kprobes __check_ge(unsigned long cpsr) +{ + cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (~cpsr) & PSR_N_BIT; +} + +static unsigned long __kprobes __check_lt(unsigned long cpsr) +{ + cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return cpsr & PSR_N_BIT; +} + +static unsigned long __kprobes __check_gt(unsigned long cpsr) +{ + unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ + return (~temp) & PSR_N_BIT; +} + +static unsigned long __kprobes __check_le(unsigned long cpsr) +{ + unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ + return temp & PSR_N_BIT; +} + +static unsigned long __kprobes __check_al(unsigned long cpsr) +{ + return true; +} + +static kprobe_check_cc * const condition_checks[16] = { + &__check_eq, &__check_ne, &__check_cs, &__check_cc, + &__check_mi, &__check_pl, &__check_vs, &__check_vc, + &__check_hi, &__check_ls, &__check_ge, &__check_lt, + &__check_gt, &__check_le, &__check_al, &__check_al +}; + +/* Return: + * INSN_REJECTED If instruction is one not allowed to kprobe, + * INSN_GOOD If instruction is supported and uses instruction slot, + * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. + * + * For instructions we don't want to kprobe (INSN_REJECTED return result): + * These are generally ones that modify the processor state making + * them "hard" to simulate such as switches processor modes or + * make accesses in alternate modes. Any of these could be simulated + * if the work was put into it, but low return considering they + * should also be very rare. + */ +enum kprobe_insn __kprobes +arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + asi->insn_check_cc = condition_checks[insn>>28]; + asi->insn[1] = KPROBE_RETURN_INSTRUCTION; + + if ((insn & 0xf0000000) == 0xf0000000) + + return space_1111(insn, asi); + + else if ((insn & 0x0e000000) == 0x00000000) + + return space_cccc_000x(insn, asi); + + else if ((insn & 0x0e000000) == 0x02000000) + + return space_cccc_001x(insn, asi); + + else if ((insn & 0x0f000010) == 0x06000010) + + return space_cccc_0110__1(insn, asi); + + else if ((insn & 0x0f000010) == 0x07000010) + + return space_cccc_0111__1(insn, asi); + + else if ((insn & 0x0c000000) == 0x04000000) + + return space_cccc_01xx(insn, asi); + + else if ((insn & 0x0e000000) == 0x08000000) + + return space_cccc_100x(insn, asi); + + else if ((insn & 0x0e000000) == 0x0a000000) + + return space_cccc_101x(insn, asi); + + return space_cccc_11xx(insn, asi); +} + +void __init arm_kprobe_decode_init(void) +{ + find_str_pc_offset(); +} diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c deleted file mode 100644 index 15eeff6aea0e..000000000000 --- a/arch/arm/kernel/kprobes-decode.c +++ /dev/null @@ -1,1670 +0,0 @@ -/* - * arch/arm/kernel/kprobes-decode.c - * - * Copyright (C) 2006, 2007 Motorola Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -/* - * We do not have hardware single-stepping on ARM, This - * effort is further complicated by the ARM not having a - * "next PC" register. Instructions that change the PC - * can't be safely single-stepped in a MP environment, so - * we have a lot of work to do: - * - * In the prepare phase: - * *) If it is an instruction that does anything - * with the CPU mode, we reject it for a kprobe. - * (This is out of laziness rather than need. The - * instructions could be simulated.) - * - * *) Otherwise, decode the instruction rewriting its - * registers to take fixed, ordered registers and - * setting a handler for it to run the instruction. - * - * In the execution phase by an instruction's handler: - * - * *) If the PC is written to by the instruction, the - * instruction must be fully simulated in software. - * - * *) Otherwise, a modified form of the instruction is - * directly executed. Its handler calls the - * instruction in insn[0]. In insn[1] is a - * "mov pc, lr" to return. - * - * Before calling, load up the reordered registers - * from the original instruction's registers. If one - * of the original input registers is the PC, compute - * and adjust the appropriate input register. - * - * After call completes, copy the output registers to - * the original instruction's original registers. - * - * We don't use a real breakpoint instruction since that - * would have us in the kernel go from SVC mode to SVC - * mode losing the link register. Instead we use an - * undefined instruction. To simplify processing, the - * undefined instruction used for kprobes must be reserved - * exclusively for kprobes use. - * - * TODO: ifdef out some instruction decoding based on architecture. - */ - -#include -#include - -#define sign_extend(x, signbit) ((x) | (0 - ((x) & (1 << (signbit))))) - -#define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25) - -#define is_r15(insn, bitpos) (((insn) & (0xf << bitpos)) == (0xf << bitpos)) - -/* - * Test if load/store instructions writeback the address register. - * if P (bit 24) == 0 or W (bit 21) == 1 - */ -#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000) - -#define PSR_fs (PSR_f|PSR_s) - -#define KPROBE_RETURN_INSTRUCTION 0xe1a0f00e /* mov pc, lr */ - -typedef long (insn_0arg_fn_t)(void); -typedef long (insn_1arg_fn_t)(long); -typedef long (insn_2arg_fn_t)(long, long); -typedef long (insn_3arg_fn_t)(long, long, long); -typedef long (insn_4arg_fn_t)(long, long, long, long); -typedef long long (insn_llret_0arg_fn_t)(void); -typedef long long (insn_llret_3arg_fn_t)(long, long, long); -typedef long long (insn_llret_4arg_fn_t)(long, long, long, long); - -union reg_pair { - long long dr; -#ifdef __LITTLE_ENDIAN - struct { long r0, r1; }; -#else - struct { long r1, r0; }; -#endif -}; - -/* - * For STR and STM instructions, an ARM core may choose to use either - * a +8 or a +12 displacement from the current instruction's address. - * Whichever value is chosen for a given core, it must be the same for - * both instructions and may not change. This function measures it. - */ - -static int str_pc_offset; - -static void __init find_str_pc_offset(void) -{ - int addr, scratch, ret; - - __asm__ ( - "sub %[ret], pc, #4 \n\t" - "str pc, %[addr] \n\t" - "ldr %[scr], %[addr] \n\t" - "sub %[ret], %[scr], %[ret] \n\t" - : [ret] "=r" (ret), [scr] "=r" (scratch), [addr] "+m" (addr)); - - str_pc_offset = ret; -} - -/* - * The insnslot_?arg_r[w]flags() functions below are to keep the - * msr -> *fn -> mrs instruction sequences indivisible so that - * the state of the CPSR flags aren't inadvertently modified - * just before or just after the call. - */ - -static inline long __kprobes -insnslot_0arg_rflags(long cpsr, insn_0arg_fn_t *fn) -{ - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long long __kprobes -insnslot_llret_0arg_rflags(long cpsr, insn_llret_0arg_fn_t *fn) -{ - register long ret0 asm("r0"); - register long ret1 asm("r1"); - union reg_pair fnr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret0), "=r" (ret1) - : [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - fnr.r0 = ret0; - fnr.r1 = ret1; - return fnr.dr; -} - -static inline long __kprobes -insnslot_1arg_rflags(long r0, long cpsr, insn_1arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long __kprobes -insnslot_2arg_rflags(long r0, long r1, long cpsr, insn_2arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), "r" (rr1), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long __kprobes -insnslot_3arg_rflags(long r0, long r1, long r2, long cpsr, insn_3arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), "r" (rr1), "r" (rr2), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long long __kprobes -insnslot_llret_3arg_rflags(long r0, long r1, long r2, long cpsr, - insn_llret_3arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long ret0 asm("r0"); - register long ret1 asm("r1"); - union reg_pair fnr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret0), "=r" (ret1) - : "0" (rr0), "r" (rr1), "r" (rr2), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - fnr.r0 = ret0; - fnr.r1 = ret1; - return fnr.dr; -} - -static inline long __kprobes -insnslot_4arg_rflags(long r0, long r1, long r2, long r3, long cpsr, - insn_4arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long rr3 asm("r3") = r3; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long __kprobes -insnslot_1arg_rwflags(long r0, long *cpsr, insn_1arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long __kprobes -insnslot_2arg_rwflags(long r0, long r1, long *cpsr, insn_2arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long __kprobes -insnslot_3arg_rwflags(long r0, long r1, long r2, long *cpsr, - insn_3arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), "r" (rr2), - [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long __kprobes -insnslot_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr, - insn_4arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long rr3 asm("r3") = r3; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), - [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long long __kprobes -insnslot_llret_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr, - insn_llret_4arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long rr3 asm("r3") = r3; - register long ret0 asm("r0"); - register long ret1 asm("r1"); - long oldcpsr = *cpsr; - long newcpsr; - union reg_pair fnr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret0), "=r" (ret1), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), - [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - fnr.r0 = ret0; - fnr.r1 = ret1; - return fnr.dr; -} - -/* - * To avoid the complications of mimicing single-stepping on a - * processor without a Next-PC or a single-step mode, and to - * avoid having to deal with the side-effects of boosting, we - * simulate or emulate (almost) all ARM instructions. - * - * "Simulation" is where the instruction's behavior is duplicated in - * C code. "Emulation" is where the original instruction is rewritten - * and executed, often by altering its registers. - * - * By having all behavior of the kprobe'd instruction completed before - * returning from the kprobe_handler(), all locks (scheduler and - * interrupt) can safely be released. There is no need for secondary - * breakpoints, no race with MP or preemptable kernels, nor having to - * clean up resources counts at a later time impacting overall system - * performance. By rewriting the instruction, only the minimum registers - * need to be loaded and saved back optimizing performance. - * - * Calling the insnslot_*_rwflags version of a function doesn't hurt - * anything even when the CPSR flags aren't updated by the - * instruction. It's just a little slower in return for saving - * a little space by not having a duplicate function that doesn't - * update the flags. (The same optimization can be said for - * instructions that do or don't perform register writeback) - * Also, instructions can either read the flags, only write the - * flags, or read and write the flags. To save combinations - * rather than for sheer performance, flag functions just assume - * read and write of flags. - */ - -static void __kprobes simulate_bbl(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = p->opcode; - long iaddr = (long)p->addr; - int disp = branch_displacement(insn); - - if (insn & (1 << 24)) - regs->ARM_lr = iaddr + 4; - - regs->ARM_pc = iaddr + 8 + disp; -} - -static void __kprobes simulate_blx1(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = p->opcode; - long iaddr = (long)p->addr; - int disp = branch_displacement(insn); - - regs->ARM_lr = iaddr + 4; - regs->ARM_pc = iaddr + 8 + disp + ((insn >> 23) & 0x2); - regs->ARM_cpsr |= PSR_T_BIT; -} - -static void __kprobes simulate_blx2bx(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = p->opcode; - int rm = insn & 0xf; - long rmv = regs->uregs[rm]; - - if (insn & (1 << 5)) - regs->ARM_lr = (long)p->addr + 4; - - regs->ARM_pc = rmv & ~0x1; - regs->ARM_cpsr &= ~PSR_T_BIT; - if (rmv & 0x1) - regs->ARM_cpsr |= PSR_T_BIT; -} - -static void __kprobes simulate_mrs(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - unsigned long mask = 0xf8ff03df; /* Mask out execution state */ - regs->uregs[rd] = regs->ARM_cpsr & mask; -} - -static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = p->opcode; - int rn = (insn >> 16) & 0xf; - int lbit = insn & (1 << 20); - int wbit = insn & (1 << 21); - int ubit = insn & (1 << 23); - int pbit = insn & (1 << 24); - long *addr = (long *)regs->uregs[rn]; - int reg_bit_vector; - int reg_count; - - reg_count = 0; - reg_bit_vector = insn & 0xffff; - while (reg_bit_vector) { - reg_bit_vector &= (reg_bit_vector - 1); - ++reg_count; - } - - if (!ubit) - addr -= reg_count; - addr += (!pbit == !ubit); - - reg_bit_vector = insn & 0xffff; - while (reg_bit_vector) { - int reg = __ffs(reg_bit_vector); - reg_bit_vector &= (reg_bit_vector - 1); - if (lbit) - regs->uregs[reg] = *addr++; - else - *addr++ = regs->uregs[reg]; - } - - if (wbit) { - if (!ubit) - addr -= reg_count; - addr -= (!pbit == !ubit); - regs->uregs[rn] = (long)addr; - } -} - -static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs) -{ - regs->ARM_pc = (long)p->addr + str_pc_offset; - simulate_ldm1stm1(p, regs); - regs->ARM_pc = (long)p->addr + 4; -} - -static void __kprobes simulate_mov_ipsp(struct kprobe *p, struct pt_regs *regs) -{ - regs->uregs[12] = regs->uregs[13]; -} - -static void __kprobes emulate_ldrd(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; /* rm may be invalid, don't care. */ - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - - /* Not following the C calling convention here, so need asm(). */ - __asm__ __volatile__ ( - "ldr r0, %[rn] \n\t" - "ldr r1, %[rm] \n\t" - "msr cpsr_fs, %[cpsr]\n\t" - "mov lr, pc \n\t" - "mov pc, %[i_fn] \n\t" - "str r0, %[rn] \n\t" /* in case of writeback */ - "str r2, %[rd0] \n\t" - "str r3, %[rd1] \n\t" - : [rn] "+m" (rnv), - [rd0] "=m" (regs->uregs[rd]), - [rd1] "=m" (regs->uregs[rd+1]) - : [rm] "m" (rmv), - [cpsr] "r" (regs->ARM_cpsr), - [i_fn] "r" (i_fn) - : "r0", "r1", "r2", "r3", "lr", "cc" - ); - if (is_writeback(insn)) - regs->uregs[rn] = rnv; -} - -static void __kprobes emulate_strd(struct kprobe *p, struct pt_regs *regs) -{ - insn_4arg_fn_t *i_fn = (insn_4arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - /* rm/rmv may be invalid, don't care. */ - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rnv_wb; - - rnv_wb = insnslot_4arg_rflags(rnv, rmv, regs->uregs[rd], - regs->uregs[rd+1], - regs->ARM_cpsr, i_fn); - if (is_writeback(insn)) - regs->uregs[rn] = rnv_wb; -} - -static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs) -{ - insn_llret_3arg_fn_t *i_fn = (insn_llret_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - union reg_pair fnr; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rdv; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long cpsr = regs->ARM_cpsr; - - fnr.dr = insnslot_llret_3arg_rflags(rnv, 0, rmv, cpsr, i_fn); - if (rn != 15) - regs->uregs[rn] = fnr.r0; /* Save Rn in case of writeback. */ - rdv = fnr.r1; - - if (rd == 15) { -#if __LINUX_ARM_ARCH__ >= 5 - cpsr &= ~PSR_T_BIT; - if (rdv & 0x1) - cpsr |= PSR_T_BIT; - regs->ARM_cpsr = cpsr; - rdv &= ~0x1; -#else - rdv &= ~0x2; -#endif - } - regs->uregs[rd] = rdv; -} - -static void __kprobes emulate_str(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long iaddr = (long)p->addr; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rdv = (rd == 15) ? iaddr + str_pc_offset : regs->uregs[rd]; - long rnv = (rn == 15) ? iaddr + 8 : regs->uregs[rn]; - long rmv = regs->uregs[rm]; /* rm/rmv may be invalid, don't care. */ - long rnv_wb; - - rnv_wb = insnslot_3arg_rflags(rnv, rdv, rmv, regs->ARM_cpsr, i_fn); - if (rn != 15) - regs->uregs[rn] = rnv_wb; /* Save Rn in case of writeback. */ -} - -static void __kprobes emulate_sat(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rm = insn & 0xf; - long rmv = regs->uregs[rm]; - - /* Writes Q flag */ - regs->uregs[rd] = insnslot_1arg_rwflags(rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_sel(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rnv = regs->uregs[rn]; - long rmv = regs->uregs[rm]; - - /* Reads GE bits */ - regs->uregs[rd] = insnslot_2arg_rflags(rnv, rmv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_none(struct kprobe *p, struct pt_regs *regs) -{ - insn_0arg_fn_t *i_fn = (insn_0arg_fn_t *)&p->ainsn.insn[0]; - - insnslot_0arg_rflags(regs->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_nop(struct kprobe *p, struct pt_regs *regs) -{ -} - -static void __kprobes -emulate_rd12_modify(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - long rdv = regs->uregs[rd]; - - regs->uregs[rd] = insnslot_1arg_rflags(rdv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd12rn0_modify(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = insn & 0xf; - long rdv = regs->uregs[rd]; - long rnv = regs->uregs[rn]; - - regs->uregs[rd] = insnslot_2arg_rflags(rdv, rnv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_rd12rm0(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rm = insn & 0xf; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = insnslot_1arg_rflags(rmv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd12rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rnv = regs->uregs[rn]; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = - insnslot_2arg_rwflags(rnv, rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd16rn12rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 16) & 0xf; - int rn = (insn >> 12) & 0xf; - int rs = (insn >> 8) & 0xf; - int rm = insn & 0xf; - long rnv = regs->uregs[rn]; - long rsv = regs->uregs[rs]; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = - insnslot_3arg_rwflags(rnv, rsv, rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd16rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 16) & 0xf; - int rs = (insn >> 8) & 0xf; - int rm = insn & 0xf; - long rsv = regs->uregs[rs]; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = - insnslot_2arg_rwflags(rsv, rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rdhi16rdlo12rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_llret_4arg_fn_t *i_fn = (insn_llret_4arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - union reg_pair fnr; - int rdhi = (insn >> 16) & 0xf; - int rdlo = (insn >> 12) & 0xf; - int rs = (insn >> 8) & 0xf; - int rm = insn & 0xf; - long rsv = regs->uregs[rs]; - long rmv = regs->uregs[rm]; - - fnr.dr = insnslot_llret_4arg_rwflags(regs->uregs[rdhi], - regs->uregs[rdlo], rsv, rmv, - ®s->ARM_cpsr, i_fn); - regs->uregs[rdhi] = fnr.r0; - regs->uregs[rdlo] = fnr.r1; -} - -static void __kprobes -emulate_alu_imm_rflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; - - regs->uregs[rd] = insnslot_1arg_rflags(rnv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_imm_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; - - regs->uregs[rd] = insnslot_1arg_rwflags(rnv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_tests_imm(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rn = (insn >> 16) & 0xf; - long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; - - insnslot_1arg_rwflags(rnv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_rflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; /* rn/rnv/rs/rsv may be */ - int rs = (insn >> 8) & 0xf; /* invalid, don't care. */ - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rsv = regs->uregs[rs]; - - regs->uregs[rd] = - insnslot_3arg_rflags(rnv, rmv, rsv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; /* rn/rnv/rs/rsv may be */ - int rs = (insn >> 8) & 0xf; /* invalid, don't care. */ - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rsv = regs->uregs[rs]; - - regs->uregs[rd] = - insnslot_3arg_rwflags(rnv, rmv, rsv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_tests(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rn = (insn >> 16) & 0xf; - int rs = (insn >> 8) & 0xf; /* rs/rsv may be invalid, don't care. */ - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rsv = regs->uregs[rs]; - - insnslot_3arg_rwflags(rnv, rmv, rsv, ®s->ARM_cpsr, i_fn); -} - -static enum kprobe_insn __kprobes -prep_emulate_ldr_str(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - int not_imm = (insn & (1 << 26)) ? (insn & (1 << 25)) - : (~insn & (1 << 22)); - - if (is_writeback(insn) && is_r15(insn, 16)) - return INSN_REJECTED; /* Writeback to PC */ - - insn &= 0xfff00fff; - insn |= 0x00001000; /* Rn = r0, Rd = r1 */ - if (not_imm) { - insn &= ~0xf; - insn |= 2; /* Rm = r2 */ - } - asi->insn[0] = insn; - asi->insn_handler = (insn & (1 << 20)) ? emulate_ldr : emulate_str; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12_modify(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xffff0fff; /* Rd = r0 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12_modify; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12rn0_modify(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xffff0ff0; /* Rd = r0 */ - insn |= 0x00000001; /* Rn = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12rn0_modify; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12rm0(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xffff0ff0; /* Rd = r0, Rm = r0 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12rm0; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12rn16rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xfff00ff0; /* Rd = r0, Rn = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12rn16rm0_rwflags; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd16rs8rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 16)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xfff0f0f0; /* Rd = r0, Rs = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd16rs8rm0_rwflags; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd16rn12rs8rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 16)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xfff000f0; /* Rd = r0, Rn = r0 */ - insn |= 0x00000102; /* Rs = r1, Rm = r2 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd16rn12rs8rm0_rwflags; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 16) || is_r15(insn, 12)) - return INSN_REJECTED; /* RdHi or RdLo is PC */ - - insn &= 0xfff000f0; /* RdHi = r0, RdLo = r1 */ - insn |= 0x00001203; /* Rs = r2, Rm = r3 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rdhi16rdlo12rs8rm0_rwflags; - return INSN_GOOD; -} - -/* - * For the instruction masking and comparisons in all the "space_*" - * functions below, Do _not_ rearrange the order of tests unless - * you're very, very sure of what you are doing. For the sake of - * efficiency, the masks for some tests sometimes assume other test - * have been done prior to them so the number of patterns to test - * for an instruction set can be as broad as possible to reduce the - * number of tests needed. - */ - -static enum kprobe_insn __kprobes -space_1111(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* memory hint : 1111 0100 x001 xxxx xxxx xxxx xxxx xxxx : */ - /* PLDI : 1111 0100 x101 xxxx xxxx xxxx xxxx xxxx : */ - /* PLDW : 1111 0101 x001 xxxx xxxx xxxx xxxx xxxx : */ - /* PLD : 1111 0101 x101 xxxx xxxx xxxx xxxx xxxx : */ - if ((insn & 0xfe300000) == 0xf4100000) { - asi->insn_handler = emulate_nop; - return INSN_GOOD_NO_SLOT; - } - - /* BLX(1) : 1111 101x xxxx xxxx xxxx xxxx xxxx xxxx : */ - if ((insn & 0xfe000000) == 0xfa000000) { - asi->insn_handler = simulate_blx1; - return INSN_GOOD_NO_SLOT; - } - - /* CPS : 1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */ - /* SETEND: 1111 0001 0000 0001 xxxx xxxx 0000 xxxx */ - - /* SRS : 1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */ - /* RFE : 1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ - - /* Coprocessor instructions... */ - /* MCRR2 : 1111 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */ - /* MRRC2 : 1111 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */ - /* LDC2 : 1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ - /* STC2 : 1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ - /* CDP2 : 1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ - /* MCR2 : 1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ - /* MRC2 : 1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ - - return INSN_REJECTED; -} - -static enum kprobe_insn __kprobes -space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* cccc 0001 0xx0 xxxx xxxx xxxx xxxx xxx0 xxxx */ - if ((insn & 0x0f900010) == 0x01000000) { - - /* MRS cpsr : cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */ - if ((insn & 0x0ff000f0) == 0x01000000) { - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - asi->insn_handler = simulate_mrs; - return INSN_GOOD_NO_SLOT; - } - - /* SMLALxy : cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */ - if ((insn & 0x0ff00090) == 0x01400080) - return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, - asi); - - /* SMULWy : cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */ - /* SMULxy : cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */ - if ((insn & 0x0ff000b0) == 0x012000a0 || - (insn & 0x0ff00090) == 0x01600080) - return prep_emulate_rd16rs8rm0_wflags(insn, asi); - - /* SMLAxy : cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx : Q */ - /* SMLAWy : cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx : Q */ - if ((insn & 0x0ff00090) == 0x01000080 || - (insn & 0x0ff000b0) == 0x01200080) - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - - /* BXJ : cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */ - /* MSR : cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */ - /* MRS spsr : cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */ - - /* Other instruction encodings aren't yet defined */ - return INSN_REJECTED; - } - - /* cccc 0001 0xx0 xxxx xxxx xxxx xxxx 0xx1 xxxx */ - else if ((insn & 0x0f900090) == 0x01000010) { - - /* BLX(2) : cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */ - /* BX : cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */ - if ((insn & 0x0ff000d0) == 0x01200010) { - if ((insn & 0x0ff000ff) == 0x0120003f) - return INSN_REJECTED; /* BLX pc */ - asi->insn_handler = simulate_blx2bx; - return INSN_GOOD_NO_SLOT; - } - - /* CLZ : cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */ - if ((insn & 0x0ff000f0) == 0x01600010) - return prep_emulate_rd12rm0(insn, asi); - - /* QADD : cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx :Q */ - /* QSUB : cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx :Q */ - /* QDADD : cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx :Q */ - /* QDSUB : cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx :Q */ - if ((insn & 0x0f9000f0) == 0x01000050) - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - - /* BKPT : 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */ - /* SMC : cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */ - - /* Other instruction encodings aren't yet defined */ - return INSN_REJECTED; - } - - /* cccc 0000 xxxx xxxx xxxx xxxx xxxx 1001 xxxx */ - else if ((insn & 0x0f0000f0) == 0x00000090) { - - /* MUL : cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx : */ - /* MULS : cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx :cc */ - /* MLA : cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx : */ - /* MLAS : cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx :cc */ - /* UMAAL : cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx : */ - /* undef : cccc 0000 0101 xxxx xxxx xxxx 1001 xxxx : */ - /* MLS : cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx : */ - /* undef : cccc 0000 0111 xxxx xxxx xxxx 1001 xxxx : */ - /* UMULL : cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx : */ - /* UMULLS : cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx :cc */ - /* UMLAL : cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx : */ - /* UMLALS : cccc 0000 1011 xxxx xxxx xxxx 1001 xxxx :cc */ - /* SMULL : cccc 0000 1100 xxxx xxxx xxxx 1001 xxxx : */ - /* SMULLS : cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx :cc */ - /* SMLAL : cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx : */ - /* SMLALS : cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx :cc */ - if ((insn & 0x00d00000) == 0x00500000) - return INSN_REJECTED; - else if ((insn & 0x00e00000) == 0x00000000) - return prep_emulate_rd16rs8rm0_wflags(insn, asi); - else if ((insn & 0x00a00000) == 0x00200000) - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - else - return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, - asi); - } - - /* cccc 000x xxxx xxxx xxxx xxxx xxxx 1xx1 xxxx */ - else if ((insn & 0x0e000090) == 0x00000090) { - - /* SWP : cccc 0001 0000 xxxx xxxx xxxx 1001 xxxx */ - /* SWPB : cccc 0001 0100 xxxx xxxx xxxx 1001 xxxx */ - /* ??? : cccc 0001 0x01 xxxx xxxx xxxx 1001 xxxx */ - /* ??? : cccc 0001 0x10 xxxx xxxx xxxx 1001 xxxx */ - /* ??? : cccc 0001 0x11 xxxx xxxx xxxx 1001 xxxx */ - /* STREX : cccc 0001 1000 xxxx xxxx xxxx 1001 xxxx */ - /* LDREX : cccc 0001 1001 xxxx xxxx xxxx 1001 xxxx */ - /* STREXD: cccc 0001 1010 xxxx xxxx xxxx 1001 xxxx */ - /* LDREXD: cccc 0001 1011 xxxx xxxx xxxx 1001 xxxx */ - /* STREXB: cccc 0001 1100 xxxx xxxx xxxx 1001 xxxx */ - /* LDREXB: cccc 0001 1101 xxxx xxxx xxxx 1001 xxxx */ - /* STREXH: cccc 0001 1110 xxxx xxxx xxxx 1001 xxxx */ - /* LDREXH: cccc 0001 1111 xxxx xxxx xxxx 1001 xxxx */ - - /* LDRD : cccc 000x xxx0 xxxx xxxx xxxx 1101 xxxx */ - /* STRD : cccc 000x xxx0 xxxx xxxx xxxx 1111 xxxx */ - /* LDRH : cccc 000x xxx1 xxxx xxxx xxxx 1011 xxxx */ - /* STRH : cccc 000x xxx0 xxxx xxxx xxxx 1011 xxxx */ - /* LDRSB : cccc 000x xxx1 xxxx xxxx xxxx 1101 xxxx */ - /* LDRSH : cccc 000x xxx1 xxxx xxxx xxxx 1111 xxxx */ - if ((insn & 0x0f0000f0) == 0x01000090) { - if ((insn & 0x0fb000f0) == 0x01000090) { - /* SWP/SWPB */ - return prep_emulate_rd12rn16rm0_wflags(insn, - asi); - } else { - /* STREX/LDREX variants and unallocaed space */ - return INSN_REJECTED; - } - - } else if ((insn & 0x0e1000d0) == 0x00000d0) { - /* STRD/LDRD */ - if ((insn & 0x0000e000) == 0x0000e000) - return INSN_REJECTED; /* Rd is LR or PC */ - if (is_writeback(insn) && is_r15(insn, 16)) - return INSN_REJECTED; /* Writeback to PC */ - - insn &= 0xfff00fff; - insn |= 0x00002000; /* Rn = r0, Rd = r2 */ - if (!(insn & (1 << 22))) { - /* Register index */ - insn &= ~0xf; - insn |= 1; /* Rm = r1 */ - } - asi->insn[0] = insn; - asi->insn_handler = - (insn & (1 << 5)) ? emulate_strd : emulate_ldrd; - return INSN_GOOD; - } - - /* LDRH/STRH/LDRSB/LDRSH */ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - return prep_emulate_ldr_str(insn, asi); - } - - /* cccc 000x xxxx xxxx xxxx xxxx xxxx xxxx xxxx */ - - /* - * ALU op with S bit and Rd == 15 : - * cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx - */ - if ((insn & 0x0e10f000) == 0x0010f000) - return INSN_REJECTED; - - /* - * "mov ip, sp" is the most common kprobe'd instruction by far. - * Check and optimize for it explicitly. - */ - if (insn == 0xe1a0c00d) { - asi->insn_handler = simulate_mov_ipsp; - return INSN_GOOD_NO_SLOT; - } - - /* - * Data processing: Immediate-shift / Register-shift - * ALU op : cccc 000x xxxx xxxx xxxx xxxx xxxx xxxx - * CPY : cccc 0001 1010 xxxx xxxx 0000 0000 xxxx - * MOV : cccc 0001 101x xxxx xxxx xxxx xxxx xxxx - * *S (bit 20) updates condition codes - * ADC/SBC/RSC reads the C flag - */ - insn &= 0xfff00ff0; /* Rn = r0, Rd = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - if (insn & 0x010) { - insn &= 0xfffff0ff; /* register shift */ - insn |= 0x00000200; /* Rs = r2 */ - } - asi->insn[0] = insn; - - if ((insn & 0x0f900000) == 0x01100000) { - /* - * TST : cccc 0001 0001 xxxx xxxx xxxx xxxx xxxx - * TEQ : cccc 0001 0011 xxxx xxxx xxxx xxxx xxxx - * CMP : cccc 0001 0101 xxxx xxxx xxxx xxxx xxxx - * CMN : cccc 0001 0111 xxxx xxxx xxxx xxxx xxxx - */ - asi->insn_handler = emulate_alu_tests; - } else { - /* ALU ops which write to Rd */ - asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ - emulate_alu_rwflags : emulate_alu_rflags; - } - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* MOVW : cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */ - /* MOVT : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */ - if ((insn & 0x0fb00000) == 0x03000000) - return prep_emulate_rd12_modify(insn, asi); - - /* hints : cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */ - if ((insn & 0x0fff0000) == 0x03200000) { - unsigned op2 = insn & 0x000000ff; - if (op2 == 0x01 || op2 == 0x04) { - /* YIELD : cccc 0011 0010 0000 xxxx xxxx 0000 0001 */ - /* SEV : cccc 0011 0010 0000 xxxx xxxx 0000 0100 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_none; - return INSN_GOOD; - } else if (op2 <= 0x03) { - /* NOP : cccc 0011 0010 0000 xxxx xxxx 0000 0000 */ - /* WFE : cccc 0011 0010 0000 xxxx xxxx 0000 0010 */ - /* WFI : cccc 0011 0010 0000 xxxx xxxx 0000 0011 */ - /* - * We make WFE and WFI true NOPs to avoid stalls due - * to missing events whilst processing the probe. - */ - asi->insn_handler = emulate_nop; - return INSN_GOOD_NO_SLOT; - } - /* For DBG and unallocated hints it's safest to reject them */ - return INSN_REJECTED; - } - - /* - * MSR : cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx - * ALU op with S bit and Rd == 15 : - * cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx - */ - if ((insn & 0x0fb00000) == 0x03200000 || /* MSR */ - (insn & 0x0e10f000) == 0x0210f000) /* ALU s-bit, R15 */ - return INSN_REJECTED; - - /* - * Data processing: 32-bit Immediate - * ALU op : cccc 001x xxxx xxxx xxxx xxxx xxxx xxxx - * MOV : cccc 0011 101x xxxx xxxx xxxx xxxx xxxx - * *S (bit 20) updates condition codes - * ADC/SBC/RSC reads the C flag - */ - insn &= 0xfff00fff; /* Rn = r0 and Rd = r0 */ - asi->insn[0] = insn; - - if ((insn & 0x0f900000) == 0x03100000) { - /* - * TST : cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx - * TEQ : cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx - * CMP : cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx - * CMN : cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx - */ - asi->insn_handler = emulate_alu_tests_imm; - } else { - /* ALU ops which write to Rd */ - asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ - emulate_alu_imm_rwflags : emulate_alu_imm_rflags; - } - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* SEL : cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx GE: !!! */ - if ((insn & 0x0ff000f0) == 0x068000b0) { - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - insn &= 0xfff00ff0; /* Rd = r0, Rn = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_sel; - return INSN_GOOD; - } - - /* SSAT : cccc 0110 101x xxxx xxxx xxxx xx01 xxxx :Q */ - /* USAT : cccc 0110 111x xxxx xxxx xxxx xx01 xxxx :Q */ - /* SSAT16 : cccc 0110 1010 xxxx xxxx xxxx 0011 xxxx :Q */ - /* USAT16 : cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx :Q */ - if ((insn & 0x0fa00030) == 0x06a00010 || - (insn & 0x0fb000f0) == 0x06a00030) { - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - insn &= 0xffff0ff0; /* Rd = r0, Rm = r0 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_sat; - return INSN_GOOD; - } - - /* REV : cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */ - /* REV16 : cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */ - /* RBIT : cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */ - /* REVSH : cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */ - if ((insn & 0x0ff00070) == 0x06b00030 || - (insn & 0x0ff00070) == 0x06f00030) - return prep_emulate_rd12rm0(insn, asi); - - /* ??? : cccc 0110 0000 xxxx xxxx xxxx xxx1 xxxx : */ - /* SADD16 : cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx :GE */ - /* SADDSUBX : cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx :GE */ - /* SSUBADDX : cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx :GE */ - /* SSUB16 : cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx :GE */ - /* SADD8 : cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx :GE */ - /* ??? : cccc 0110 0001 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0001 xxxx xxxx xxxx 1101 xxxx : */ - /* SSUB8 : cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx :GE */ - /* QADD16 : cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx : */ - /* QADDSUBX : cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx : */ - /* QSUBADDX : cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx : */ - /* QSUB16 : cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx : */ - /* QADD8 : cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0010 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0010 xxxx xxxx xxxx 1101 xxxx : */ - /* QSUB8 : cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx : */ - /* SHADD16 : cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx : */ - /* SHADDSUBX : cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx : */ - /* SHSUBADDX : cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx : */ - /* SHSUB16 : cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx : */ - /* SHADD8 : cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0011 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0011 xxxx xxxx xxxx 1101 xxxx : */ - /* SHSUB8 : cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx : */ - /* ??? : cccc 0110 0100 xxxx xxxx xxxx xxx1 xxxx : */ - /* UADD16 : cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx :GE */ - /* UADDSUBX : cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx :GE */ - /* USUBADDX : cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx :GE */ - /* USUB16 : cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx :GE */ - /* UADD8 : cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx :GE */ - /* ??? : cccc 0110 0101 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0101 xxxx xxxx xxxx 1101 xxxx : */ - /* USUB8 : cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx :GE */ - /* UQADD16 : cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx : */ - /* UQADDSUBX : cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx : */ - /* UQSUBADDX : cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx : */ - /* UQSUB16 : cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx : */ - /* UQADD8 : cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0110 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0110 xxxx xxxx xxxx 1101 xxxx : */ - /* UQSUB8 : cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx : */ - /* UHADD16 : cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx : */ - /* UHADDSUBX : cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx : */ - /* UHSUBADDX : cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx : */ - /* UHSUB16 : cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx : */ - /* UHADD8 : cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0111 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0111 xxxx xxxx xxxx 1101 xxxx : */ - /* UHSUB8 : cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx : */ - if ((insn & 0x0f800010) == 0x06000010) { - if ((insn & 0x00300000) == 0x00000000 || - (insn & 0x000000e0) == 0x000000a0 || - (insn & 0x000000e0) == 0x000000c0) - return INSN_REJECTED; /* Unallocated space */ - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - } - - /* PKHBT : cccc 0110 1000 xxxx xxxx xxxx x001 xxxx : */ - /* PKHTB : cccc 0110 1000 xxxx xxxx xxxx x101 xxxx : */ - if ((insn & 0x0ff00030) == 0x06800010) - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - - /* SXTAB16 : cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTB16 : cccc 0110 1000 1111 xxxx xxxx 0111 xxxx : */ - /* ??? : cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTAB : cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTB : cccc 0110 1010 1111 xxxx xxxx 0111 xxxx : */ - /* SXTAH : cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTH : cccc 0110 1011 1111 xxxx xxxx 0111 xxxx : */ - /* UXTAB16 : cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTB16 : cccc 0110 1100 1111 xxxx xxxx 0111 xxxx : */ - /* ??? : cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTAB : cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTB : cccc 0110 1110 1111 xxxx xxxx 0111 xxxx : */ - /* UXTAH : cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTH : cccc 0110 1111 1111 xxxx xxxx 0111 xxxx : */ - if ((insn & 0x0f8000f0) == 0x06800070) { - if ((insn & 0x00300000) == 0x00100000) - return INSN_REJECTED; /* Unallocated space */ - - if ((insn & 0x000f0000) == 0x000f0000) - return prep_emulate_rd12rm0(insn, asi); - else - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - } - - /* Other instruction encodings aren't yet defined */ - return INSN_REJECTED; -} - -static enum kprobe_insn __kprobes -space_cccc_0111__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* Undef : cccc 0111 1111 xxxx xxxx xxxx 1111 xxxx */ - if ((insn & 0x0ff000f0) == 0x03f000f0) - return INSN_REJECTED; - - /* SMLALD : cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */ - /* SMLSLD : cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */ - if ((insn & 0x0ff00090) == 0x07400010) - return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, asi); - - /* SMLAD : cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx :Q */ - /* SMUAD : cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx :Q */ - /* SMLSD : cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx :Q */ - /* SMUSD : cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx : */ - /* SMMLA : cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx : */ - /* SMMUL : cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx : */ - /* USADA8 : cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx : */ - /* USAD8 : cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx : */ - if ((insn & 0x0ff00090) == 0x07000010 || - (insn & 0x0ff000d0) == 0x07500010 || - (insn & 0x0ff000f0) == 0x07800010) { - - if ((insn & 0x0000f000) == 0x0000f000) - return prep_emulate_rd16rs8rm0_wflags(insn, asi); - else - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - } - - /* SMMLS : cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx : */ - if ((insn & 0x0ff000d0) == 0x075000d0) - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - - /* SBFX : cccc 0111 101x xxxx xxxx xxxx x101 xxxx : */ - /* UBFX : cccc 0111 111x xxxx xxxx xxxx x101 xxxx : */ - if ((insn & 0x0fa00070) == 0x07a00050) - return prep_emulate_rd12rm0(insn, asi); - - /* BFI : cccc 0111 110x xxxx xxxx xxxx x001 xxxx : */ - /* BFC : cccc 0111 110x xxxx xxxx xxxx x001 1111 : */ - if ((insn & 0x0fe00070) == 0x07c00010) { - - if ((insn & 0x0000000f) == 0x0000000f) - return prep_emulate_rd12_modify(insn, asi); - else - return prep_emulate_rd12rn0_modify(insn, asi); - } - - return INSN_REJECTED; -} - -static enum kprobe_insn __kprobes -space_cccc_01xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* LDR : cccc 01xx x0x1 xxxx xxxx xxxx xxxx xxxx */ - /* LDRB : cccc 01xx x1x1 xxxx xxxx xxxx xxxx xxxx */ - /* LDRBT : cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */ - /* LDRT : cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */ - /* STR : cccc 01xx x0x0 xxxx xxxx xxxx xxxx xxxx */ - /* STRB : cccc 01xx x1x0 xxxx xxxx xxxx xxxx xxxx */ - /* STRBT : cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */ - /* STRT : cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */ - - if ((insn & 0x00500000) == 0x00500000 && is_r15(insn, 12)) - return INSN_REJECTED; /* LDRB into PC */ - - return prep_emulate_ldr_str(insn, asi); -} - -static enum kprobe_insn __kprobes -space_cccc_100x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* LDM(2) : cccc 100x x101 xxxx 0xxx xxxx xxxx xxxx */ - /* LDM(3) : cccc 100x x1x1 xxxx 1xxx xxxx xxxx xxxx */ - if ((insn & 0x0e708000) == 0x85000000 || - (insn & 0x0e508000) == 0x85010000) - return INSN_REJECTED; - - /* LDM(1) : cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ - /* STM(1) : cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */ - asi->insn_handler = ((insn & 0x108000) == 0x008000) ? /* STM & R15 */ - simulate_stm1_pc : simulate_ldm1stm1; - return INSN_GOOD_NO_SLOT; -} - -static enum kprobe_insn __kprobes -space_cccc_101x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* B : cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */ - /* BL : cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */ - asi->insn_handler = simulate_bbl; - return INSN_GOOD_NO_SLOT; -} - -static enum kprobe_insn __kprobes -space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* Coprocessor instructions... */ - /* MCRR : cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */ - /* MRRC : cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */ - /* LDC : cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ - /* STC : cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ - /* CDP : cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ - /* MCR : cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ - /* MRC : cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ - - /* SVC : cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */ - - return INSN_REJECTED; -} - -static unsigned long __kprobes __check_eq(unsigned long cpsr) -{ - return cpsr & PSR_Z_BIT; -} - -static unsigned long __kprobes __check_ne(unsigned long cpsr) -{ - return (~cpsr) & PSR_Z_BIT; -} - -static unsigned long __kprobes __check_cs(unsigned long cpsr) -{ - return cpsr & PSR_C_BIT; -} - -static unsigned long __kprobes __check_cc(unsigned long cpsr) -{ - return (~cpsr) & PSR_C_BIT; -} - -static unsigned long __kprobes __check_mi(unsigned long cpsr) -{ - return cpsr & PSR_N_BIT; -} - -static unsigned long __kprobes __check_pl(unsigned long cpsr) -{ - return (~cpsr) & PSR_N_BIT; -} - -static unsigned long __kprobes __check_vs(unsigned long cpsr) -{ - return cpsr & PSR_V_BIT; -} - -static unsigned long __kprobes __check_vc(unsigned long cpsr) -{ - return (~cpsr) & PSR_V_BIT; -} - -static unsigned long __kprobes __check_hi(unsigned long cpsr) -{ - cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ - return cpsr & PSR_C_BIT; -} - -static unsigned long __kprobes __check_ls(unsigned long cpsr) -{ - cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ - return (~cpsr) & PSR_C_BIT; -} - -static unsigned long __kprobes __check_ge(unsigned long cpsr) -{ - cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - return (~cpsr) & PSR_N_BIT; -} - -static unsigned long __kprobes __check_lt(unsigned long cpsr) -{ - cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - return cpsr & PSR_N_BIT; -} - -static unsigned long __kprobes __check_gt(unsigned long cpsr) -{ - unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ - return (~temp) & PSR_N_BIT; -} - -static unsigned long __kprobes __check_le(unsigned long cpsr) -{ - unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ - return temp & PSR_N_BIT; -} - -static unsigned long __kprobes __check_al(unsigned long cpsr) -{ - return true; -} - -static kprobe_check_cc * const condition_checks[16] = { - &__check_eq, &__check_ne, &__check_cs, &__check_cc, - &__check_mi, &__check_pl, &__check_vs, &__check_vc, - &__check_hi, &__check_ls, &__check_ge, &__check_lt, - &__check_gt, &__check_le, &__check_al, &__check_al -}; - -/* Return: - * INSN_REJECTED If instruction is one not allowed to kprobe, - * INSN_GOOD If instruction is supported and uses instruction slot, - * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. - * - * For instructions we don't want to kprobe (INSN_REJECTED return result): - * These are generally ones that modify the processor state making - * them "hard" to simulate such as switches processor modes or - * make accesses in alternate modes. Any of these could be simulated - * if the work was put into it, but low return considering they - * should also be very rare. - */ -enum kprobe_insn __kprobes -arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - asi->insn_check_cc = condition_checks[insn>>28]; - asi->insn[1] = KPROBE_RETURN_INSTRUCTION; - - if ((insn & 0xf0000000) == 0xf0000000) - - return space_1111(insn, asi); - - else if ((insn & 0x0e000000) == 0x00000000) - - return space_cccc_000x(insn, asi); - - else if ((insn & 0x0e000000) == 0x02000000) - - return space_cccc_001x(insn, asi); - - else if ((insn & 0x0f000010) == 0x06000010) - - return space_cccc_0110__1(insn, asi); - - else if ((insn & 0x0f000010) == 0x07000010) - - return space_cccc_0111__1(insn, asi); - - else if ((insn & 0x0c000000) == 0x04000000) - - return space_cccc_01xx(insn, asi); - - else if ((insn & 0x0e000000) == 0x08000000) - - return space_cccc_100x(insn, asi); - - else if ((insn & 0x0e000000) == 0x0a000000) - - return space_cccc_101x(insn, asi); - - return space_cccc_11xx(insn, asi); -} - -void __init arm_kprobe_decode_init(void) -{ - find_str_pc_offset(); -} -- cgit v1.2.3 From 221bf15ffd2ad6cdc624aa4274f706499501c123 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 20 Apr 2011 10:52:38 +0100 Subject: ARM: kprobes: Split out internal parts of kprobes.h Later, we will be adding a considerable amount of internal implementation definitions to kprobe header files and it would be good to have these in local header file along side the source code, rather than pollute the existing header which is include by all users of kprobes. To this end, we add arch/arm/kernel/kprobes.h and move into this the existing internal defintions from arch/arm/include/asm/kprobes.h Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/include/asm/kprobes.h | 17 ----------------- arch/arm/kernel/kprobes-arm.c | 2 ++ arch/arm/kernel/kprobes.c | 2 ++ arch/arm/kernel/kprobes.h | 37 +++++++++++++++++++++++++++++++++++++ 4 files changed, 41 insertions(+), 17 deletions(-) create mode 100644 arch/arm/kernel/kprobes.h diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index e46bdd0097eb..57d37d52d71e 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -24,12 +24,6 @@ #define MAX_INSN_SIZE 2 #define MAX_STACK_SIZE 64 /* 32 would probably be OK */ -/* - * This undefined instruction must be unique and - * reserved solely for kprobes' use. - */ -#define KPROBE_BREAKPOINT_INSTRUCTION 0xe7f001f8 - #define regs_return_value(regs) ((regs)->ARM_r0) #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 @@ -62,20 +56,9 @@ struct kprobe_ctlblk { }; void arch_remove_kprobe(struct kprobe *); -void kretprobe_trampoline(void); - int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr); int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); -enum kprobe_insn { - INSN_REJECTED, - INSN_GOOD, - INSN_GOOD_NO_SLOT -}; - -enum kprobe_insn arm_kprobe_decode_insn(kprobe_opcode_t, - struct arch_specific_insn *); -void __init arm_kprobe_decode_init(void); #endif /* _ARM_KPROBES_H */ diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 15eeff6aea0e..976ce14c5576 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -61,6 +61,8 @@ #include #include +#include "kprobes.h" + #define sign_extend(x, signbit) ((x) | (0 - ((x) & (1 << (signbit))))) #define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25) diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 1656c87501c0..3ba5f8d0d82c 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -28,6 +28,8 @@ #include #include +#include "kprobes.h" + #define MIN_STACK_SIZE(addr) \ min((unsigned long)MAX_STACK_SIZE, \ (unsigned long)current_thread_info() + THREAD_START_SP - (addr)) diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h new file mode 100644 index 000000000000..87a5241b2f18 --- /dev/null +++ b/arch/arm/kernel/kprobes.h @@ -0,0 +1,37 @@ +/* + * arch/arm/kernel/kprobes.h + * + * Contents moved from arch/arm/include/asm/kprobes.h which is + * Copyright (C) 2006, 2007 Motorola Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ARM_KERNEL_KPROBES_H +#define _ARM_KERNEL_KPROBES_H + +/* + * This undefined instruction must be unique and + * reserved solely for kprobes' use. + */ +#define KPROBE_BREAKPOINT_INSTRUCTION 0xe7f001f8 + +enum kprobe_insn { + INSN_REJECTED, + INSN_GOOD, + INSN_GOOD_NO_SLOT +}; + +enum kprobe_insn arm_kprobe_decode_insn(kprobe_opcode_t, + struct arch_specific_insn *); + +void __init arm_kprobe_decode_init(void); + +#endif /* _ARM_KERNEL_KPROBES_H */ -- cgit v1.2.3 From 0ab4c02ddae2e1d32d686a7773608f6c44fb2a83 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 6 Jul 2011 11:25:18 +0100 Subject: ARM: kprobes: Add kprobes-common.c This file will contain the instruction decoding and emulation code which is common to both ARM and Thumb instruction sets. For now, we will just move over condition_checks from kprobes-arm.c This table is also renamed to kprobe_condition_checks to avoid polluting the public namespace with a too generic name. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/Makefile | 2 +- arch/arm/kernel/kprobes-arm.c | 92 +--------------------------------- arch/arm/kernel/kprobes-common.c | 105 +++++++++++++++++++++++++++++++++++++++ arch/arm/kernel/kprobes.h | 2 + 4 files changed, 109 insertions(+), 92 deletions(-) create mode 100644 arch/arm/kernel/kprobes-common.c diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 914c7a6f1706..a22b8f1c7b14 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -37,7 +37,7 @@ obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o -obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_KPROBES) += kprobes.o kprobes-common.o obj-$(CONFIG_KPROBES) += kprobes-arm.o obj-$(CONFIG_ATAGS_PROC) += atags.o obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 976ce14c5576..8d4464f9471b 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1523,96 +1523,6 @@ space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) return INSN_REJECTED; } -static unsigned long __kprobes __check_eq(unsigned long cpsr) -{ - return cpsr & PSR_Z_BIT; -} - -static unsigned long __kprobes __check_ne(unsigned long cpsr) -{ - return (~cpsr) & PSR_Z_BIT; -} - -static unsigned long __kprobes __check_cs(unsigned long cpsr) -{ - return cpsr & PSR_C_BIT; -} - -static unsigned long __kprobes __check_cc(unsigned long cpsr) -{ - return (~cpsr) & PSR_C_BIT; -} - -static unsigned long __kprobes __check_mi(unsigned long cpsr) -{ - return cpsr & PSR_N_BIT; -} - -static unsigned long __kprobes __check_pl(unsigned long cpsr) -{ - return (~cpsr) & PSR_N_BIT; -} - -static unsigned long __kprobes __check_vs(unsigned long cpsr) -{ - return cpsr & PSR_V_BIT; -} - -static unsigned long __kprobes __check_vc(unsigned long cpsr) -{ - return (~cpsr) & PSR_V_BIT; -} - -static unsigned long __kprobes __check_hi(unsigned long cpsr) -{ - cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ - return cpsr & PSR_C_BIT; -} - -static unsigned long __kprobes __check_ls(unsigned long cpsr) -{ - cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ - return (~cpsr) & PSR_C_BIT; -} - -static unsigned long __kprobes __check_ge(unsigned long cpsr) -{ - cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - return (~cpsr) & PSR_N_BIT; -} - -static unsigned long __kprobes __check_lt(unsigned long cpsr) -{ - cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - return cpsr & PSR_N_BIT; -} - -static unsigned long __kprobes __check_gt(unsigned long cpsr) -{ - unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ - return (~temp) & PSR_N_BIT; -} - -static unsigned long __kprobes __check_le(unsigned long cpsr) -{ - unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ - temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ - return temp & PSR_N_BIT; -} - -static unsigned long __kprobes __check_al(unsigned long cpsr) -{ - return true; -} - -static kprobe_check_cc * const condition_checks[16] = { - &__check_eq, &__check_ne, &__check_cs, &__check_cc, - &__check_mi, &__check_pl, &__check_vs, &__check_vc, - &__check_hi, &__check_ls, &__check_ge, &__check_lt, - &__check_gt, &__check_le, &__check_al, &__check_al -}; - /* Return: * INSN_REJECTED If instruction is one not allowed to kprobe, * INSN_GOOD If instruction is supported and uses instruction slot, @@ -1628,7 +1538,7 @@ static kprobe_check_cc * const condition_checks[16] = { enum kprobe_insn __kprobes arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { - asi->insn_check_cc = condition_checks[insn>>28]; + asi->insn_check_cc = kprobe_condition_checks[insn>>28]; asi->insn[1] = KPROBE_RETURN_INSTRUCTION; if ((insn & 0xf0000000) == 0xf0000000) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c new file mode 100644 index 000000000000..794827ec27d7 --- /dev/null +++ b/arch/arm/kernel/kprobes-common.c @@ -0,0 +1,105 @@ +/* + * arch/arm/kernel/kprobes-common.c + * + * Copyright (C) 2011 Jon Medhurst . + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +#include "kprobes.h" + + +static unsigned long __kprobes __check_eq(unsigned long cpsr) +{ + return cpsr & PSR_Z_BIT; +} + +static unsigned long __kprobes __check_ne(unsigned long cpsr) +{ + return (~cpsr) & PSR_Z_BIT; +} + +static unsigned long __kprobes __check_cs(unsigned long cpsr) +{ + return cpsr & PSR_C_BIT; +} + +static unsigned long __kprobes __check_cc(unsigned long cpsr) +{ + return (~cpsr) & PSR_C_BIT; +} + +static unsigned long __kprobes __check_mi(unsigned long cpsr) +{ + return cpsr & PSR_N_BIT; +} + +static unsigned long __kprobes __check_pl(unsigned long cpsr) +{ + return (~cpsr) & PSR_N_BIT; +} + +static unsigned long __kprobes __check_vs(unsigned long cpsr) +{ + return cpsr & PSR_V_BIT; +} + +static unsigned long __kprobes __check_vc(unsigned long cpsr) +{ + return (~cpsr) & PSR_V_BIT; +} + +static unsigned long __kprobes __check_hi(unsigned long cpsr) +{ + cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return cpsr & PSR_C_BIT; +} + +static unsigned long __kprobes __check_ls(unsigned long cpsr) +{ + cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (~cpsr) & PSR_C_BIT; +} + +static unsigned long __kprobes __check_ge(unsigned long cpsr) +{ + cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (~cpsr) & PSR_N_BIT; +} + +static unsigned long __kprobes __check_lt(unsigned long cpsr) +{ + cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return cpsr & PSR_N_BIT; +} + +static unsigned long __kprobes __check_gt(unsigned long cpsr) +{ + unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ + return (~temp) & PSR_N_BIT; +} + +static unsigned long __kprobes __check_le(unsigned long cpsr) +{ + unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ + return temp & PSR_N_BIT; +} + +static unsigned long __kprobes __check_al(unsigned long cpsr) +{ + return true; +} + +kprobe_check_cc * const kprobe_condition_checks[16] = { + &__check_eq, &__check_ne, &__check_cs, &__check_cc, + &__check_mi, &__check_pl, &__check_vs, &__check_vc, + &__check_hi, &__check_ls, &__check_ge, &__check_lt, + &__check_gt, &__check_le, &__check_al, &__check_al +}; diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 87a5241b2f18..792f2316227a 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -34,4 +34,6 @@ enum kprobe_insn arm_kprobe_decode_insn(kprobe_opcode_t, void __init arm_kprobe_decode_init(void); +extern kprobe_check_cc * const kprobe_condition_checks[16]; + #endif /* _ARM_KERNEL_KPROBES_H */ -- cgit v1.2.3 From 1b59d874660be7f790861ad849858cc009089515 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 6 Jul 2011 20:33:41 +0100 Subject: ARM: kprobes: Move is_writeback define to header file. This will be used later in other files. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 6 ------ arch/arm/kernel/kprobes.h | 6 ++++++ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 8d4464f9471b..3c4678edcbf8 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -69,12 +69,6 @@ #define is_r15(insn, bitpos) (((insn) & (0xf << bitpos)) == (0xf << bitpos)) -/* - * Test if load/store instructions writeback the address register. - * if P (bit 24) == 0 or W (bit 21) == 1 - */ -#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000) - #define PSR_fs (PSR_f|PSR_s) #define KPROBE_RETURN_INSTRUCTION 0xe1a0f00e /* mov pc, lr */ diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 792f2316227a..4de2f37b1a85 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -36,4 +36,10 @@ void __init arm_kprobe_decode_init(void); extern kprobe_check_cc * const kprobe_condition_checks[16]; +/* + * Test if load/store instructions writeback the address register. + * if P (bit 24) == 0 or W (bit 21) == 1 + */ +#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000) + #endif /* _ARM_KERNEL_KPROBES_H */ -- cgit v1.2.3 From 6c8df3300f60cae54aeb2a6dda8efe7ffe16a322 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 7 Jul 2011 10:21:40 +0100 Subject: ARM: kprobes: Move find_str_pc_offset into kprobes-common.c Move str_pc_offset into kprobes-common.c as it will be needed by common code later. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 28 ---------------------------- arch/arm/kernel/kprobes-common.c | 33 +++++++++++++++++++++++++++++++++ arch/arm/kernel/kprobes.h | 2 ++ 3 files changed, 35 insertions(+), 28 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 3c4678edcbf8..0262b29163d1 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -91,29 +91,6 @@ union reg_pair { #endif }; -/* - * For STR and STM instructions, an ARM core may choose to use either - * a +8 or a +12 displacement from the current instruction's address. - * Whichever value is chosen for a given core, it must be the same for - * both instructions and may not change. This function measures it. - */ - -static int str_pc_offset; - -static void __init find_str_pc_offset(void) -{ - int addr, scratch, ret; - - __asm__ ( - "sub %[ret], pc, #4 \n\t" - "str pc, %[addr] \n\t" - "ldr %[scr], %[addr] \n\t" - "sub %[ret], %[scr], %[ret] \n\t" - : [ret] "=r" (ret), [scr] "=r" (scratch), [addr] "+m" (addr)); - - str_pc_offset = ret; -} - /* * The insnslot_?arg_r[w]flags() functions below are to keep the * msr -> *fn -> mrs instruction sequences indivisible so that @@ -1569,8 +1546,3 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) return space_cccc_11xx(insn, asi); } - -void __init arm_kprobe_decode_init(void) -{ - find_str_pc_offset(); -} diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 794827ec27d7..e18576cca6cf 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -3,6 +3,9 @@ * * Copyright (C) 2011 Jon Medhurst . * + * Some contents moved here from arch/arm/include/asm/kprobes-arm.c which is + * Copyright (C) 2006, 2007 Motorola Inc. + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -14,6 +17,36 @@ #include "kprobes.h" +/* + * For STR and STM instructions, an ARM core may choose to use either + * a +8 or a +12 displacement from the current instruction's address. + * Whichever value is chosen for a given core, it must be the same for + * both instructions and may not change. This function measures it. + */ + +int str_pc_offset; + +void __init find_str_pc_offset(void) +{ + int addr, scratch, ret; + + __asm__ ( + "sub %[ret], pc, #4 \n\t" + "str pc, %[addr] \n\t" + "ldr %[scr], %[addr] \n\t" + "sub %[ret], %[scr], %[ret] \n\t" + : [ret] "=r" (ret), [scr] "=r" (scratch), [addr] "+m" (addr)); + + str_pc_offset = ret; +} + + +void __init arm_kprobe_decode_init(void) +{ + find_str_pc_offset(); +} + + static unsigned long __kprobes __check_eq(unsigned long cpsr) { return cpsr & PSR_Z_BIT; diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 4de2f37b1a85..43f630d7f03d 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -36,6 +36,8 @@ void __init arm_kprobe_decode_init(void); extern kprobe_check_cc * const kprobe_condition_checks[16]; +extern int str_pc_offset; + /* * Test if load/store instructions writeback the address register. * if P (bit 24) == 0 or W (bit 21) == 1 -- cgit v1.2.3 From aea490299f7f0412f884a4895bc96211d8d8dbaf Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 7 Jul 2011 19:58:29 +0100 Subject: ARM: kprobes: Make str_pc_offset a constant on ARMv7 The str_pc_offset value is architecturally defined on ARMv7 onwards so we can make it a compile time constant. This means on Thumb kernels the runtime checking code isn't needed, which saves us from having to fix it to work for Thumb. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-common.c | 4 ++++ arch/arm/kernel/kprobes.h | 14 ++++++++++++++ 2 files changed, 18 insertions(+) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index e18576cca6cf..87e91ce4d495 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -17,6 +17,8 @@ #include "kprobes.h" +#ifndef find_str_pc_offset + /* * For STR and STM instructions, an ARM core may choose to use either * a +8 or a +12 displacement from the current instruction's address. @@ -40,6 +42,8 @@ void __init find_str_pc_offset(void) str_pc_offset = ret; } +#endif /* !find_str_pc_offset */ + void __init arm_kprobe_decode_init(void) { diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 43f630d7f03d..406bb2da7fea 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -36,7 +36,21 @@ void __init arm_kprobe_decode_init(void); extern kprobe_check_cc * const kprobe_condition_checks[16]; + +#if __LINUX_ARM_ARCH__ >= 7 + +/* str_pc_offset is architecturally defined from ARMv7 onwards */ +#define str_pc_offset 8 +#define find_str_pc_offset() + +#else /* __LINUX_ARM_ARCH__ < 7 */ + +/* We need a run-time check to determine str_pc_offset */ extern int str_pc_offset; +void __init find_str_pc_offset(void); + +#endif + /* * Test if load/store instructions writeback the address register. -- cgit v1.2.3 From de41984003ed2315dbb7d58168cc3e72e15b075c Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 14 Jun 2011 13:08:04 +0100 Subject: ARM: kprobes: Make kprobes framework work on Thumb-2 kernels Fix up kprobes framework so that it builds and correctly interworks on Thumb-2 kernels. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes.c | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 3ba5f8d0d82c..0e47d3d67427 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -302,7 +302,11 @@ void __naked __kprobes kretprobe_trampoline(void) "bl trampoline_handler \n\t" "mov lr, r0 \n\t" "ldmia sp!, {r0 - r11} \n\t" +#ifdef CONFIG_THUMB2_KERNEL + "bx lr \n\t" +#else "mov pc, lr \n\t" +#endif : : : "memory"); } @@ -380,11 +384,22 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) struct jprobe *jp = container_of(p, struct jprobe, kp); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); long sp_addr = regs->ARM_sp; + long cpsr; kcb->jprobe_saved_regs = *regs; memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr)); regs->ARM_pc = (long)jp->entry; - regs->ARM_cpsr |= PSR_I_BIT; + + cpsr = regs->ARM_cpsr | PSR_I_BIT; +#ifdef CONFIG_THUMB2_KERNEL + /* Set correct Thumb state in cpsr */ + if (regs->ARM_pc & 1) + cpsr |= PSR_T_BIT; + else + cpsr &= ~PSR_T_BIT; +#endif + regs->ARM_cpsr = cpsr; + preempt_disable(); return 1; } @@ -406,7 +421,12 @@ void __kprobes jprobe_return(void) * This is to prevent any simulated instruction from writing * over the regs when they are accessing the stack. */ +#ifdef CONFIG_THUMB2_KERNEL + "sub r0, %0, %1 \n\t" + "mov sp, r0 \n\t" +#else "sub sp, %0, %1 \n\t" +#endif "ldr r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t" "str %0, [sp, %2] \n\t" "str r0, [sp, %3] \n\t" @@ -417,15 +437,28 @@ void __kprobes jprobe_return(void) * Return to the context saved by setjmp_pre_handler * and restored by longjmp_break_handler. */ +#ifdef CONFIG_THUMB2_KERNEL + "ldr lr, [sp, %2] \n\t" /* lr = saved sp */ + "ldrd r0, r1, [sp, %5] \n\t" /* r0,r1 = saved lr,pc */ + "ldr r2, [sp, %4] \n\t" /* r2 = saved psr */ + "stmdb lr!, {r0, r1, r2} \n\t" /* push saved lr and */ + /* rfe context */ + "ldmia sp, {r0 - r12} \n\t" + "mov sp, lr \n\t" + "ldr lr, [sp], #4 \n\t" + "rfeia sp! \n\t" +#else "ldr r0, [sp, %4] \n\t" "msr cpsr_cxsf, r0 \n\t" "ldmia sp, {r0 - pc} \n\t" +#endif : : "r" (kcb->jprobe_saved_regs.ARM_sp), "I" (sizeof(struct pt_regs) * 2), "J" (offsetof(struct pt_regs, ARM_sp)), "J" (offsetof(struct pt_regs, ARM_pc)), - "J" (offsetof(struct pt_regs, ARM_cpsr)) + "J" (offsetof(struct pt_regs, ARM_cpsr)), + "J" (offsetof(struct pt_regs, ARM_lr)) : "memory", "cc"); } -- cgit v1.2.3 From 2437170710c4a3dee137a65623960aa7ac82a32e Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 19 Apr 2011 17:56:58 +0100 Subject: ARM: kprobes: Add Thumb instruction decoding stubs Extend arch_prepare_kprobe to support probing of Thumb code. For the actual decoding of Thumb instructions, stub functions are added which currently just reject the probe. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/Makefile | 4 ++++ arch/arm/kernel/kprobes-thumb.c | 26 ++++++++++++++++++++++++++ arch/arm/kernel/kprobes.c | 20 ++++++++++++++++++-- arch/arm/kernel/kprobes.h | 13 +++++++++++++ 4 files changed, 61 insertions(+), 2 deletions(-) create mode 100644 arch/arm/kernel/kprobes-thumb.c diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index a22b8f1c7b14..f7887dc53c1f 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -38,7 +38,11 @@ obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_KPROBES) += kprobes.o kprobes-common.o +ifdef CONFIG_THUMB2_KERNEL +obj-$(CONFIG_KPROBES) += kprobes-thumb.o +else obj-$(CONFIG_KPROBES) += kprobes-arm.o +endif obj-$(CONFIG_ATAGS_PROC) += atags.o obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o obj-$(CONFIG_ARM_THUMBEE) += thumbee.o diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c new file mode 100644 index 000000000000..ac6b2d138ee5 --- /dev/null +++ b/arch/arm/kernel/kprobes-thumb.c @@ -0,0 +1,26 @@ +/* + * arch/arm/kernel/kprobes-thumb.c + * + * Copyright (C) 2011 Jon Medhurst . + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +#include "kprobes.h" + +enum kprobe_insn __kprobes +thumb16_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + return INSN_REJECTED; +} + +enum kprobe_insn __kprobes +thumb32_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + return INSN_REJECTED; +} diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 0e47d3d67427..0df2d6d57c04 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -51,16 +51,32 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) kprobe_opcode_t insn; kprobe_opcode_t tmp_insn[MAX_INSN_SIZE]; unsigned long addr = (unsigned long)p->addr; + kprobe_decode_insn_t *decode_insn; int is; - if (addr & 0x3 || in_exception_text(addr)) + if (in_exception_text(addr)) return -EINVAL; +#ifdef CONFIG_THUMB2_KERNEL + addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */ + insn = ((u16 *)addr)[0]; + if (is_wide_instruction(insn)) { + insn <<= 16; + insn |= ((u16 *)addr)[1]; + decode_insn = thumb32_kprobe_decode_insn; + } else + decode_insn = thumb16_kprobe_decode_insn; +#else /* !CONFIG_THUMB2_KERNEL */ + if (addr & 0x3) + return -EINVAL; insn = *p->addr; + decode_insn = arm_kprobe_decode_insn; +#endif + p->opcode = insn; p->ainsn.insn = tmp_insn; - switch (arm_kprobe_decode_insn(insn, &p->ainsn)) { + switch ((*decode_insn)(insn, &p->ainsn)) { case INSN_REJECTED: /* not supported */ return -EINVAL; diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 406bb2da7fea..86abfabe83f2 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -29,8 +29,21 @@ enum kprobe_insn { INSN_GOOD_NO_SLOT }; +typedef enum kprobe_insn (kprobe_decode_insn_t)(kprobe_opcode_t, + struct arch_specific_insn *); + +#ifdef CONFIG_THUMB2_KERNEL + +enum kprobe_insn thumb16_kprobe_decode_insn(kprobe_opcode_t, + struct arch_specific_insn *); +enum kprobe_insn thumb32_kprobe_decode_insn(kprobe_opcode_t, + struct arch_specific_insn *); + +#else /* !CONFIG_THUMB2_KERNEL */ + enum kprobe_insn arm_kprobe_decode_insn(kprobe_opcode_t, struct arch_specific_insn *); +#endif void __init arm_kprobe_decode_init(void); -- cgit v1.2.3 From 856bc356394a28edb8c388e31212f6ceb0a04ce6 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 14 Jun 2011 13:09:39 +0100 Subject: ARM: Kconfig: Allow kprobes on Thumb-2 kernels Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9adc278a22ab..68b456129bef 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -10,7 +10,7 @@ config ARM select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI) select HAVE_OPROFILE if (HAVE_PERF_EVENTS) select HAVE_ARCH_KGDB - select HAVE_KPROBES if (!XIP_KERNEL && !THUMB2_KERNEL) + select HAVE_KPROBES if !XIP_KERNEL select HAVE_KRETPROBES if (HAVE_KPROBES) select HAVE_FUNCTION_TRACER if (!XIP_KERNEL) select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL) -- cgit v1.2.3 From aceb487ab2ea0dca43f5131e456f45bc9f8c1bed Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 19 Apr 2011 17:18:35 +0100 Subject: ARM: kprobes: Add Thumb breakpoint support Extend the breakpoint insertion and catching functions to support Thumb code. As breakpoints are no longer of a fixed size, the flush_insns macro is modified to take a size argument instead of an instruction count. Note, we need both 16- and 32-bit Thumb breakpoints, because if we were to use a 16-bit breakpoint to replace a 32-bit instruction which was in an IT block, and the condition check failed, then the breakpoint may not fire (it's unpredictable behaviour) and the CPU could then try and execute the second half of the 32-bit Thumb instruction. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes.c | 122 +++++++++++++++++++++++++++++++++++++++++----- arch/arm/kernel/kprobes.h | 7 ++- 2 files changed, 115 insertions(+), 14 deletions(-) diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 0df2d6d57c04..a9050bad4434 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -34,10 +34,10 @@ min((unsigned long)MAX_STACK_SIZE, \ (unsigned long)current_thread_info() + THREAD_START_SP - (addr)) -#define flush_insns(addr, cnt) \ +#define flush_insns(addr, size) \ flush_icache_range((unsigned long)(addr), \ (unsigned long)(addr) + \ - sizeof(kprobe_opcode_t) * (cnt)) + (size)) /* Used as a marker in ARM_pc to note when we're in a jprobe. */ #define JPROBE_MAGIC_ADDR 0xffffffff @@ -86,7 +86,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return -ENOMEM; for (is = 0; is < MAX_INSN_SIZE; ++is) p->ainsn.insn[is] = tmp_insn[is]; - flush_insns(p->ainsn.insn, MAX_INSN_SIZE); + flush_insns(p->ainsn.insn, + sizeof(p->ainsn.insn[0]) * MAX_INSN_SIZE); break; case INSN_GOOD_NO_SLOT: /* instruction doesn't need insn slot */ @@ -97,24 +98,82 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return 0; } +#ifdef CONFIG_THUMB2_KERNEL + +/* + * For a 32-bit Thumb breakpoint spanning two memory words we need to take + * special precautions to insert the breakpoint atomically, especially on SMP + * systems. This is achieved by calling this arming function using stop_machine. + */ +static int __kprobes set_t32_breakpoint(void *addr) +{ + ((u16 *)addr)[0] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION >> 16; + ((u16 *)addr)[1] = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION & 0xffff; + flush_insns(addr, 2*sizeof(u16)); + return 0; +} + void __kprobes arch_arm_kprobe(struct kprobe *p) { - *p->addr = KPROBE_BREAKPOINT_INSTRUCTION; - flush_insns(p->addr, 1); + uintptr_t addr = (uintptr_t)p->addr & ~1; /* Remove any Thumb flag */ + + if (!is_wide_instruction(p->opcode)) { + *(u16 *)addr = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION; + flush_insns(addr, sizeof(u16)); + } else if (addr & 2) { + /* A 32-bit instruction spanning two words needs special care */ + stop_machine(set_t32_breakpoint, (void *)addr, &cpu_online_map); + } else { + /* Word aligned 32-bit instruction can be written atomically */ + u32 bkp = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION; +#ifndef __ARMEB__ /* Swap halfwords for little-endian */ + bkp = (bkp >> 16) | (bkp << 16); +#endif + *(u32 *)addr = bkp; + flush_insns(addr, sizeof(u32)); + } } +#else /* !CONFIG_THUMB2_KERNEL */ + +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + *p->addr = KPROBE_ARM_BREAKPOINT_INSTRUCTION; + flush_insns(p->addr, sizeof(p->addr[0])); +} + +#endif /* !CONFIG_THUMB2_KERNEL */ + /* * The actual disarming is done here on each CPU and synchronized using * stop_machine. This synchronization is necessary on SMP to avoid removing * a probe between the moment the 'Undefined Instruction' exception is raised * and the moment the exception handler reads the faulting instruction from - * memory. + * memory. It is also needed to atomically set the two half-words of a 32-bit + * Thumb breakpoint. */ int __kprobes __arch_disarm_kprobe(void *p) { struct kprobe *kp = p; +#ifdef CONFIG_THUMB2_KERNEL + u16 *addr = (u16 *)((uintptr_t)kp->addr & ~1); + kprobe_opcode_t insn = kp->opcode; + unsigned int len; + + if (is_wide_instruction(insn)) { + ((u16 *)addr)[0] = insn>>16; + ((u16 *)addr)[1] = insn; + len = 2*sizeof(u16); + } else { + ((u16 *)addr)[0] = insn; + len = sizeof(u16); + } + flush_insns(addr, len); + +#else /* !CONFIG_THUMB2_KERNEL */ *kp->addr = kp->opcode; - flush_insns(kp->addr, 1); + flush_insns(kp->addr, sizeof(kp->addr[0])); +#endif return 0; } @@ -167,11 +226,23 @@ void __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p, *cur; struct kprobe_ctlblk *kcb; - kprobe_opcode_t *addr = (kprobe_opcode_t *)regs->ARM_pc; kcb = get_kprobe_ctlblk(); cur = kprobe_running(); - p = get_kprobe(addr); + +#ifdef CONFIG_THUMB2_KERNEL + /* + * First look for a probe which was registered using an address with + * bit 0 set, this is the usual situation for pointers to Thumb code. + * If not found, fallback to looking for one with bit 0 clear. + */ + p = get_kprobe((kprobe_opcode_t *)(regs->ARM_pc | 1)); + if (!p) + p = get_kprobe((kprobe_opcode_t *)regs->ARM_pc); + +#else /* ! CONFIG_THUMB2_KERNEL */ + p = get_kprobe((kprobe_opcode_t *)regs->ARM_pc); +#endif if (p) { if (cur) { @@ -511,17 +582,44 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) return 0; } -static struct undef_hook kprobes_break_hook = { +#ifdef CONFIG_THUMB2_KERNEL + +static struct undef_hook kprobes_thumb16_break_hook = { + .instr_mask = 0xffff, + .instr_val = KPROBE_THUMB16_BREAKPOINT_INSTRUCTION, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = kprobe_trap_handler, +}; + +static struct undef_hook kprobes_thumb32_break_hook = { + .instr_mask = 0xffffffff, + .instr_val = KPROBE_THUMB32_BREAKPOINT_INSTRUCTION, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = kprobe_trap_handler, +}; + +#else /* !CONFIG_THUMB2_KERNEL */ + +static struct undef_hook kprobes_arm_break_hook = { .instr_mask = 0xffffffff, - .instr_val = KPROBE_BREAKPOINT_INSTRUCTION, + .instr_val = KPROBE_ARM_BREAKPOINT_INSTRUCTION, .cpsr_mask = MODE_MASK, .cpsr_val = SVC_MODE, .fn = kprobe_trap_handler, }; +#endif /* !CONFIG_THUMB2_KERNEL */ + int __init arch_init_kprobes() { arm_kprobe_decode_init(); - register_undef_hook(&kprobes_break_hook); +#ifdef CONFIG_THUMB2_KERNEL + register_undef_hook(&kprobes_thumb16_break_hook); + register_undef_hook(&kprobes_thumb32_break_hook); +#else + register_undef_hook(&kprobes_arm_break_hook); +#endif return 0; } diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 86abfabe83f2..a84b14d8cdc8 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -18,10 +18,13 @@ #define _ARM_KERNEL_KPROBES_H /* - * This undefined instruction must be unique and + * These undefined instructions must be unique and * reserved solely for kprobes' use. */ -#define KPROBE_BREAKPOINT_INSTRUCTION 0xe7f001f8 +#define KPROBE_ARM_BREAKPOINT_INSTRUCTION 0xe7f001f8 +#define KPROBE_THUMB16_BREAKPOINT_INSTRUCTION 0xde18 +#define KPROBE_THUMB32_BREAKPOINT_INSTRUCTION 0xf7f0a018 + enum kprobe_insn { INSN_REJECTED, -- cgit v1.2.3 From eaf4f33feca2704ad1d06f1ef6b427712c506cc0 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 20 Apr 2011 19:29:52 +0100 Subject: ARM: kprobes: Add condition code checking to Thumb emulation Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index ac6b2d138ee5..24a188b1601a 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -13,14 +13,36 @@ #include "kprobes.h" + +/* + * True if current instruction is in an IT block. + */ +#define in_it_block(cpsr) ((cpsr & 0x06000c00) != 0x00000000) + +/* + * Return the condition code to check for the currently executing instruction. + * This is in ITSTATE<7:4> which is in CPSR<15:12> but is only valid if + * in_it_block returns true. + */ +#define current_cond(cpsr) ((cpsr >> 12) & 0xf) + +static unsigned long __kprobes thumb_check_cc(unsigned long cpsr) +{ + if (unlikely(in_it_block(cpsr))) + return kprobe_condition_checks[current_cond(cpsr)](cpsr); + return true; +} + enum kprobe_insn __kprobes thumb16_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { + asi->insn_check_cc = thumb_check_cc; return INSN_REJECTED; } enum kprobe_insn __kprobes thumb32_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { + asi->insn_check_cc = thumb_check_cc; return INSN_REJECTED; } -- cgit v1.2.3 From 6aaa8b5570c7b5b9eb8913ec80263a1012b1dd66 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 16 Jun 2011 14:53:56 +0100 Subject: ARM: kprobes: Add it_advance() This advances the ITSTATE bits in CPSR to their values for the next instruction. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index a84b14d8cdc8..5e2485c4cacd 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -68,6 +68,31 @@ void __init find_str_pc_offset(void); #endif +/* + * Update ITSTATE after normal execution of an IT block instruction. + * + * The 8 IT state bits are split into two parts in CPSR: + * ITSTATE<1:0> are in CPSR<26:25> + * ITSTATE<7:2> are in CPSR<15:10> + */ +static inline unsigned long it_advance(unsigned long cpsr) + { + if ((cpsr & 0x06000400) == 0) { + /* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */ + cpsr &= ~PSR_IT_MASK; + } else { + /* We need to shift left ITSTATE<4:0> */ + const unsigned long mask = 0x06001c00; /* Mask ITSTATE<4:0> */ + unsigned long it = cpsr & mask; + it <<= 1; + it |= it >> (27 - 10); /* Carry ITSTATE<2> to correct place */ + it &= mask; + cpsr &= ~mask; + cpsr |= it; + } + return cpsr; +} + /* * Test if load/store instructions writeback the address register. * if P (bit 24) == 0 or W (bit 21) == 1 -- cgit v1.2.3 From 3cca6c243568d355c1ccecaaa71bf490f014d729 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 16 Jun 2011 15:54:00 +0100 Subject: ARM: kprobes: Don't trigger probes on conditional instructions when condition is false This patch changes the behavior of kprobes on ARM so that: Kprobes on conditional instructions don't trigger when the condition is false. For conditional branches, this means that they don't trigger in the branch not taken case. Rationale: When probes are placed onto conditionally executed instructions in a Thumb IT block, they may not fire if the condition is not met. This is because we use invalid instructions for breakpoints and "it is IMPLEMENTATION DEFINED whether the instruction executes as a NOP or causes an Undefined Instruction exception". Therefore, for consistency, we will ignore all probes on any conditional instructions when the condition is false. Alternative solutions seem to be too complex to implement or inconsistent. This issue was discussed on linux.arm.kernel in the thread titled "[RFC] kprobes with thumb2 conditional code" See http://comments.gmane.org/gmane.linux.linaro.devel/2985 Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index a9050bad4434..b6e9a1cc1c55 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -207,6 +207,20 @@ static void __kprobes set_current_kprobe(struct kprobe *p) __get_cpu_var(current_kprobe) = p; } +static void __kprobes +singlestep_skip(struct kprobe *p, struct pt_regs *regs) +{ +#ifdef CONFIG_THUMB2_KERNEL + regs->ARM_cpsr = it_advance(regs->ARM_cpsr); + if (is_wide_instruction(p->opcode)) + regs->ARM_pc += 4; + else + regs->ARM_pc += 2; +#else + regs->ARM_pc += 4; +#endif +} + static void __kprobes singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { @@ -262,7 +276,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs) /* impossible cases */ BUG(); } - } else { + } else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) { + /* Probe hit and conditional execution check ok. */ set_current_kprobe(p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; @@ -282,6 +297,13 @@ void __kprobes kprobe_handler(struct pt_regs *regs) } reset_current_kprobe(); } + } else { + /* + * Probe hit but conditional execution check failed, + * so just skip the instruction and continue as if + * nothing had happened. + */ + singlestep_skip(p, regs); } } else if (cur) { /* We probably hit a jprobe. Call its break handler. */ -- cgit v1.2.3 From 3b26945597d5eff5d428a268c9d109338fce801e Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 16 Jun 2011 17:22:37 +0100 Subject: ARM: kprobes: Use conditional breakpoints for ARM probes Now we no longer trigger probes on conditional instructions when the condition is false, we can make use of conditional instructions as breakpoints in ARM code to avoid taking unnecessary exceptions. Note, we can't rely on not getting an exception when the condition check fails, as that is Implementation Defined on newer ARM architectures. We therefore still need to perform manual condition checks as well. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes.c | 10 ++++++++-- arch/arm/kernel/kprobes.h | 2 +- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index b6e9a1cc1c55..0003dfd3b854 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -138,7 +138,13 @@ void __kprobes arch_arm_kprobe(struct kprobe *p) void __kprobes arch_arm_kprobe(struct kprobe *p) { - *p->addr = KPROBE_ARM_BREAKPOINT_INSTRUCTION; + kprobe_opcode_t insn = p->opcode; + kprobe_opcode_t brkp = KPROBE_ARM_BREAKPOINT_INSTRUCTION; + if (insn >= 0xe0000000) + brkp |= 0xe0000000; /* Unconditional instruction */ + else + brkp |= insn & 0xf0000000; /* Copy condition from insn */ + *p->addr = brkp; flush_insns(p->addr, sizeof(p->addr[0])); } @@ -625,7 +631,7 @@ static struct undef_hook kprobes_thumb32_break_hook = { #else /* !CONFIG_THUMB2_KERNEL */ static struct undef_hook kprobes_arm_break_hook = { - .instr_mask = 0xffffffff, + .instr_mask = 0x0fffffff, .instr_val = KPROBE_ARM_BREAKPOINT_INSTRUCTION, .cpsr_mask = MODE_MASK, .cpsr_val = SVC_MODE, diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 5e2485c4cacd..e3803c65c4be 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -21,7 +21,7 @@ * These undefined instructions must be unique and * reserved solely for kprobes' use. */ -#define KPROBE_ARM_BREAKPOINT_INSTRUCTION 0xe7f001f8 +#define KPROBE_ARM_BREAKPOINT_INSTRUCTION 0x07f001f8 #define KPROBE_THUMB16_BREAKPOINT_INSTRUCTION 0xde18 #define KPROBE_THUMB32_BREAKPOINT_INSTRUCTION 0xf7f0a018 -- cgit v1.2.3 From c6a7d97d57ef41477a85f4c0f48ea5243132ee1f Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 12:11:27 +0100 Subject: ARM: kprobes: Add hooks to override singlestep() When a probe fires we must single-step the instruction which was replaced by a breakpoint. As the steps to do this vary between ARM and Thumb instructions we need a way to customise single-stepping. This is done by adding a new hook called insn_singlestep to arch_specific_insn which is initialised by the instruction decoding functions. These single-step hooks must update PC and call the instruction handler. For Thumb instructions an additional step of updating ITSTATE is needed. We do this after calling the handler because some handlers will need to test if they are running in an IT block. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/include/asm/kprobes.h | 9 +++++---- arch/arm/kernel/kprobes-arm.c | 7 +++++++ arch/arm/kernel/kprobes-thumb.c | 16 ++++++++++++++++ arch/arm/kernel/kprobes.c | 8 +++----- 4 files changed, 31 insertions(+), 9 deletions(-) diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 57d37d52d71e..1e9ff56d40c7 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -32,14 +32,15 @@ typedef u32 kprobe_opcode_t; struct kprobe; typedef void (kprobe_insn_handler_t)(struct kprobe *, struct pt_regs *); - typedef unsigned long (kprobe_check_cc)(unsigned long); +typedef void (kprobe_insn_singlestep_t)(struct kprobe *, struct pt_regs *); /* Architecture specific copy of original instruction. */ struct arch_specific_insn { - kprobe_opcode_t *insn; - kprobe_insn_handler_t *insn_handler; - kprobe_check_cc *insn_check_cc; + kprobe_opcode_t *insn; + kprobe_insn_handler_t *insn_handler; + kprobe_check_cc *insn_check_cc; + kprobe_insn_singlestep_t *insn_singlestep; }; struct prev_kprobe { diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 0262b29163d1..a1143e86a09a 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1494,6 +1494,12 @@ space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) return INSN_REJECTED; } +static void __kprobes arm_singlestep(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_pc += 4; + p->ainsn.insn_handler(p, regs); +} + /* Return: * INSN_REJECTED If instruction is one not allowed to kprobe, * INSN_GOOD If instruction is supported and uses instruction slot, @@ -1509,6 +1515,7 @@ space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) enum kprobe_insn __kprobes arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { + asi->insn_singlestep = arm_singlestep; asi->insn_check_cc = kprobe_condition_checks[insn>>28]; asi->insn[1] = KPROBE_RETURN_INSTRUCTION; diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 24a188b1601a..973c3eb1243a 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -33,9 +33,24 @@ static unsigned long __kprobes thumb_check_cc(unsigned long cpsr) return true; } +static void __kprobes thumb16_singlestep(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_pc += 2; + p->ainsn.insn_handler(p, regs); + regs->ARM_cpsr = it_advance(regs->ARM_cpsr); +} + +static void __kprobes thumb32_singlestep(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_pc += 4; + p->ainsn.insn_handler(p, regs); + regs->ARM_cpsr = it_advance(regs->ARM_cpsr); +} + enum kprobe_insn __kprobes thumb16_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { + asi->insn_singlestep = thumb16_singlestep; asi->insn_check_cc = thumb_check_cc; return INSN_REJECTED; } @@ -43,6 +58,7 @@ thumb16_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) enum kprobe_insn __kprobes thumb32_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { + asi->insn_singlestep = thumb32_singlestep; asi->insn_check_cc = thumb_check_cc; return INSN_REJECTED; } diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 0003dfd3b854..77b7c6974802 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -227,12 +227,10 @@ singlestep_skip(struct kprobe *p, struct pt_regs *regs) #endif } -static void __kprobes singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static inline void __kprobes +singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - regs->ARM_pc += 4; - if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) - p->ainsn.insn_handler(p, regs); + p->ainsn.insn_singlestep(p, regs); } /* -- cgit v1.2.3 From e2960317d4581689bf80dbad4d75e7a59f11a3f7 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 14:05:51 +0100 Subject: ARM: kprobes: Extend arch_specific_insn to add pointer to emulated instruction When we come to emulating Thumb instructions then, to interwork correctly, the code on in the instruction slot must be invoked with a function pointer which has the least significant bit set. Rather that set this by hand in every Thumb emulation function we will add a new field for this purpose to arch_specific_insn, called insn_fn. This also enables us to seamlessly share emulation functions between ARM and Thumb code. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/include/asm/kprobes.h | 2 ++ arch/arm/kernel/kprobes.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 1e9ff56d40c7..feec86768f9c 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -34,6 +34,7 @@ struct kprobe; typedef void (kprobe_insn_handler_t)(struct kprobe *, struct pt_regs *); typedef unsigned long (kprobe_check_cc)(unsigned long); typedef void (kprobe_insn_singlestep_t)(struct kprobe *, struct pt_regs *); +typedef void (kprobe_insn_fn_t)(void); /* Architecture specific copy of original instruction. */ struct arch_specific_insn { @@ -41,6 +42,7 @@ struct arch_specific_insn { kprobe_insn_handler_t *insn_handler; kprobe_check_cc *insn_check_cc; kprobe_insn_singlestep_t *insn_singlestep; + kprobe_insn_fn_t *insn_fn; }; struct prev_kprobe { diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 77b7c6974802..129c1163248b 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -51,6 +51,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) kprobe_opcode_t insn; kprobe_opcode_t tmp_insn[MAX_INSN_SIZE]; unsigned long addr = (unsigned long)p->addr; + bool thumb; kprobe_decode_insn_t *decode_insn; int is; @@ -58,6 +59,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return -EINVAL; #ifdef CONFIG_THUMB2_KERNEL + thumb = true; addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */ insn = ((u16 *)addr)[0]; if (is_wide_instruction(insn)) { @@ -67,6 +69,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) } else decode_insn = thumb16_kprobe_decode_insn; #else /* !CONFIG_THUMB2_KERNEL */ + thumb = false; if (addr & 0x3) return -EINVAL; insn = *p->addr; @@ -88,6 +91,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) p->ainsn.insn[is] = tmp_insn[is]; flush_insns(p->ainsn.insn, sizeof(p->ainsn.insn[0]) * MAX_INSN_SIZE); + p->ainsn.insn_fn = (kprobe_insn_fn_t *) + ((uintptr_t)p->ainsn.insn | thumb); break; case INSN_GOOD_NO_SLOT: /* instruction doesn't need insn slot */ -- cgit v1.2.3 From 0d1a095aa1e6e2a233bfb1729e15233e77f69d54 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 26 Apr 2011 15:15:56 +0100 Subject: ARM: kprobes: Infrastructure for table driven decoding of CPU instructions The existing ARM instruction decoding functions are a mass of if/else code. Rather than follow this pattern for Thumb instruction decoding this patch implements an infrastructure for a new table driven scheme. This has several advantages: - Reduces the kernel size by approx 2kB. (The ARM instruction decoding will eventually have -3.1kB code, +1.3kB data; with similar or better estimated savings for Thumb decoding.) - Allows programmatic checking of decoding consistency and test case coverage. - Provides more uniform source code and is therefore, arguably, clearer. For a detailed explanation of how decoding tables work see the in-source documentation in kprobes.h, and also for kprobe_decode_insn(). Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-common.c | 258 +++++++++++++++++++++++++++++++++++++++ arch/arm/kernel/kprobes.h | 248 ++++++++++++++++++++++++++++++++++++- 2 files changed, 505 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 87e91ce4d495..1cb6a82a5e24 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -140,3 +140,261 @@ kprobe_check_cc * const kprobe_condition_checks[16] = { &__check_hi, &__check_ls, &__check_ge, &__check_lt, &__check_gt, &__check_le, &__check_al, &__check_al }; + + +/* + * Prepare an instruction slot to receive an instruction for emulating. + * This is done by placing a subroutine return after the location where the + * instruction will be placed. We also modify ARM instructions to be + * unconditional as the condition code will already be checked before any + * emulation handler is called. + */ +static kprobe_opcode_t __kprobes +prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, + bool thumb) +{ +#ifdef CONFIG_THUMB2_KERNEL + if (thumb) { + u16 *thumb_insn = (u16 *)asi->insn; + thumb_insn[1] = 0x4770; /* Thumb bx lr */ + thumb_insn[2] = 0x4770; /* Thumb bx lr */ + return insn; + } + asi->insn[1] = 0xe12fff1e; /* ARM bx lr */ +#else + asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */ +#endif + /* Make an ARM instruction unconditional */ + if (insn < 0xe0000000) + insn = (insn | 0xe0000000) & ~0x10000000; + return insn; +} + +/* + * Write a (probably modified) instruction into the slot previously prepared by + * prepare_emulated_insn + */ +static void __kprobes +set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, + bool thumb) +{ +#ifdef CONFIG_THUMB2_KERNEL + if (thumb) { + u16 *ip = (u16 *)asi->insn; + if (is_wide_instruction(insn)) + *ip++ = insn >> 16; + *ip++ = insn; + return; + } +#endif + asi->insn[0] = insn; +} + +/* + * When we modify the register numbers encoded in an instruction to be emulated, + * the new values come from this define. For ARM and 32-bit Thumb instructions + * this gives... + * + * bit position 16 12 8 4 0 + * ---------------+---+---+---+---+---+ + * register r2 r0 r1 -- r3 + */ +#define INSN_NEW_BITS 0x00020103 + +/* Each nibble has same value as that at INSN_NEW_BITS bit 16 */ +#define INSN_SAMEAS16_BITS 0x22222222 + +/* + * Validate and modify each of the registers encoded in an instruction. + * + * Each nibble in regs contains a value from enum decode_reg_type. For each + * non-zero value, the corresponding nibble in pinsn is validated and modified + * according to the type. + */ +static bool __kprobes decode_regs(kprobe_opcode_t* pinsn, u32 regs) +{ + kprobe_opcode_t insn = *pinsn; + kprobe_opcode_t mask = 0xf; /* Start at least significant nibble */ + + for (; regs != 0; regs >>= 4, mask <<= 4) { + + kprobe_opcode_t new_bits = INSN_NEW_BITS; + + switch (regs & 0xf) { + + case REG_TYPE_NONE: + /* Nibble not a register, skip to next */ + continue; + + case REG_TYPE_ANY: + /* Any register is allowed */ + break; + + case REG_TYPE_SAMEAS16: + /* Replace register with same as at bit position 16 */ + new_bits = INSN_SAMEAS16_BITS; + break; + + case REG_TYPE_SP: + /* Only allow SP (R13) */ + if ((insn ^ 0xdddddddd) & mask) + goto reject; + break; + + case REG_TYPE_PC: + /* Only allow PC (R15) */ + if ((insn ^ 0xffffffff) & mask) + goto reject; + break; + + case REG_TYPE_NOSP: + /* Reject SP (R13) */ + if (((insn ^ 0xdddddddd) & mask) == 0) + goto reject; + break; + + case REG_TYPE_NOSPPC: + case REG_TYPE_NOSPPCX: + /* Reject SP and PC (R13 and R15) */ + if (((insn ^ 0xdddddddd) & 0xdddddddd & mask) == 0) + goto reject; + break; + + case REG_TYPE_NOPCWB: + if (!is_writeback(insn)) + break; /* No writeback, so any register is OK */ + /* fall through... */ + case REG_TYPE_NOPC: + case REG_TYPE_NOPCX: + /* Reject PC (R15) */ + if (((insn ^ 0xffffffff) & mask) == 0) + goto reject; + break; + } + + /* Replace value of nibble with new register number... */ + insn &= ~mask; + insn |= new_bits & mask; + } + + *pinsn = insn; + return true; + +reject: + return false; +} + +static const int decode_struct_sizes[NUM_DECODE_TYPES] = { + [DECODE_TYPE_TABLE] = sizeof(struct decode_table), + [DECODE_TYPE_CUSTOM] = sizeof(struct decode_custom), + [DECODE_TYPE_SIMULATE] = sizeof(struct decode_simulate), + [DECODE_TYPE_EMULATE] = sizeof(struct decode_emulate), + [DECODE_TYPE_OR] = sizeof(struct decode_or), + [DECODE_TYPE_REJECT] = sizeof(struct decode_reject) +}; + +/* + * kprobe_decode_insn operates on data tables in order to decode an ARM + * architecture instruction onto which a kprobe has been placed. + * + * These instruction decoding tables are a concatenation of entries each + * of which consist of one of the following structs: + * + * decode_table + * decode_custom + * decode_simulate + * decode_emulate + * decode_or + * decode_reject + * + * Each of these starts with a struct decode_header which has the following + * fields: + * + * type_regs + * mask + * value + * + * The least significant DECODE_TYPE_BITS of type_regs contains a value + * from enum decode_type, this indicates which of the decode_* structs + * the entry contains. The value DECODE_TYPE_END indicates the end of the + * table. + * + * When the table is parsed, each entry is checked in turn to see if it + * matches the instruction to be decoded using the test: + * + * (insn & mask) == value + * + * If no match is found before the end of the table is reached then decoding + * fails with INSN_REJECTED. + * + * When a match is found, decode_regs() is called to validate and modify each + * of the registers encoded in the instruction; the data it uses to do this + * is (type_regs >> DECODE_TYPE_BITS). A validation failure will cause decoding + * to fail with INSN_REJECTED. + * + * Once the instruction has passed the above tests, further processing + * depends on the type of the table entry's decode struct. + * + */ +int __kprobes +kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, + const union decode_item *table, bool thumb) +{ + const struct decode_header *h = (struct decode_header *)table; + const struct decode_header *next; + bool matched = false; + + insn = prepare_emulated_insn(insn, asi, thumb); + + for (;; h = next) { + enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK; + u32 regs = h->type_regs.bits >> DECODE_TYPE_BITS; + + if (type == DECODE_TYPE_END) + return INSN_REJECTED; + + next = (struct decode_header *) + ((uintptr_t)h + decode_struct_sizes[type]); + + if (!matched && (insn & h->mask.bits) != h->value.bits) + continue; + + if (!decode_regs(&insn, regs)) + return INSN_REJECTED; + + switch (type) { + + case DECODE_TYPE_TABLE: { + struct decode_table *d = (struct decode_table *)h; + next = (struct decode_header *)d->table.table; + break; + } + + case DECODE_TYPE_CUSTOM: { + struct decode_custom *d = (struct decode_custom *)h; + return (*d->decoder.decoder)(insn, asi); + } + + case DECODE_TYPE_SIMULATE: { + struct decode_simulate *d = (struct decode_simulate *)h; + asi->insn_handler = d->handler.handler; + return INSN_GOOD_NO_SLOT; + } + + case DECODE_TYPE_EMULATE: { + struct decode_emulate *d = (struct decode_emulate *)h; + asi->insn_handler = d->handler.handler; + set_emulated_insn(insn, asi, thumb); + return INSN_GOOD; + } + + case DECODE_TYPE_OR: + matched = true; + break; + + case DECODE_TYPE_REJECT: + default: + return INSN_REJECTED; + } + } + } diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index e3803c65c4be..c00681ce5cce 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -1,7 +1,9 @@ /* * arch/arm/kernel/kprobes.h * - * Contents moved from arch/arm/include/asm/kprobes.h which is + * Copyright (C) 2011 Jon Medhurst . + * + * Some contents moved here from arch/arm/include/asm/kprobes.h which is * Copyright (C) 2006, 2007 Motorola Inc. * * This program is free software; you can redistribute it and/or modify @@ -99,4 +101,248 @@ static inline unsigned long it_advance(unsigned long cpsr) */ #define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000) +/* + * The following definitions and macros are used to build instruction + * decoding tables for use by kprobe_decode_insn. + * + * These tables are a concatenation of entries each of which consist of one of + * the decode_* structs. All of the fields in every type of decode structure + * are of the union type decode_item, therefore the entire decode table can be + * viewed as an array of these and declared like: + * + * static const union decode_item table_name[] = {}; + * + * In order to construct each entry in the table, macros are used to + * initialise a number of sequential decode_item values in a layout which + * matches the relevant struct. E.g. DECODE_SIMULATE initialise a struct + * decode_simulate by initialising four decode_item objects like this... + * + * {.bits = _type}, + * {.bits = _mask}, + * {.bits = _value}, + * {.handler = _handler}, + * + * Initialising a specified member of the union means that the compiler + * will produce a warning if the argument is of an incorrect type. + * + * Below is a list of each of the macros used to initialise entries and a + * description of the action performed when that entry is matched to an + * instruction. A match is found when (instruction & mask) == value. + * + * DECODE_TABLE(mask, value, table) + * Instruction decoding jumps to parsing the new sub-table 'table'. + * + * DECODE_CUSTOM(mask, value, decoder) + * The custom function 'decoder' is called to the complete decoding + * of an instruction. + * + * DECODE_SIMULATE(mask, value, handler) + * Set the probes instruction handler to 'handler', this will be used + * to simulate the instruction when the probe is hit. Decoding returns + * with INSN_GOOD_NO_SLOT. + * + * DECODE_EMULATE(mask, value, handler) + * Set the probes instruction handler to 'handler', this will be used + * to emulate the instruction when the probe is hit. The modified + * instruction (see below) is placed in the probes instruction slot so it + * may be called by the emulation code. Decoding returns with INSN_GOOD. + * + * DECODE_REJECT(mask, value) + * Instruction decoding fails with INSN_REJECTED + * + * DECODE_OR(mask, value) + * This allows the mask/value test of multiple table entries to be + * logically ORed. Once an 'or' entry is matched the decoding action to + * be performed is that of the next entry which isn't an 'or'. E.g. + * + * DECODE_OR (mask1, value1) + * DECODE_OR (mask2, value2) + * DECODE_SIMULATE (mask3, value3, simulation_handler) + * + * This means that if any of the three mask/value pairs match the + * instruction being decoded, then 'simulation_handler' will be used + * for it. + * + * Both the SIMULATE and EMULATE macros have a second form which take an + * additional 'regs' argument. + * + * DECODE_SIMULATEX(mask, value, handler, regs) + * DECODE_EMULATEX (mask, value, handler, regs) + * + * These are used to specify what kind of CPU register is encoded in each of the + * least significant 5 nibbles of the instruction being decoded. The regs value + * is specified using the REGS macro, this takes any of the REG_TYPE_* values + * from enum decode_reg_type as arguments; only the '*' part of the name is + * given. E.g. + * + * REGS(0, ANY, NOPC, 0, ANY) + * + * This indicates an instruction is encoded like: + * + * bits 19..16 ignore + * bits 15..12 any register allowed here + * bits 11.. 8 any register except PC allowed here + * bits 7.. 4 ignore + * bits 3.. 0 any register allowed here + * + * This register specification is checked after a decode table entry is found to + * match an instruction (through the mask/value test). Any invalid register then + * found in the instruction will cause decoding to fail with INSN_REJECTED. In + * the above example this would happen if bits 11..8 of the instruction were + * 1111, indicating R15 or PC. + * + * As well as checking for legal combinations of registers, this data is also + * used to modify the registers encoded in the instructions so that an + * emulation routines can use it. (See decode_regs() and INSN_NEW_BITS.) + * + * Here is a real example which matches ARM instructions of the form + * "AND ,,, " + * + * DECODE_EMULATEX (0x0e000090, 0x00000010, emulate_rd12rn16rm0rs8_rwflags, + * REGS(ANY, ANY, NOPC, 0, ANY)), + * ^ ^ ^ ^ + * Rn Rd Rs Rm + * + * Decoding the instruction "AND R4, R5, R6, ASL R15" will be rejected because + * Rs == R15 + * + * Decoding the instruction "AND R4, R5, R6, ASL R7" will be accepted and the + * instruction will be modified to "AND R0, R2, R3, ASL R1" and then placed into + * the kprobes instruction slot. This can then be called later by the handler + * function emulate_rd12rn16rm0rs8_rwflags in order to simulate the instruction. + */ + +enum decode_type { + DECODE_TYPE_END, + DECODE_TYPE_TABLE, + DECODE_TYPE_CUSTOM, + DECODE_TYPE_SIMULATE, + DECODE_TYPE_EMULATE, + DECODE_TYPE_OR, + DECODE_TYPE_REJECT, + NUM_DECODE_TYPES /* Must be last enum */ +}; + +#define DECODE_TYPE_BITS 4 +#define DECODE_TYPE_MASK ((1 << DECODE_TYPE_BITS) - 1) + +enum decode_reg_type { + REG_TYPE_NONE = 0, /* Not a register, ignore */ + REG_TYPE_ANY, /* Any register allowed */ + REG_TYPE_SAMEAS16, /* Register should be same as that at bits 19..16 */ + REG_TYPE_SP, /* Register must be SP */ + REG_TYPE_PC, /* Register must be PC */ + REG_TYPE_NOSP, /* Register must not be SP */ + REG_TYPE_NOSPPC, /* Register must not be SP or PC */ + REG_TYPE_NOPC, /* Register must not be PC */ + REG_TYPE_NOPCWB, /* No PC if load/store write-back flag also set */ + + /* The following types are used when the encoding for PC indicates + * another instruction form. This distiction only matters for test + * case coverage checks. + */ + REG_TYPE_NOPCX, /* Register must not be PC */ + REG_TYPE_NOSPPCX, /* Register must not be SP or PC */ + + /* Alias to allow '0' arg to be used in REGS macro. */ + REG_TYPE_0 = REG_TYPE_NONE +}; + +#define REGS(r16, r12, r8, r4, r0) \ + ((REG_TYPE_##r16) << 16) + \ + ((REG_TYPE_##r12) << 12) + \ + ((REG_TYPE_##r8) << 8) + \ + ((REG_TYPE_##r4) << 4) + \ + (REG_TYPE_##r0) + +union decode_item { + u32 bits; + const union decode_item *table; + kprobe_insn_handler_t *handler; + kprobe_decode_insn_t *decoder; +}; + + +#define DECODE_END \ + {.bits = DECODE_TYPE_END} + + +struct decode_header { + union decode_item type_regs; + union decode_item mask; + union decode_item value; +}; + +#define DECODE_HEADER(_type, _mask, _value, _regs) \ + {.bits = (_type) | ((_regs) << DECODE_TYPE_BITS)}, \ + {.bits = (_mask)}, \ + {.bits = (_value)} + + +struct decode_table { + struct decode_header header; + union decode_item table; +}; + +#define DECODE_TABLE(_mask, _value, _table) \ + DECODE_HEADER(DECODE_TYPE_TABLE, _mask, _value, 0), \ + {.table = (_table)} + + +struct decode_custom { + struct decode_header header; + union decode_item decoder; +}; + +#define DECODE_CUSTOM(_mask, _value, _decoder) \ + DECODE_HEADER(DECODE_TYPE_CUSTOM, _mask, _value, 0), \ + {.decoder = (_decoder)} + + +struct decode_simulate { + struct decode_header header; + union decode_item handler; +}; + +#define DECODE_SIMULATEX(_mask, _value, _handler, _regs) \ + DECODE_HEADER(DECODE_TYPE_SIMULATE, _mask, _value, _regs), \ + {.handler = (_handler)} + +#define DECODE_SIMULATE(_mask, _value, _handler) \ + DECODE_SIMULATEX(_mask, _value, _handler, 0) + + +struct decode_emulate { + struct decode_header header; + union decode_item handler; +}; + +#define DECODE_EMULATEX(_mask, _value, _handler, _regs) \ + DECODE_HEADER(DECODE_TYPE_EMULATE, _mask, _value, _regs), \ + {.handler = (_handler)} + +#define DECODE_EMULATE(_mask, _value, _handler) \ + DECODE_EMULATEX(_mask, _value, _handler, 0) + + +struct decode_or { + struct decode_header header; +}; + +#define DECODE_OR(_mask, _value) \ + DECODE_HEADER(DECODE_TYPE_OR, _mask, _value, 0) + + +struct decode_reject { + struct decode_header header; +}; + +#define DECODE_REJECT(_mask, _value) \ + DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0) + + +int kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, + const union decode_item *table, bool thumb16); + + #endif /* _ARM_KERNEL_KPROBES_H */ -- cgit v1.2.3 From 3f92dfed6a9a5f490128c8e7cc6a64dfe412994f Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 15:36:32 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb hint instructions For hints which may have observable effects, like SEV (send event), we use kprobe_emulate_none which emulates the hint by executing the original instruction. For NOP we simulate the instruction using kprobe_simulate_nop, which does nothing. As probes execute with interrupts disabled this is also used for hints which may block for an indefinite time, like WFE (wait for event). Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-common.c | 9 +++++++++ arch/arm/kernel/kprobes-thumb.c | 35 ++++++++++++++++++++++++++++++++++- arch/arm/kernel/kprobes.h | 3 +++ 3 files changed, 46 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 1cb6a82a5e24..3a3e765d2090 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -142,6 +142,15 @@ kprobe_check_cc * const kprobe_condition_checks[16] = { }; +void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs) +{ +} + +void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs) +{ + p->ainsn.insn_fn(); +} + /* * Prepare an instruction slot to receive an instruction for emulating. * This is done by placing a subroutine return after the location where the diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 973c3eb1243a..7dcf6df4a85c 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -26,6 +26,39 @@ */ #define current_cond(cpsr) ((cpsr >> 12) & 0xf) +static const union decode_item t16_table_1011[] = { + /* Miscellaneous 16-bit instructions */ + + /* + * If-Then, and hints + * 1011 1111 xxxx xxxx + */ + + /* YIELD 1011 1111 0001 0000 */ + DECODE_OR (0xffff, 0xbf10), + /* SEV 1011 1111 0100 0000 */ + DECODE_EMULATE (0xffff, 0xbf40, kprobe_emulate_none), + /* NOP 1011 1111 0000 0000 */ + /* WFE 1011 1111 0010 0000 */ + /* WFI 1011 1111 0011 0000 */ + DECODE_SIMULATE (0xffcf, 0xbf00, kprobe_simulate_nop), + /* Unassigned hints 1011 1111 xxxx 0000 */ + DECODE_REJECT (0xff0f, 0xbf00), + + DECODE_END +}; + +const union decode_item kprobe_decode_thumb16_table[] = { + + /* + * Miscellaneous 16-bit instructions + * 1011 xxxx xxxx xxxx + */ + DECODE_TABLE (0xf000, 0xb000, t16_table_1011), + + DECODE_END +}; + static unsigned long __kprobes thumb_check_cc(unsigned long cpsr) { if (unlikely(in_it_block(cpsr))) @@ -52,7 +85,7 @@ thumb16_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { asi->insn_singlestep = thumb16_singlestep; asi->insn_check_cc = thumb_check_cc; - return INSN_REJECTED; + return kprobe_decode_insn(insn, asi, kprobe_decode_thumb16_table, true); } enum kprobe_insn __kprobes diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index c00681ce5cce..36e07684fe08 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -95,6 +95,9 @@ static inline unsigned long it_advance(unsigned long cpsr) return cpsr; } +void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs); +void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs); + /* * Test if load/store instructions writeback the address register. * if P (bit 24) == 0 or W (bit 21) == 1 -- cgit v1.2.3 From 7460bce42323df6570c7ba5091cb5201c7af1944 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 3 Jun 2011 12:12:33 +0100 Subject: ARM: ptrace: Add APSR_MASK definition to ptrace.h APSR_MASK can be used to extract the APSR bits from the CPSR. The comment for these definitions is also changed because it was inaccurate as the existing defines didn't refer to any part of the APSR. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/include/asm/ptrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index d484871698da..96187ff58c24 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -69,8 +69,9 @@ #define PSR_c 0x000000ff /* Control */ /* - * ARMv7 groups of APSR bits + * ARMv7 groups of PSR bits */ +#define APSR_MASK 0xf80f0000 /* N, Z, C, V, Q and GE flags */ #define PSR_ISET_MASK 0x01000010 /* ISA state (J, T) mask */ #define PSR_IT_MASK 0x0600fc00 /* If-Then execution state mask */ #define PSR_ENDIAN_MASK 0x00000200 /* Endianness state mask */ -- cgit v1.2.3 From 02d194f64772aee91e7319ca033905b0bafee04c Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 15:46:05 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb data-processing instructions These instructions only operate on the low registers R0-R7, therefore it is possible to emulate them by executing the original instruction unaltered if we restore and save these registers. This is what t16_emulate_loregs does. Some of these instructions don't update the PSR when they execute in an IT block, so there are two flavours of emulation functions: t16_emulate_loregs_{noit}rwflags Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 81 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 7dcf6df4a85c..e1cef8273126 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -26,6 +26,42 @@ */ #define current_cond(cpsr) ((cpsr >> 12) & 0xf) +static unsigned long __kprobes +t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) +{ + unsigned long oldcpsr = regs->ARM_cpsr; + unsigned long newcpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[oldcpsr] \n\t" + "ldmia %[regs], {r0-r7} \n\t" + "blx %[fn] \n\t" + "stmia %[regs], {r0-r7} \n\t" + "mrs %[newcpsr], cpsr \n\t" + : [newcpsr] "=r" (newcpsr) + : [oldcpsr] "r" (oldcpsr), [regs] "r" (regs), + [fn] "r" (p->ainsn.insn_fn) + : "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", + "lr", "memory", "cc" + ); + + return (oldcpsr & ~APSR_MASK) | (newcpsr & APSR_MASK); +} + +static void __kprobes +t16_emulate_loregs_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_cpsr = t16_emulate_loregs(p, regs); +} + +static void __kprobes +t16_emulate_loregs_noitrwflags(struct kprobe *p, struct pt_regs *regs) +{ + unsigned long cpsr = t16_emulate_loregs(p, regs); + if (!in_it_block(cpsr)) + regs->ARM_cpsr = cpsr; +} + static const union decode_item t16_table_1011[] = { /* Miscellaneous 16-bit instructions */ @@ -50,6 +86,51 @@ static const union decode_item t16_table_1011[] = { const union decode_item kprobe_decode_thumb16_table[] = { + /* + * Shift (immediate), add, subtract, move, and compare + * 00xx xxxx xxxx xxxx + */ + + /* CMP (immediate) 0010 1xxx xxxx xxxx */ + DECODE_EMULATE (0xf800, 0x2800, t16_emulate_loregs_rwflags), + + /* ADD (register) 0001 100x xxxx xxxx */ + /* SUB (register) 0001 101x xxxx xxxx */ + /* LSL (immediate) 0000 0xxx xxxx xxxx */ + /* LSR (immediate) 0000 1xxx xxxx xxxx */ + /* ASR (immediate) 0001 0xxx xxxx xxxx */ + /* ADD (immediate, Thumb) 0001 110x xxxx xxxx */ + /* SUB (immediate, Thumb) 0001 111x xxxx xxxx */ + /* MOV (immediate) 0010 0xxx xxxx xxxx */ + /* ADD (immediate, Thumb) 0011 0xxx xxxx xxxx */ + /* SUB (immediate, Thumb) 0011 1xxx xxxx xxxx */ + DECODE_EMULATE (0xc000, 0x0000, t16_emulate_loregs_noitrwflags), + + /* + * 16-bit Thumb data-processing instructions + * 0100 00xx xxxx xxxx + */ + + /* TST (register) 0100 0010 00xx xxxx */ + DECODE_EMULATE (0xffc0, 0x4200, t16_emulate_loregs_rwflags), + /* CMP (register) 0100 0010 10xx xxxx */ + /* CMN (register) 0100 0010 11xx xxxx */ + DECODE_EMULATE (0xff80, 0x4280, t16_emulate_loregs_rwflags), + /* AND (register) 0100 0000 00xx xxxx */ + /* EOR (register) 0100 0000 01xx xxxx */ + /* LSL (register) 0100 0000 10xx xxxx */ + /* LSR (register) 0100 0000 11xx xxxx */ + /* ASR (register) 0100 0001 00xx xxxx */ + /* ADC (register) 0100 0001 01xx xxxx */ + /* SBC (register) 0100 0001 10xx xxxx */ + /* ROR (register) 0100 0001 11xx xxxx */ + /* RSB (immediate) 0100 0010 01xx xxxx */ + /* ORR (register) 0100 0011 00xx xxxx */ + /* MUL 0100 0011 00xx xxxx */ + /* BIC (register) 0100 0011 10xx xxxx */ + /* MVN (register) 0100 0011 10xx xxxx */ + DECODE_EMULATE (0xfc00, 0x4000, t16_emulate_loregs_noitrwflags), + /* * Miscellaneous 16-bit instructions * 1011 xxxx xxxx xxxx -- cgit v1.2.3 From 059987ffa7f8905fada25c8af1734e254209c55d Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 11:01:54 +0100 Subject: ARM: kprobes: Add bx_write_pc() This writes a value to PC, with interworking. I.e. switches to Thumb or ARM mode depending on the state of the least significant bit. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 36e07684fe08..12627a376bf6 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -95,6 +95,20 @@ static inline unsigned long it_advance(unsigned long cpsr) return cpsr; } +static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs) +{ + long cpsr = regs->ARM_cpsr; + if (pcv & 0x1) { + cpsr |= PSR_T_BIT; + pcv &= ~0x1; + } else { + cpsr &= ~PSR_T_BIT; + pcv &= ~0x2; /* Avoid UNPREDICTABLE address allignment */ + } + regs->ARM_cpsr = cpsr; + regs->ARM_pc = pcv; +} + void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs); void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs); -- cgit v1.2.3 From a9c3c29e72cc459be0ecd597f0af11a67713175b Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 15:51:03 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb BX and BLX instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index e1cef8273126..b457da0e7397 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -26,6 +26,31 @@ */ #define current_cond(cpsr) ((cpsr >> 12) & 0xf) +/* + * Return the PC value for a probe in thumb code. + * This is the address of the probed instruction plus 4. + * We subtract one because the address will have bit zero set to indicate + * a pointer to thumb code. + */ +static inline unsigned long __kprobes thumb_probe_pc(struct kprobe *p) +{ + return (unsigned long)p->addr - 1 + 4; +} + +static void __kprobes +t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + int rm = (insn >> 3) & 0xf; + unsigned long rmv = (rm == 15) ? pc : regs->uregs[rm]; + + if (insn & (1 << 7)) /* BLX ? */ + regs->ARM_lr = (unsigned long)p->addr + 2; + + bx_write_pc(rmv, regs); +} + static unsigned long __kprobes t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) { @@ -131,6 +156,18 @@ const union decode_item kprobe_decode_thumb16_table[] = { /* MVN (register) 0100 0011 10xx xxxx */ DECODE_EMULATE (0xfc00, 0x4000, t16_emulate_loregs_noitrwflags), + /* + * Special data instructions and branch and exchange + * 0100 01xx xxxx xxxx + */ + + /* BLX pc 0100 0111 1111 1xxx */ + DECODE_REJECT (0xfff8, 0x47f8), + + /* BX (register) 0100 0111 0xxx xxxx */ + /* BLX (register) 0100 0111 1xxx xxxx */ + DECODE_SIMULATE (0xff00, 0x4700, t16_simulate_bxblx), + /* * Miscellaneous 16-bit instructions * 1011 xxxx xxxx xxxx -- cgit v1.2.3 From 3b5940e81182ff26d539dcf0ee8b2310f6965833 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 15:54:57 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb special data instructions These data-processing instructions operate on the full range of CPU registers, so to simulate them we have to modify the registers used by the instruction. We can't make use of the decoding table framework to do this because the registers aren't encoded cleanly in separate nibbles, therefore we need a custom decode function. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 49 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index b457da0e7397..cd4d03d19950 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -87,6 +87,47 @@ t16_emulate_loregs_noitrwflags(struct kprobe *p, struct pt_regs *regs) regs->ARM_cpsr = cpsr; } +static void __kprobes +t16_emulate_hiregs(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + int rdn = (insn & 0x7) | ((insn & 0x80) >> 4); + int rm = (insn >> 3) & 0xf; + + register unsigned long rdnv asm("r1"); + register unsigned long rmv asm("r0"); + unsigned long cpsr = regs->ARM_cpsr; + + rdnv = (rdn == 15) ? pc : regs->uregs[rdn]; + rmv = (rm == 15) ? pc : regs->uregs[rm]; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "blx %[fn] \n\t" + "mrs %[cpsr], cpsr \n\t" + : "=r" (rdnv), [cpsr] "=r" (cpsr) + : "0" (rdnv), "r" (rmv), "1" (cpsr), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + if (rdn == 15) + rdnv &= ~1; + + regs->uregs[rdn] = rdnv; + regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); +} + +static enum kprobe_insn __kprobes +t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + insn &= ~0x00ff; + insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */ + ((u16 *)asi->insn)[0] = insn; + asi->insn_handler = t16_emulate_hiregs; + return INSN_GOOD; +} + static const union decode_item t16_table_1011[] = { /* Miscellaneous 16-bit instructions */ @@ -168,6 +209,14 @@ const union decode_item kprobe_decode_thumb16_table[] = { /* BLX (register) 0100 0111 1xxx xxxx */ DECODE_SIMULATE (0xff00, 0x4700, t16_simulate_bxblx), + /* ADD pc, pc 0100 0100 1111 1111 */ + DECODE_REJECT (0xffff, 0x44ff), + + /* ADD (register) 0100 0100 xxxx xxxx */ + /* CMP (register) 0100 0101 xxxx xxxx */ + /* MOV (register) 0100 0110 xxxx xxxx */ + DECODE_CUSTOM (0xfc00, 0x4400, t16_decode_hiregs), + /* * Miscellaneous 16-bit instructions * 1011 xxxx xxxx xxxx -- cgit v1.2.3 From f8695142820f3cb3bc97444a240eec5375a2b107 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:00:09 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb load and store instructions Most of these instructions only operate on the low registers R0-R7 so they can make use of t16_emulate_loregs_rwflags. The instructions which use SP or PC for addressing have their own simulation functions. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 60 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index cd4d03d19950..632a5e8f5977 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -51,6 +51,29 @@ t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs) bx_write_pc(rmv, regs); } +static void __kprobes +t16_simulate_ldr_literal(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long* base = (unsigned long *)(thumb_probe_pc(p) & ~3); + long index = insn & 0xff; + int rt = (insn >> 8) & 0x7; + regs->uregs[rt] = base[index]; +} + +static void __kprobes +t16_simulate_ldrstr_sp_relative(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long* base = (unsigned long *)regs->ARM_sp; + long index = insn & 0xff; + int rt = (insn >> 8) & 0x7; + if (insn & 0x800) /* LDR */ + regs->uregs[rt] = base[index]; + else /* STR */ + base[index] = regs->uregs[rt]; +} + static unsigned long __kprobes t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) { @@ -217,12 +240,49 @@ const union decode_item kprobe_decode_thumb16_table[] = { /* MOV (register) 0100 0110 xxxx xxxx */ DECODE_CUSTOM (0xfc00, 0x4400, t16_decode_hiregs), + /* + * Load from Literal Pool + * LDR (literal) 0100 1xxx xxxx xxxx + */ + DECODE_SIMULATE (0xf800, 0x4800, t16_simulate_ldr_literal), + + /* + * 16-bit Thumb Load/store instructions + * 0101 xxxx xxxx xxxx + * 011x xxxx xxxx xxxx + * 100x xxxx xxxx xxxx + */ + + /* STR (register) 0101 000x xxxx xxxx */ + /* STRH (register) 0101 001x xxxx xxxx */ + /* STRB (register) 0101 010x xxxx xxxx */ + /* LDRSB (register) 0101 011x xxxx xxxx */ + /* LDR (register) 0101 100x xxxx xxxx */ + /* LDRH (register) 0101 101x xxxx xxxx */ + /* LDRB (register) 0101 110x xxxx xxxx */ + /* LDRSH (register) 0101 111x xxxx xxxx */ + /* STR (immediate, Thumb) 0110 0xxx xxxx xxxx */ + /* LDR (immediate, Thumb) 0110 1xxx xxxx xxxx */ + /* STRB (immediate, Thumb) 0111 0xxx xxxx xxxx */ + /* LDRB (immediate, Thumb) 0111 1xxx xxxx xxxx */ + DECODE_EMULATE (0xc000, 0x4000, t16_emulate_loregs_rwflags), + /* STRH (immediate, Thumb) 1000 0xxx xxxx xxxx */ + /* LDRH (immediate, Thumb) 1000 1xxx xxxx xxxx */ + DECODE_EMULATE (0xf000, 0x8000, t16_emulate_loregs_rwflags), + /* STR (immediate, Thumb) 1001 0xxx xxxx xxxx */ + /* LDR (immediate, Thumb) 1001 1xxx xxxx xxxx */ + DECODE_SIMULATE (0xf000, 0x9000, t16_simulate_ldrstr_sp_relative), + /* * Miscellaneous 16-bit instructions * 1011 xxxx xxxx xxxx */ DECODE_TABLE (0xf000, 0xb000, t16_table_1011), + /* STM 1100 0xxx xxxx xxxx */ + /* LDM 1100 1xxx xxxx xxxx */ + DECODE_EMULATE (0xf000, 0xc000, t16_emulate_loregs_rwflags), + DECODE_END }; -- cgit v1.2.3 From 2f335829040cb16d0640e87121bef208894d4934 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:05:53 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb PC- and SP-relative address instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 632a5e8f5977..2b30828d5f0c 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -74,6 +74,28 @@ t16_simulate_ldrstr_sp_relative(struct kprobe *p, struct pt_regs *regs) base[index] = regs->uregs[rt]; } +static void __kprobes +t16_simulate_reladr(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long base = (insn & 0x800) ? regs->ARM_sp + : (thumb_probe_pc(p) & ~3); + long offset = insn & 0xff; + int rt = (insn >> 8) & 0x7; + regs->uregs[rt] = base + offset * 4; +} + +static void __kprobes +t16_simulate_add_sp_imm(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + long imm = insn & 0x7f; + if (insn & 0x80) /* SUB */ + regs->ARM_sp -= imm * 4; + else /* ADD */ + regs->ARM_sp += imm * 4; +} + static unsigned long __kprobes t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) { @@ -154,6 +176,10 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) static const union decode_item t16_table_1011[] = { /* Miscellaneous 16-bit instructions */ + /* ADD (SP plus immediate) 1011 0000 0xxx xxxx */ + /* SUB (SP minus immediate) 1011 0000 1xxx xxxx */ + DECODE_SIMULATE (0xff00, 0xb000, t16_simulate_add_sp_imm), + /* * If-Then, and hints * 1011 1111 xxxx xxxx @@ -273,6 +299,13 @@ const union decode_item kprobe_decode_thumb16_table[] = { /* LDR (immediate, Thumb) 1001 1xxx xxxx xxxx */ DECODE_SIMULATE (0xf000, 0x9000, t16_simulate_ldrstr_sp_relative), + /* + * Generate PC-/SP-relative address + * ADR (literal) 1010 0xxx xxxx xxxx + * ADD (SP plus immediate) 1010 1xxx xxxx xxxx + */ + DECODE_SIMULATE (0xf000, 0xa000, t16_simulate_reladr), + /* * Miscellaneous 16-bit instructions * 1011 xxxx xxxx xxxx -- cgit v1.2.3 From 32818f31f8ed811ea7ef924f24642580a63a7c85 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:10:44 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb CBZ and bit manipulation instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 2b30828d5f0c..a5bdb2dc39e7 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -96,6 +96,20 @@ t16_simulate_add_sp_imm(struct kprobe *p, struct pt_regs *regs) regs->ARM_sp += imm * 4; } +static void __kprobes +t16_simulate_cbz(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rn = insn & 0x7; + kprobe_opcode_t nonzero = regs->uregs[rn] ? insn : ~insn; + if (nonzero & 0x800) { + long i = insn & 0x200; + long imm5 = insn & 0xf8; + unsigned long pc = thumb_probe_pc(p); + regs->ARM_pc = pc + (i >> 3) + (imm5 >> 2); + } +} + static unsigned long __kprobes t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) { @@ -180,6 +194,21 @@ static const union decode_item t16_table_1011[] = { /* SUB (SP minus immediate) 1011 0000 1xxx xxxx */ DECODE_SIMULATE (0xff00, 0xb000, t16_simulate_add_sp_imm), + /* CBZ 1011 00x1 xxxx xxxx */ + /* CBNZ 1011 10x1 xxxx xxxx */ + DECODE_SIMULATE (0xf500, 0xb100, t16_simulate_cbz), + + /* SXTH 1011 0010 00xx xxxx */ + /* SXTB 1011 0010 01xx xxxx */ + /* UXTH 1011 0010 10xx xxxx */ + /* UXTB 1011 0010 11xx xxxx */ + /* REV 1011 1010 00xx xxxx */ + /* REV16 1011 1010 01xx xxxx */ + /* ??? 1011 1010 10xx xxxx */ + /* REVSH 1011 1010 11xx xxxx */ + DECODE_REJECT (0xffc0, 0xba80), + DECODE_EMULATE (0xf500, 0xb000, t16_emulate_loregs_rwflags), + /* * If-Then, and hints * 1011 1111 xxxx xxxx -- cgit v1.2.3 From fd0c8d8a48c57cb8a3f1fbbe46a2b208b57ff477 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:13:29 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb PUSH and POP instructions These instructions are equivalent to stmdb sp!,{r0-r7,lr} ldmdb sp!,{r0-r7,pc} and we emulate them by transforming them into the 32-bit Thumb instructions stmdb r9!,{r0-r7,r8} ldmdb r9!,{r0-r7,r8} This is simpler, and almost certainly executes faster, than writing simulation functions. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 86 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index a5bdb2dc39e7..e0289493b4c6 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -187,6 +187,87 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi) return INSN_GOOD; } +static void __kprobes +t16_emulate_push(struct kprobe *p, struct pt_regs *regs) +{ + __asm__ __volatile__ ( + "ldr r9, [%[regs], #13*4] \n\t" + "ldr r8, [%[regs], #14*4] \n\t" + "ldmia %[regs], {r0-r7} \n\t" + "blx %[fn] \n\t" + "str r9, [%[regs], #13*4] \n\t" + : + : [regs] "r" (regs), [fn] "r" (p->ainsn.insn_fn) + : "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", + "lr", "memory", "cc" + ); +} + +static enum kprobe_insn __kprobes +t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* + * To simulate a PUSH we use a Thumb-2 "STMDB R9!, {registers}" + * and call it with R9=SP and LR in the register list represented + * by R8. + */ + ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */ + ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + asi->insn_handler = t16_emulate_push; + return INSN_GOOD; +} + +static void __kprobes +t16_emulate_pop_nopc(struct kprobe *p, struct pt_regs *regs) +{ + __asm__ __volatile__ ( + "ldr r9, [%[regs], #13*4] \n\t" + "ldmia %[regs], {r0-r7} \n\t" + "blx %[fn] \n\t" + "stmia %[regs], {r0-r7} \n\t" + "str r9, [%[regs], #13*4] \n\t" + : + : [regs] "r" (regs), [fn] "r" (p->ainsn.insn_fn) + : "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r9", + "lr", "memory", "cc" + ); +} + +static void __kprobes +t16_emulate_pop_pc(struct kprobe *p, struct pt_regs *regs) +{ + register unsigned long pc asm("r8"); + + __asm__ __volatile__ ( + "ldr r9, [%[regs], #13*4] \n\t" + "ldmia %[regs], {r0-r7} \n\t" + "blx %[fn] \n\t" + "stmia %[regs], {r0-r7} \n\t" + "str r9, [%[regs], #13*4] \n\t" + : "=r" (pc) + : [regs] "r" (regs), [fn] "r" (p->ainsn.insn_fn) + : "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r9", + "lr", "memory", "cc" + ); + + bx_write_pc(pc, regs); +} + +static enum kprobe_insn __kprobes +t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* + * To simulate a POP we use a Thumb-2 "LDMDB R9!, {registers}" + * and call it with R9=SP and PC in the register list represented + * by R8. + */ + ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */ + ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */ + asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc + : t16_emulate_pop_nopc; + return INSN_GOOD; +} + static const union decode_item t16_table_1011[] = { /* Miscellaneous 16-bit instructions */ @@ -209,6 +290,11 @@ static const union decode_item t16_table_1011[] = { DECODE_REJECT (0xffc0, 0xba80), DECODE_EMULATE (0xf500, 0xb000, t16_emulate_loregs_rwflags), + /* PUSH 1011 010x xxxx xxxx */ + DECODE_CUSTOM (0xfe00, 0xb400, t16_decode_push), + /* POP 1011 110x xxxx xxxx */ + DECODE_CUSTOM (0xfe00, 0xbc00, t16_decode_pop), + /* * If-Then, and hints * 1011 1111 xxxx xxxx -- cgit v1.2.3 From 5b94faf8d76be2116223c2591b31ddae5eecac2b Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:16:05 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb IT instruction The normal Thumb singlestepping routine updates the IT state after calling the instruction handler. We don't what this to happen after the IT instruction simulation sets the IT state, therefore we need to provide a custom singlestep routine. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index e0289493b4c6..e496948fefac 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -110,6 +110,37 @@ t16_simulate_cbz(struct kprobe *p, struct pt_regs *regs) } } +static void __kprobes +t16_simulate_it(struct kprobe *p, struct pt_regs *regs) +{ + /* + * The 8 IT state bits are split into two parts in CPSR: + * ITSTATE<1:0> are in CPSR<26:25> + * ITSTATE<7:2> are in CPSR<15:10> + * The new IT state is in the lower byte of insn. + */ + kprobe_opcode_t insn = p->opcode; + unsigned long cpsr = regs->ARM_cpsr; + cpsr &= ~PSR_IT_MASK; + cpsr |= (insn & 0xfc) << 8; + cpsr |= (insn & 0x03) << 25; + regs->ARM_cpsr = cpsr; +} + +static void __kprobes +t16_singlestep_it(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_pc += 2; + t16_simulate_it(p, regs); +} + +static enum kprobe_insn __kprobes +t16_decode_it(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + asi->insn_singlestep = t16_singlestep_it; + return INSN_GOOD_NO_SLOT; +} + static unsigned long __kprobes t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) { @@ -310,6 +341,8 @@ static const union decode_item t16_table_1011[] = { DECODE_SIMULATE (0xffcf, 0xbf00, kprobe_simulate_nop), /* Unassigned hints 1011 1111 xxxx 0000 */ DECODE_REJECT (0xff0f, 0xbf00), + /* IT 1011 1111 xxxx xxxx */ + DECODE_CUSTOM (0xff00, 0xbf00, t16_decode_it), DECODE_END }; -- cgit v1.2.3 From 444956677eccfcdfe05de761e1286f62c423ce88 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:25:47 +0100 Subject: ARM: kprobes: Reject 16-bit Thumb SVC and UNDEFINED instructions SVC (SWI) instructions shouldn't occur in kernel code so we don't need to be able to probe them. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index e496948fefac..997fc6d59a40 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -464,6 +464,14 @@ const union decode_item kprobe_decode_thumb16_table[] = { /* LDM 1100 1xxx xxxx xxxx */ DECODE_EMULATE (0xf000, 0xc000, t16_emulate_loregs_rwflags), + /* + * Conditional branch, and Supervisor Call + */ + + /* Permanently UNDEFINED 1101 1110 xxxx xxxx */ + /* SVC 1101 1111 xxxx xxxx */ + DECODE_REJECT (0xfe00, 0xde00), + DECODE_END }; -- cgit v1.2.3 From 396b41f68d937a0c48ba624186ed06288b35bb4e Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:30:43 +0100 Subject: ARM: kprobes: Decode 16-bit Thumb branch instructions We previously changed the behaviour of probes so that conditional instructions don't fire when the condition isn't met. For ARM branches, and Thumb branches in IT blocks, this means they don't fire if the branch isn't taken. For consistency, we implement the same for Thumb conditional branch instructions. This involves setting up insn_check_cc to point to the relevant condition checking function. As the emulation routine is only called when this condition passes, it doesn't need to check again and can unconditionally update PC. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 997fc6d59a40..d3133fd2d4e8 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -141,6 +141,35 @@ t16_decode_it(kprobe_opcode_t insn, struct arch_specific_insn *asi) return INSN_GOOD_NO_SLOT; } +static void __kprobes +t16_simulate_cond_branch(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + long offset = insn & 0x7f; + offset -= insn & 0x80; /* Apply sign bit */ + regs->ARM_pc = pc + (offset * 2); +} + +static enum kprobe_insn __kprobes +t16_decode_cond_branch(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + int cc = (insn >> 8) & 0xf; + asi->insn_check_cc = kprobe_condition_checks[cc]; + asi->insn_handler = t16_simulate_cond_branch; + return INSN_GOOD_NO_SLOT; +} + +static void __kprobes +t16_simulate_branch(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + long offset = insn & 0x3ff; + offset -= insn & 0x400; /* Apply sign bit */ + regs->ARM_pc = pc + (offset * 2); +} + static unsigned long __kprobes t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs) { @@ -472,6 +501,15 @@ const union decode_item kprobe_decode_thumb16_table[] = { /* SVC 1101 1111 xxxx xxxx */ DECODE_REJECT (0xfe00, 0xde00), + /* Conditional branch 1101 xxxx xxxx xxxx */ + DECODE_CUSTOM (0xf000, 0xd000, t16_decode_cond_branch), + + /* + * Unconditional branch + * B 1110 0xxx xxxx xxxx + */ + DECODE_SIMULATE (0xf800, 0xe000, t16_simulate_branch), + DECODE_END }; -- cgit v1.2.3 From 0a188ccb5eceb58101fcc11b3ec2d860ccbf92a3 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 2 Jul 2011 16:39:07 +0100 Subject: ARM: kprobes: Reject 16-bit Thumb SETEND, CPS and BKPT instructions These are very rare and/or problematic to emulate so we will take the easy option and disallow probing them (as does the existing ARM implementation). Rejecting these instructions doesn't actually require any entries in the decoding table as it is the default case for instructions which aren't found. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index d3133fd2d4e8..554578bc5f09 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -373,6 +373,10 @@ static const union decode_item t16_table_1011[] = { /* IT 1011 1111 xxxx xxxx */ DECODE_CUSTOM (0xff00, 0xbf00, t16_decode_it), + /* SETEND 1011 0110 010x xxxx */ + /* CPS 1011 0110 011x xxxx */ + /* BKPT 1011 1110 xxxx xxxx */ + /* And unallocated instructions... */ DECODE_END }; -- cgit v1.2.3 From f39ca8b488a6c1e8db47746e1cdb841a6999edd7 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 13:55:47 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb hint instructions For hints which may have observable effects, like SEV (send event), we use kprobe_emulate_none which emulates the hint by executing the original instruction. For NOP we simulate the instruction using kprobe_simulate_nop, which does nothing. As probes execute with interrupts disabled this is also used for hints which may block for an indefinite time, like WFE (wait for event). Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 554578bc5f09..27f83a32a038 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -37,6 +37,32 @@ static inline unsigned long __kprobes thumb_probe_pc(struct kprobe *p) return (unsigned long)p->addr - 1 + 4; } +static const union decode_item t32_table_1111_0xxx___1[] = { + /* Branches and miscellaneous control */ + + /* YIELD 1111 0011 1010 xxxx 10x0 x000 0000 0001 */ + DECODE_OR (0xfff0d7ff, 0xf3a08001), + /* SEV 1111 0011 1010 xxxx 10x0 x000 0000 0100 */ + DECODE_EMULATE (0xfff0d7ff, 0xf3a08004, kprobe_emulate_none), + /* NOP 1111 0011 1010 xxxx 10x0 x000 0000 0000 */ + /* WFE 1111 0011 1010 xxxx 10x0 x000 0000 0010 */ + /* WFI 1111 0011 1010 xxxx 10x0 x000 0000 0011 */ + DECODE_SIMULATE (0xfff0d7fc, 0xf3a08000, kprobe_simulate_nop), + + DECODE_END +}; + +const union decode_item kprobe_decode_thumb32_table[] = { + + /* + * Branches and miscellaneous control + * 1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xf8008000, 0xf0008000, t32_table_1111_0xxx___1), + + DECODE_END +}; + static void __kprobes t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs) { @@ -551,5 +577,5 @@ thumb32_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { asi->insn_singlestep = thumb32_singlestep; asi->insn_check_cc = thumb_check_cc; - return INSN_REJECTED; + return kprobe_decode_insn(insn, asi, kprobe_decode_thumb32_table, true); } -- cgit v1.2.3 From 263e368a2f1f960db07d7524a4a3e7df951f1f72 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 10 Jun 2011 20:29:04 +0100 Subject: ARM: kprobes: Add load_write_pc() This writes a value to PC which was obtained as the result of a LDR or LDM instruction. For ARMv5T and later this must perform interworking. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-common.c | 15 +++++++++++++++ arch/arm/kernel/kprobes.h | 24 ++++++++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 3a3e765d2090..86fdc4c4c2ce 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -45,9 +45,24 @@ void __init find_str_pc_offset(void) #endif /* !find_str_pc_offset */ +#ifndef test_load_write_pc_interworking + +bool load_write_pc_interworks; + +void __init test_load_write_pc_interworking(void) +{ + int arch = cpu_architecture(); + BUG_ON(arch == CPU_ARCH_UNKNOWN); + load_write_pc_interworks = arch >= CPU_ARCH_ARMv5T; +} + +#endif /* !test_load_write_pc_interworking */ + + void __init arm_kprobe_decode_init(void) { find_str_pc_offset(); + test_load_write_pc_interworking(); } diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 12627a376bf6..5d6bf0d0a18a 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -109,6 +109,30 @@ static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs) regs->ARM_pc = pcv; } + +#if __LINUX_ARM_ARCH__ >= 6 + +/* Kernels built for >= ARMv6 should never run on <= ARMv5 hardware, so... */ +#define load_write_pc_interworks true +#define test_load_write_pc_interworking() + +#else /* __LINUX_ARM_ARCH__ < 6 */ + +/* We need run-time testing to determine if load_write_pc() should interwork. */ +extern bool load_write_pc_interworks; +void __init test_load_write_pc_interworking(void); + +#endif + +static inline void __kprobes load_write_pc(long pcv, struct pt_regs *regs) +{ + if (load_write_pc_interworks) + bx_write_pc(pcv, regs); + else + regs->ARM_pc = pcv; +} + + void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs); void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs); -- cgit v1.2.3 From 235a4ce79feb8d5351f9164981bc57d5e29f974b Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 7 Jul 2011 08:57:22 +0100 Subject: ARM: kprobes: Add common decoding function for LDM and STM The encoding of these instructions is substantially the same for both ARM and Thumb, so we can have common decoding and simulation functions. This patch moves the simulation functions from kprobes-arm.c to kprobes-common.c. It also adds a new simulation function (simulate_ldm1_pc) for the case where we load into PC because this may need to interwork. The instruction decoding is done by a custom function (kprobe_decode_ldmstm) rather than just relying on decoding table entries because we will later be adding optimisation code. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 58 ++++----------------------------- arch/arm/kernel/kprobes-common.c | 70 ++++++++++++++++++++++++++++++++++++++++ arch/arm/kernel/kprobes.h | 3 ++ 3 files changed, 80 insertions(+), 51 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index a1143e86a09a..c6f2c693b1b6 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -437,54 +437,6 @@ static void __kprobes simulate_mrs(struct kprobe *p, struct pt_regs *regs) regs->uregs[rd] = regs->ARM_cpsr & mask; } -static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs) -{ - kprobe_opcode_t insn = p->opcode; - int rn = (insn >> 16) & 0xf; - int lbit = insn & (1 << 20); - int wbit = insn & (1 << 21); - int ubit = insn & (1 << 23); - int pbit = insn & (1 << 24); - long *addr = (long *)regs->uregs[rn]; - int reg_bit_vector; - int reg_count; - - reg_count = 0; - reg_bit_vector = insn & 0xffff; - while (reg_bit_vector) { - reg_bit_vector &= (reg_bit_vector - 1); - ++reg_count; - } - - if (!ubit) - addr -= reg_count; - addr += (!pbit == !ubit); - - reg_bit_vector = insn & 0xffff; - while (reg_bit_vector) { - int reg = __ffs(reg_bit_vector); - reg_bit_vector &= (reg_bit_vector - 1); - if (lbit) - regs->uregs[reg] = *addr++; - else - *addr++ = regs->uregs[reg]; - } - - if (wbit) { - if (!ubit) - addr -= reg_count; - addr -= (!pbit == !ubit); - regs->uregs[rn] = (long)addr; - } -} - -static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs) -{ - regs->ARM_pc = (long)p->addr + str_pc_offset; - simulate_ldm1stm1(p, regs); - regs->ARM_pc = (long)p->addr + 4; -} - static void __kprobes simulate_mov_ipsp(struct kprobe *p, struct pt_regs *regs) { regs->uregs[12] = regs->uregs[13]; @@ -1463,9 +1415,13 @@ space_cccc_100x(kprobe_opcode_t insn, struct arch_specific_insn *asi) /* LDM(1) : cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ /* STM(1) : cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */ - asi->insn_handler = ((insn & 0x108000) == 0x008000) ? /* STM & R15 */ - simulate_stm1_pc : simulate_ldm1stm1; - return INSN_GOOD_NO_SLOT; + + /* + * Make the instruction unconditional because the new emulation + * functions don't bother to setup the PSR context. + */ + insn = (insn | 0xe0000000) & ~0x10000000; + return kprobe_decode_ldmstm(insn, asi); } static enum kprobe_insn __kprobes diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 86fdc4c4c2ce..43d663cafdd1 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -166,6 +166,76 @@ void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs) p->ainsn.insn_fn(); } +static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rn = (insn >> 16) & 0xf; + int lbit = insn & (1 << 20); + int wbit = insn & (1 << 21); + int ubit = insn & (1 << 23); + int pbit = insn & (1 << 24); + long *addr = (long *)regs->uregs[rn]; + int reg_bit_vector; + int reg_count; + + reg_count = 0; + reg_bit_vector = insn & 0xffff; + while (reg_bit_vector) { + reg_bit_vector &= (reg_bit_vector - 1); + ++reg_count; + } + + if (!ubit) + addr -= reg_count; + addr += (!pbit == !ubit); + + reg_bit_vector = insn & 0xffff; + while (reg_bit_vector) { + int reg = __ffs(reg_bit_vector); + reg_bit_vector &= (reg_bit_vector - 1); + if (lbit) + regs->uregs[reg] = *addr++; + else + *addr++ = regs->uregs[reg]; + } + + if (wbit) { + if (!ubit) + addr -= reg_count; + addr -= (!pbit == !ubit); + regs->uregs[rn] = (long)addr; + } +} + +static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs) +{ + regs->ARM_pc = (long)p->addr + str_pc_offset; + simulate_ldm1stm1(p, regs); + regs->ARM_pc = (long)p->addr + 4; +} + +static void __kprobes simulate_ldm1_pc(struct kprobe *p, struct pt_regs *regs) +{ + simulate_ldm1stm1(p, regs); + load_write_pc(regs->ARM_pc, regs); +} + +enum kprobe_insn __kprobes +kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + kprobe_insn_handler_t *handler = 0; + unsigned reglist = insn & 0xffff; + int is_ldm = insn & 0x100000; + + if (reglist & 0x8000) + handler = is_ldm ? simulate_ldm1_pc : simulate_stm1_pc; + else + handler = simulate_ldm1stm1; + asi->insn_handler = handler; + return INSN_GOOD_NO_SLOT; +} + + /* * Prepare an instruction slot to receive an instruction for emulating. * This is done by placing a subroutine return after the location where the diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index 5d6bf0d0a18a..c442852e65e4 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -136,6 +136,9 @@ static inline void __kprobes load_write_pc(long pcv, struct pt_regs *regs) void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs); void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs); +enum kprobe_insn __kprobes +kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi); + /* * Test if load/store instructions writeback the address register. * if P (bit 24) == 0 or W (bit 21) == 1 -- cgit v1.2.3 From 3d4a99785abee0687f8fad9a055d2f0c61a9dd57 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 14 Jun 2011 15:54:28 +0100 Subject: ARM: kprobes: Optimise emulation of LDM and STM This patch improves the performance of LDM and STM instruction emulation. This is desirable because. - jprobes and kretprobes probe the first instruction in a function and, when the frame pointer is omitted, this instruction is often a STM used to push registers onto the stack. - The STM and LDM instructions are common in the body and tail of functions. - At the same time as being a common instruction form, they also have one of the slowest and most complicated simulation routines. The approach taken to optimisation is to use emulation rather than simulation, that is, a modified form of the instruction is run with an appropriate register context. Benchmarking on an OMAP3530 shows the optimised emulation is between 2 and 3 times faster than the simulation routines. On a Kirkwood based device the relative performance was very significantly better than this. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-common.c | 68 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 43d663cafdd1..32bb0f236684 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -220,13 +220,81 @@ static void __kprobes simulate_ldm1_pc(struct kprobe *p, struct pt_regs *regs) load_write_pc(regs->ARM_pc, regs); } +static void __kprobes +emulate_generic_r0_12_noflags(struct kprobe *p, struct pt_regs *regs) +{ + register void *rregs asm("r1") = regs; + register void *rfn asm("lr") = p->ainsn.insn_fn; + + __asm__ __volatile__ ( + "stmdb sp!, {%[regs], r11} \n\t" + "ldmia %[regs], {r0-r12} \n\t" +#if __LINUX_ARM_ARCH__ >= 6 + "blx %[fn] \n\t" +#else + "str %[fn], [sp, #-4]! \n\t" + "adr lr, 1f \n\t" + "ldr pc, [sp], #4 \n\t" + "1: \n\t" +#endif + "ldr lr, [sp], #4 \n\t" /* lr = regs */ + "stmia lr, {r0-r12} \n\t" + "ldr r11, [sp], #4 \n\t" + : [regs] "=r" (rregs), [fn] "=r" (rfn) + : "0" (rregs), "1" (rfn) + : "r0", "r2", "r3", "r4", "r5", "r6", "r7", + "r8", "r9", "r10", "r12", "memory", "cc" + ); +} + +static void __kprobes +emulate_generic_r2_14_noflags(struct kprobe *p, struct pt_regs *regs) +{ + emulate_generic_r0_12_noflags(p, (struct pt_regs *)(regs->uregs+2)); +} + +static void __kprobes +emulate_ldm_r3_15(struct kprobe *p, struct pt_regs *regs) +{ + emulate_generic_r0_12_noflags(p, (struct pt_regs *)(regs->uregs+3)); + load_write_pc(regs->ARM_pc, regs); +} + enum kprobe_insn __kprobes kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) { kprobe_insn_handler_t *handler = 0; unsigned reglist = insn & 0xffff; int is_ldm = insn & 0x100000; + int rn = (insn >> 16) & 0xf; + + if (rn <= 12 && (reglist & 0xe000) == 0) { + /* Instruction only uses registers in the range R0..R12 */ + handler = emulate_generic_r0_12_noflags; + + } else if (rn >= 2 && (reglist & 0x8003) == 0) { + /* Instruction only uses registers in the range R2..R14 */ + rn -= 2; + reglist >>= 2; + handler = emulate_generic_r2_14_noflags; + + } else if (rn >= 3 && (reglist & 0x0007) == 0) { + /* Instruction only uses registers in the range R3..R15 */ + if (is_ldm && (reglist & 0x8000)) { + rn -= 3; + reglist >>= 3; + handler = emulate_ldm_r3_15; + } + } + + if (handler) { + /* We can emulate the instruction in (possibly) modified form */ + asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist; + asi->insn_handler = handler; + return INSN_GOOD; + } + /* Fallback to slower simulation... */ if (reglist & 0x8000) handler = is_ldm ? simulate_ldm1_pc : simulate_stm1_pc; else -- cgit v1.2.3 From eaf1d06500c48109dcd37b7856773fdf608a8d21 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 7 Jul 2011 08:59:32 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb load/store multiple instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 48 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 27f83a32a038..d25e5cbdd736 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -37,6 +37,48 @@ static inline unsigned long __kprobes thumb_probe_pc(struct kprobe *p) return (unsigned long)p->addr - 1 + 4; } +static enum kprobe_insn __kprobes +t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi); + + /* Fixup modified instruction to have halfwords in correct order...*/ + insn = asi->insn[0]; + ((u16 *)asi->insn)[0] = insn >> 16; + ((u16 *)asi->insn)[1] = insn & 0xffff; + + return ret; +} + +static const union decode_item t32_table_1110_100x_x0xx[] = { + /* Load/store multiple instructions */ + + /* Rn is PC 1110 100x x0xx 1111 xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfe4f0000, 0xe80f0000), + + /* SRS 1110 1000 00x0 xxxx xxxx xxxx xxxx xxxx */ + /* RFE 1110 1000 00x1 xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xffc00000, 0xe8000000), + /* SRS 1110 1001 10x0 xxxx xxxx xxxx xxxx xxxx */ + /* RFE 1110 1001 10x1 xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xffc00000, 0xe9800000), + + /* STM Rn, {...pc} 1110 100x x0x0 xxxx 1xxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfe508000, 0xe8008000), + /* LDM Rn, {...lr,pc} 1110 100x x0x1 xxxx 11xx xxxx xxxx xxxx */ + DECODE_REJECT (0xfe50c000, 0xe810c000), + /* LDM/STM Rn, {...sp} 1110 100x x0xx xxxx xx1x xxxx xxxx xxxx */ + DECODE_REJECT (0xfe402000, 0xe8002000), + + /* STMIA 1110 1000 10x0 xxxx xxxx xxxx xxxx xxxx */ + /* LDMIA 1110 1000 10x1 xxxx xxxx xxxx xxxx xxxx */ + /* STMDB 1110 1001 00x0 xxxx xxxx xxxx xxxx xxxx */ + /* LDMDB 1110 1001 00x1 xxxx xxxx xxxx xxxx xxxx */ + DECODE_CUSTOM (0xfe400000, 0xe8000000, t32_decode_ldmstm), + + DECODE_END +}; + static const union decode_item t32_table_1111_0xxx___1[] = { /* Branches and miscellaneous control */ @@ -54,6 +96,12 @@ static const union decode_item t32_table_1111_0xxx___1[] = { const union decode_item kprobe_decode_thumb32_table[] = { + /* + * Load/store multiple instructions + * 1110 100x x0xx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xfe400000, 0xe8000000, t32_table_1110_100x_x0xx), + /* * Branches and miscellaneous control * 1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx -- cgit v1.2.3 From b48354d3584e93284fba2ee99f6f9f44d18e4f83 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:23:21 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb load/store dual and load/store exclusive instructions We reject probing of load/store exclusive instructions because any emulation routine could never succeed in gaining exclusive access as the exception framework clears the exclusivity monitor when a probes breakpoint is hit. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 56 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index d25e5cbdd736..299dc3a33ad2 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -50,6 +50,33 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) return ret; } +static void __kprobes +t32_emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p) & ~3; + int rt1 = (insn >> 12) & 0xf; + int rt2 = (insn >> 8) & 0xf; + int rn = (insn >> 16) & 0xf; + + register unsigned long rt1v asm("r0") = regs->uregs[rt1]; + register unsigned long rt2v asm("r1") = regs->uregs[rt2]; + register unsigned long rnv asm("r2") = (rn == 15) ? pc + : regs->uregs[rn]; + + __asm__ __volatile__ ( + "blx %[fn]" + : "=r" (rt1v), "=r" (rt2v), "=r" (rnv) + : "0" (rt1v), "1" (rt2v), "2" (rnv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + if (rn != 15) + regs->uregs[rn] = rnv; /* Writeback base register */ + regs->uregs[rt1] = rt1v; + regs->uregs[rt2] = rt2v; +} + static const union decode_item t32_table_1110_100x_x0xx[] = { /* Load/store multiple instructions */ @@ -79,6 +106,29 @@ static const union decode_item t32_table_1110_100x_x0xx[] = { DECODE_END }; +static const union decode_item t32_table_1110_100x_x1xx[] = { + /* Load/store dual, load/store exclusive, table branch */ + + /* STRD (immediate) 1110 1000 x110 xxxx xxxx xxxx xxxx xxxx */ + /* LDRD (immediate) 1110 1000 x111 xxxx xxxx xxxx xxxx xxxx */ + DECODE_OR (0xff600000, 0xe8600000), + /* STRD (immediate) 1110 1001 x1x0 xxxx xxxx xxxx xxxx xxxx */ + /* LDRD (immediate) 1110 1001 x1x1 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xff400000, 0xe9400000, t32_emulate_ldrdstrd, + REGS(NOPCWB, NOSPPC, NOSPPC, 0, 0)), + + /* STREX 1110 1000 0100 xxxx xxxx xxxx xxxx xxxx */ + /* LDREX 1110 1000 0101 xxxx xxxx xxxx xxxx xxxx */ + /* STREXB 1110 1000 1100 xxxx xxxx xxxx 0100 xxxx */ + /* STREXH 1110 1000 1100 xxxx xxxx xxxx 0101 xxxx */ + /* STREXD 1110 1000 1100 xxxx xxxx xxxx 0111 xxxx */ + /* LDREXB 1110 1000 1101 xxxx xxxx xxxx 0100 xxxx */ + /* LDREXH 1110 1000 1101 xxxx xxxx xxxx 0101 xxxx */ + /* LDREXD 1110 1000 1101 xxxx xxxx xxxx 0111 xxxx */ + /* And unallocated instructions... */ + DECODE_END +}; + static const union decode_item t32_table_1111_0xxx___1[] = { /* Branches and miscellaneous control */ @@ -102,6 +152,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfe400000, 0xe8000000, t32_table_1110_100x_x0xx), + /* + * Load/store dual, load/store exclusive, table branch + * 1110 100x x1xx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xfe400000, 0xe8400000, t32_table_1110_100x_x1xx), + /* * Branches and miscellaneous control * 1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx -- cgit v1.2.3 From dd212bd3cbd337f8f3bd6b30929bef5a8c8ba81b Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:26:16 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb table branch instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 299dc3a33ad2..dfaea25c6069 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -37,6 +37,26 @@ static inline unsigned long __kprobes thumb_probe_pc(struct kprobe *p) return (unsigned long)p->addr - 1 + 4; } +static void __kprobes +t32_simulate_table_branch(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + unsigned long rnv = (rn == 15) ? pc : regs->uregs[rn]; + unsigned long rmv = regs->uregs[rm]; + unsigned int halfwords; + + if (insn & 0x10) + halfwords = ((u16 *)rnv)[rmv]; + else + halfwords = ((u8 *)rnv)[rmv]; + + regs->ARM_pc = pc + 2 * halfwords; +} + static enum kprobe_insn __kprobes t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) { @@ -117,6 +137,11 @@ static const union decode_item t32_table_1110_100x_x1xx[] = { DECODE_EMULATEX (0xff400000, 0xe9400000, t32_emulate_ldrdstrd, REGS(NOPCWB, NOSPPC, NOSPPC, 0, 0)), + /* TBB 1110 1000 1101 xxxx xxxx xxxx 0000 xxxx */ + /* TBH 1110 1000 1101 xxxx xxxx xxxx 0001 xxxx */ + DECODE_SIMULATEX(0xfff000e0, 0xe8d00000, t32_simulate_table_branch, + REGS(NOSP, 0, 0, 0, NOSPPC)), + /* STREX 1110 1000 0100 xxxx xxxx xxxx xxxx xxxx */ /* LDREX 1110 1000 0101 xxxx xxxx xxxx xxxx xxxx */ /* STREXB 1110 1000 1100 xxxx xxxx xxxx 0100 xxxx */ -- cgit v1.2.3 From 080e0013269e9fd428fd834e8a915a80fe6c8ae9 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:31:58 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb data-processing (shifted register) instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 93 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 93 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index dfaea25c6069..eac945ccf618 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -97,6 +97,33 @@ t32_emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs) regs->uregs[rt2] = rt2v; } +static void __kprobes +t32_emulate_rd8rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 8) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rdv asm("r1") = regs->uregs[rd]; + register unsigned long rnv asm("r2") = regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + unsigned long cpsr = regs->ARM_cpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + "blx %[fn] \n\t" + "mrs %[cpsr], cpsr \n\t" + : "=r" (rdv), [cpsr] "=r" (cpsr) + : "0" (rdv), "r" (rnv), "r" (rmv), + "1" (cpsr), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rd] = rdv; + regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); +} + static const union decode_item t32_table_1110_100x_x0xx[] = { /* Load/store multiple instructions */ @@ -154,6 +181,66 @@ static const union decode_item t32_table_1110_100x_x1xx[] = { DECODE_END }; +static const union decode_item t32_table_1110_101x[] = { + /* Data-processing (shifted register) */ + + /* TST 1110 1010 0001 xxxx xxxx 1111 xxxx xxxx */ + /* TEQ 1110 1010 1001 xxxx xxxx 1111 xxxx xxxx */ + DECODE_EMULATEX (0xff700f00, 0xea100f00, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, 0, 0, NOSPPC)), + + /* CMN 1110 1011 0001 xxxx xxxx 1111 xxxx xxxx */ + DECODE_OR (0xfff00f00, 0xeb100f00), + /* CMP 1110 1011 1011 xxxx xxxx 1111 xxxx xxxx */ + DECODE_EMULATEX (0xfff00f00, 0xebb00f00, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOPC, 0, 0, 0, NOSPPC)), + + /* MOV 1110 1010 010x 1111 xxxx xxxx xxxx xxxx */ + /* MVN 1110 1010 011x 1111 xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xffcf0000, 0xea4f0000, t32_emulate_rd8rn16rm0_rwflags, + REGS(0, 0, NOSPPC, 0, NOSPPC)), + + /* ??? 1110 1010 101x xxxx xxxx xxxx xxxx xxxx */ + /* ??? 1110 1010 111x xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xffa00000, 0xeaa00000), + /* ??? 1110 1011 001x xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xffe00000, 0xeb200000), + /* ??? 1110 1011 100x xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xffe00000, 0xeb800000), + /* ??? 1110 1011 111x xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xffe00000, 0xebe00000), + + /* ADD/SUB SP, SP, Rm, LSL #0..3 */ + /* 1110 1011 x0xx 1101 x000 1101 xx00 xxxx */ + DECODE_EMULATEX (0xff4f7f30, 0xeb0d0d00, t32_emulate_rd8rn16rm0_rwflags, + REGS(SP, 0, SP, 0, NOSPPC)), + + /* ADD/SUB SP, SP, Rm, shift */ + /* 1110 1011 x0xx 1101 xxxx 1101 xxxx xxxx */ + DECODE_REJECT (0xff4f0f00, 0xeb0d0d00), + + /* ADD/SUB Rd, SP, Rm, shift */ + /* 1110 1011 x0xx 1101 xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xff4f0000, 0xeb0d0000, t32_emulate_rd8rn16rm0_rwflags, + REGS(SP, 0, NOPC, 0, NOSPPC)), + + /* AND 1110 1010 000x xxxx xxxx xxxx xxxx xxxx */ + /* BIC 1110 1010 001x xxxx xxxx xxxx xxxx xxxx */ + /* ORR 1110 1010 010x xxxx xxxx xxxx xxxx xxxx */ + /* ORN 1110 1010 011x xxxx xxxx xxxx xxxx xxxx */ + /* EOR 1110 1010 100x xxxx xxxx xxxx xxxx xxxx */ + /* PKH 1110 1010 110x xxxx xxxx xxxx xxxx xxxx */ + /* ADD 1110 1011 000x xxxx xxxx xxxx xxxx xxxx */ + /* ADC 1110 1011 010x xxxx xxxx xxxx xxxx xxxx */ + /* SBC 1110 1011 011x xxxx xxxx xxxx xxxx xxxx */ + /* SUB 1110 1011 101x xxxx xxxx xxxx xxxx xxxx */ + /* RSB 1110 1011 110x xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfe000000, 0xea000000, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)), + + DECODE_END +}; + static const union decode_item t32_table_1111_0xxx___1[] = { /* Branches and miscellaneous control */ @@ -183,6 +270,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfe400000, 0xe8400000, t32_table_1110_100x_x1xx), + /* + * Data-processing (shifted register) + * 1110 101x xxxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xfe000000, 0xea000000, t32_table_1110_101x), + /* * Branches and miscellaneous control * 1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx -- cgit v1.2.3 From 2fcaf7e75804dbb75862a230a5a19d0508153324 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:36:35 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb data-processing (modified immediate) instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 58 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index eac945ccf618..cf834484fb58 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -241,6 +241,58 @@ static const union decode_item t32_table_1110_101x[] = { DECODE_END }; +static const union decode_item t32_table_1111_0x0x___0[] = { + /* Data-processing (modified immediate) */ + + /* TST 1111 0x00 0001 xxxx 0xxx 1111 xxxx xxxx */ + /* TEQ 1111 0x00 1001 xxxx 0xxx 1111 xxxx xxxx */ + DECODE_EMULATEX (0xfb708f00, 0xf0100f00, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, 0, 0, 0)), + + /* CMN 1111 0x01 0001 xxxx 0xxx 1111 xxxx xxxx */ + DECODE_OR (0xfbf08f00, 0xf1100f00), + /* CMP 1111 0x01 1011 xxxx 0xxx 1111 xxxx xxxx */ + DECODE_EMULATEX (0xfbf08f00, 0xf1b00f00, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOPC, 0, 0, 0, 0)), + + /* MOV 1111 0x00 010x 1111 0xxx xxxx xxxx xxxx */ + /* MVN 1111 0x00 011x 1111 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfbcf8000, 0xf04f0000, t32_emulate_rd8rn16rm0_rwflags, + REGS(0, 0, NOSPPC, 0, 0)), + + /* ??? 1111 0x00 101x xxxx 0xxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfbe08000, 0xf0a00000), + /* ??? 1111 0x00 110x xxxx 0xxx xxxx xxxx xxxx */ + /* ??? 1111 0x00 111x xxxx 0xxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfbc08000, 0xf0c00000), + /* ??? 1111 0x01 001x xxxx 0xxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfbe08000, 0xf1200000), + /* ??? 1111 0x01 100x xxxx 0xxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfbe08000, 0xf1800000), + /* ??? 1111 0x01 111x xxxx 0xxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfbe08000, 0xf1e00000), + + /* ADD Rd, SP, #imm 1111 0x01 000x 1101 0xxx xxxx xxxx xxxx */ + /* SUB Rd, SP, #imm 1111 0x01 101x 1101 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfb4f8000, 0xf10d0000, t32_emulate_rd8rn16rm0_rwflags, + REGS(SP, 0, NOPC, 0, 0)), + + /* AND 1111 0x00 000x xxxx 0xxx xxxx xxxx xxxx */ + /* BIC 1111 0x00 001x xxxx 0xxx xxxx xxxx xxxx */ + /* ORR 1111 0x00 010x xxxx 0xxx xxxx xxxx xxxx */ + /* ORN 1111 0x00 011x xxxx 0xxx xxxx xxxx xxxx */ + /* EOR 1111 0x00 100x xxxx 0xxx xxxx xxxx xxxx */ + /* ADD 1111 0x01 000x xxxx 0xxx xxxx xxxx xxxx */ + /* ADC 1111 0x01 010x xxxx 0xxx xxxx xxxx xxxx */ + /* SBC 1111 0x01 011x xxxx 0xxx xxxx xxxx xxxx */ + /* SUB 1111 0x01 101x xxxx 0xxx xxxx xxxx xxxx */ + /* RSB 1111 0x01 110x xxxx 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfa008000, 0xf0000000, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, NOSPPC, 0, 0)), + + DECODE_END +}; + static const union decode_item t32_table_1111_0xxx___1[] = { /* Branches and miscellaneous control */ @@ -276,6 +328,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfe000000, 0xea000000, t32_table_1110_101x), + /* + * Data-processing (modified immediate) + * 1111 0x0x xxxx xxxx 0xxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xfa008000, 0xf0000000, t32_table_1111_0x0x___0), + /* * Branches and miscellaneous control * 1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx -- cgit v1.2.3 From 7848786a7a198dd5e097330ad0cbfdf155a25499 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:40:26 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb data-processing (plain binary immediate) instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 95 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 95 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index cf834484fb58..1fbeba8093f1 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -124,6 +124,46 @@ t32_emulate_rd8rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs) regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); } +static void __kprobes +t32_emulate_rd8pc16_noflags(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + int rd = (insn >> 8) & 0xf; + + register unsigned long rdv asm("r1") = regs->uregs[rd]; + register unsigned long rnv asm("r2") = pc & ~3; + + __asm__ __volatile__ ( + "blx %[fn]" + : "=r" (rdv) + : "0" (rdv), "r" (rnv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rd] = rdv; +} + +static void __kprobes +t32_emulate_rd8rn16_noflags(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 8) & 0xf; + int rn = (insn >> 16) & 0xf; + + register unsigned long rdv asm("r1") = regs->uregs[rd]; + register unsigned long rnv asm("r2") = regs->uregs[rn]; + + __asm__ __volatile__ ( + "blx %[fn]" + : "=r" (rdv) + : "0" (rdv), "r" (rnv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rd] = rdv; +} + static const union decode_item t32_table_1110_100x_x0xx[] = { /* Load/store multiple instructions */ @@ -293,6 +333,55 @@ static const union decode_item t32_table_1111_0x0x___0[] = { DECODE_END }; +static const union decode_item t32_table_1111_0x1x___0[] = { + /* Data-processing (plain binary immediate) */ + + /* ADDW Rd, PC, #imm 1111 0x10 0000 1111 0xxx xxxx xxxx xxxx */ + DECODE_OR (0xfbff8000, 0xf20f0000), + /* SUBW Rd, PC, #imm 1111 0x10 1010 1111 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfbff8000, 0xf2af0000, t32_emulate_rd8pc16_noflags, + REGS(PC, 0, NOSPPC, 0, 0)), + + /* ADDW SP, SP, #imm 1111 0x10 0000 1101 0xxx 1101 xxxx xxxx */ + DECODE_OR (0xfbff8f00, 0xf20d0d00), + /* SUBW SP, SP, #imm 1111 0x10 1010 1101 0xxx 1101 xxxx xxxx */ + DECODE_EMULATEX (0xfbff8f00, 0xf2ad0d00, t32_emulate_rd8rn16_noflags, + REGS(SP, 0, SP, 0, 0)), + + /* ADDW 1111 0x10 0000 xxxx 0xxx xxxx xxxx xxxx */ + DECODE_OR (0xfbf08000, 0xf2000000), + /* SUBW 1111 0x10 1010 xxxx 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfbf08000, 0xf2a00000, t32_emulate_rd8rn16_noflags, + REGS(NOPCX, 0, NOSPPC, 0, 0)), + + /* MOVW 1111 0x10 0100 xxxx 0xxx xxxx xxxx xxxx */ + /* MOVT 1111 0x10 1100 xxxx 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfb708000, 0xf2400000, t32_emulate_rd8rn16_noflags, + REGS(0, 0, NOSPPC, 0, 0)), + + /* SSAT16 1111 0x11 0010 xxxx 0000 xxxx 00xx xxxx */ + /* SSAT 1111 0x11 00x0 xxxx 0xxx xxxx xxxx xxxx */ + /* USAT16 1111 0x11 1010 xxxx 0000 xxxx 00xx xxxx */ + /* USAT 1111 0x11 10x0 xxxx 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfb508000, 0xf3000000, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, NOSPPC, 0, 0)), + + /* SFBX 1111 0x11 0100 xxxx 0xxx xxxx xxxx xxxx */ + /* UFBX 1111 0x11 1100 xxxx 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfb708000, 0xf3400000, t32_emulate_rd8rn16_noflags, + REGS(NOSPPC, 0, NOSPPC, 0, 0)), + + /* BFC 1111 0x11 0110 1111 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfbff8000, 0xf36f0000, t32_emulate_rd8rn16_noflags, + REGS(0, 0, NOSPPC, 0, 0)), + + /* BFI 1111 0x11 0110 xxxx 0xxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfbf08000, 0xf3600000, t32_emulate_rd8rn16_noflags, + REGS(NOSPPCX, 0, NOSPPC, 0, 0)), + + DECODE_END +}; + static const union decode_item t32_table_1111_0xxx___1[] = { /* Branches and miscellaneous control */ @@ -334,6 +423,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfa008000, 0xf0000000, t32_table_1111_0x0x___0), + /* + * Data-processing (plain binary immediate) + * 1111 0x1x xxxx xxxx 0xxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xfa008000, 0xf2000000, t32_table_1111_0x1x___0), + /* * Branches and miscellaneous control * 1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx -- cgit v1.2.3 From b06f3ee34d8b817d566d15d25a21f8320b3f7c57 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:52:18 +0100 Subject: ARM: kprobes: Decode 32-bit miscellaneous control instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 1fbeba8093f1..c07c2470ccaa 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -57,6 +57,15 @@ t32_simulate_table_branch(struct kprobe *p, struct pt_regs *regs) regs->ARM_pc = pc + 2 * halfwords; } +static void __kprobes +t32_simulate_mrs(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 8) & 0xf; + unsigned long mask = 0xf8ff03df; /* Mask out execution state */ + regs->uregs[rd] = regs->ARM_cpsr & mask; +} + static enum kprobe_insn __kprobes t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) { @@ -394,6 +403,28 @@ static const union decode_item t32_table_1111_0xxx___1[] = { /* WFI 1111 0011 1010 xxxx 10x0 x000 0000 0011 */ DECODE_SIMULATE (0xfff0d7fc, 0xf3a08000, kprobe_simulate_nop), + /* MRS Rd, CPSR 1111 0011 1110 xxxx 10x0 xxxx xxxx xxxx */ + DECODE_SIMULATEX(0xfff0d000, 0xf3e08000, t32_simulate_mrs, + REGS(0, 0, NOSPPC, 0, 0)), + + /* + * Unsupported instructions + * 1111 0x11 1xxx xxxx 10x0 xxxx xxxx xxxx + * + * MSR 1111 0011 100x xxxx 10x0 xxxx xxxx xxxx + * DBG hint 1111 0011 1010 xxxx 10x0 x000 1111 xxxx + * Unallocated hints 1111 0011 1010 xxxx 10x0 x000 xxxx xxxx + * CPS 1111 0011 1010 xxxx 10x0 xxxx xxxx xxxx + * CLREX/DSB/DMB/ISB 1111 0011 1011 xxxx 10x0 xxxx xxxx xxxx + * BXJ 1111 0011 1100 xxxx 10x0 xxxx xxxx xxxx + * SUBS PC,LR,# 1111 0011 1101 xxxx 10x0 xxxx xxxx xxxx + * MRS Rd, SPSR 1111 0011 1111 xxxx 10x0 xxxx xxxx xxxx + * SMC 1111 0111 1111 xxxx 1000 xxxx xxxx xxxx + * UNDEFINED 1111 0111 1111 xxxx 1010 xxxx xxxx xxxx + * ??? 1111 0111 1xxx xxxx 1010 xxxx xxxx xxxx + */ + DECODE_REJECT (0xfb80d000, 0xf3808000), + DECODE_END }; -- cgit v1.2.3 From ce715c772f0124f9d3f6f5cffcb85688c81d2c07 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:53:45 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb branch instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 65 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 63 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index c07c2470ccaa..1677234000b2 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -49,9 +49,9 @@ t32_simulate_table_branch(struct kprobe *p, struct pt_regs *regs) unsigned long rmv = regs->uregs[rm]; unsigned int halfwords; - if (insn & 0x10) + if (insn & 0x10) /* TBH */ halfwords = ((u16 *)rnv)[rmv]; - else + else /* TBB */ halfwords = ((u8 *)rnv)[rmv]; regs->ARM_pc = pc + 2 * halfwords; @@ -66,6 +66,58 @@ t32_simulate_mrs(struct kprobe *p, struct pt_regs *regs) regs->uregs[rd] = regs->ARM_cpsr & mask; } +static void __kprobes +t32_simulate_cond_branch(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + + long offset = insn & 0x7ff; /* imm11 */ + offset += (insn & 0x003f0000) >> 5; /* imm6 */ + offset += (insn & 0x00002000) << 4; /* J1 */ + offset += (insn & 0x00000800) << 7; /* J2 */ + offset -= (insn & 0x04000000) >> 7; /* Apply sign bit */ + + regs->ARM_pc = pc + (offset * 2); +} + +static enum kprobe_insn __kprobes +t32_decode_cond_branch(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + int cc = (insn >> 22) & 0xf; + asi->insn_check_cc = kprobe_condition_checks[cc]; + asi->insn_handler = t32_simulate_cond_branch; + return INSN_GOOD_NO_SLOT; +} + +static void __kprobes +t32_simulate_branch(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = thumb_probe_pc(p); + + long offset = insn & 0x7ff; /* imm11 */ + offset += (insn & 0x03ff0000) >> 5; /* imm10 */ + offset += (insn & 0x00002000) << 9; /* J1 */ + offset += (insn & 0x00000800) << 10; /* J2 */ + if (insn & 0x04000000) + offset -= 0x00800000; /* Apply sign bit */ + else + offset ^= 0x00600000; /* Invert J1 and J2 */ + + if (insn & (1 << 14)) { + /* BL or BLX */ + regs->ARM_lr = (unsigned long)p->addr + 4; + if (!(insn & (1 << 12))) { + /* BLX so switch to ARM mode */ + regs->ARM_cpsr &= ~PSR_T_BIT; + pc &= ~3; + } + } + + regs->ARM_pc = pc + (offset * 2); +} + static enum kprobe_insn __kprobes t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) { @@ -425,6 +477,15 @@ static const union decode_item t32_table_1111_0xxx___1[] = { */ DECODE_REJECT (0xfb80d000, 0xf3808000), + /* Bcc 1111 0xxx xxxx xxxx 10x0 xxxx xxxx xxxx */ + DECODE_CUSTOM (0xf800d000, 0xf0008000, t32_decode_cond_branch), + + /* BLX 1111 0xxx xxxx xxxx 11x0 xxxx xxxx xxx0 */ + DECODE_OR (0xf800d001, 0xf000c000), + /* B 1111 0xxx xxxx xxxx 10x1 xxxx xxxx xxxx */ + /* BL 1111 0xxx xxxx xxxx 11x1 xxxx xxxx xxxx */ + DECODE_SIMULATE (0xf8009000, 0xf0009000, t32_simulate_branch), + DECODE_END }; -- cgit v1.2.3 From 6a0d1a1c5692d6192684fb7aa8f4d7f401f8dbab Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 14:57:18 +0100 Subject: ARM: kprobes: Reject 32-bit Thumb coprocessor and SIMD instructions The kernel doesn't currently support VFP or Neon code, and probing of code with CP15 operations is fraught with bad consequences. So we will just reject probing these instructions. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 1677234000b2..6cc51b48762f 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -509,6 +509,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfe000000, 0xea000000, t32_table_1110_101x), + /* + * Coprocessor instructions + * 1110 11xx xxxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_REJECT (0xfc000000, 0xec000000), + /* * Data-processing (modified immediate) * 1111 0x0x xxxx xxxx 0xxx xxxx xxxx xxxx @@ -527,6 +533,16 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xf8008000, 0xf0008000, t32_table_1111_0xxx___1), + /* + * Advanced SIMD element or structure load/store instructions + * 1111 1001 xxx0 xxxx xxxx xxxx xxxx xxxx + */ + DECODE_REJECT (0xff100000, 0xf9000000), + + /* + * Coprocessor instructions + * 1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx + */ DECODE_END }; -- cgit v1.2.3 From 46009cc5c59e0acdf165ed8a9d1ccc43baf44800 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 15:00:42 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb memory hint instructions We'll treat the preload instructions as nops as they are just performance hints. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 6cc51b48762f..bf1113c89b15 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -489,6 +489,33 @@ static const union decode_item t32_table_1111_0xxx___1[] = { DECODE_END }; +static const union decode_item t32_table_1111_100x_x0x1__1111[] = { + /* Memory hints */ + + /* PLD (literal) 1111 1000 x001 1111 1111 xxxx xxxx xxxx */ + /* PLI (literal) 1111 1001 x001 1111 1111 xxxx xxxx xxxx */ + DECODE_SIMULATE (0xfe7ff000, 0xf81ff000, kprobe_simulate_nop), + + /* PLD{W} (immediate) 1111 1000 10x1 xxxx 1111 xxxx xxxx xxxx */ + DECODE_OR (0xffd0f000, 0xf890f000), + /* PLD{W} (immediate) 1111 1000 00x1 xxxx 1111 1100 xxxx xxxx */ + DECODE_OR (0xffd0ff00, 0xf810fc00), + /* PLI (immediate) 1111 1001 1001 xxxx 1111 xxxx xxxx xxxx */ + DECODE_OR (0xfff0f000, 0xf990f000), + /* PLI (immediate) 1111 1001 0001 xxxx 1111 1100 xxxx xxxx */ + DECODE_SIMULATEX(0xfff0ff00, 0xf910fc00, kprobe_simulate_nop, + REGS(NOPCX, 0, 0, 0, 0)), + + /* PLD{W} (register) 1111 1000 00x1 xxxx 1111 0000 00xx xxxx */ + DECODE_OR (0xffd0ffc0, 0xf810f000), + /* PLI (register) 1111 1001 0001 xxxx 1111 0000 00xx xxxx */ + DECODE_SIMULATEX(0xfff0ffc0, 0xf910f000, kprobe_simulate_nop, + REGS(NOPCX, 0, 0, 0, NOSPPC)), + + /* Other unallocated instructions... */ + DECODE_END +}; + const union decode_item kprobe_decode_thumb32_table[] = { /* @@ -539,6 +566,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_REJECT (0xff100000, 0xf9000000), + /* + * Memory hints + * 1111 100x x0x1 xxxx 1111 xxxx xxxx xxxx + */ + DECODE_TABLE (0xfe50f000, 0xf810f000, t32_table_1111_100x_x0x1__1111), + /* * Coprocessor instructions * 1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx -- cgit v1.2.3 From d691023b62bdf33ed84023330f4d2c77d2325b01 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 15:04:26 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb load/store single data item instructions We will reject probing of unprivileged load and store instructions. These rarely occur and writing test cases for them is difficult. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 153 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index bf1113c89b15..9be8bea2990c 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -118,6 +118,44 @@ t32_simulate_branch(struct kprobe *p, struct pt_regs *regs) regs->ARM_pc = pc + (offset * 2); } +static void __kprobes +t32_simulate_ldr_literal(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long addr = thumb_probe_pc(p) & ~3; + int rt = (insn >> 12) & 0xf; + unsigned long rtv; + + long offset = insn & 0xfff; + if (insn & 0x00800000) + addr += offset; + else + addr -= offset; + + if (insn & 0x00400000) { + /* LDR */ + rtv = *(unsigned long *)addr; + if (rt == 15) { + bx_write_pc(rtv, regs); + return; + } + } else if (insn & 0x00200000) { + /* LDRH */ + if (insn & 0x01000000) + rtv = *(s16 *)addr; + else + rtv = *(u16 *)addr; + } else { + /* LDRB */ + if (insn & 0x01000000) + rtv = *(s8 *)addr; + else + rtv = *(u8 *)addr; + } + + regs->uregs[rt] = rtv; +} + static enum kprobe_insn __kprobes t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi) { @@ -158,6 +196,32 @@ t32_emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs) regs->uregs[rt2] = rt2v; } +static void __kprobes +t32_emulate_ldrstr(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rt = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rtv asm("r0") = regs->uregs[rt]; + register unsigned long rnv asm("r2") = regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + + __asm__ __volatile__ ( + "blx %[fn]" + : "=r" (rtv), "=r" (rnv) + : "0" (rtv), "1" (rnv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rn] = rnv; /* Writeback base register */ + if (rt == 15) /* Can't be true for a STR as they aren't allowed */ + bx_write_pc(rtv, regs); + else + regs->uregs[rt] = rtv; +} + static void __kprobes t32_emulate_rd8rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs) { @@ -516,6 +580,87 @@ static const union decode_item t32_table_1111_100x_x0x1__1111[] = { DECODE_END }; +static const union decode_item t32_table_1111_100x[] = { + /* Store/Load single data item */ + + /* ??? 1111 100x x11x xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfe600000, 0xf8600000), + + /* ??? 1111 1001 0101 xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xfff00000, 0xf9500000), + + /* ??? 1111 100x 0xxx xxxx xxxx 10x0 xxxx xxxx */ + DECODE_REJECT (0xfe800d00, 0xf8000800), + + /* STRBT 1111 1000 0000 xxxx xxxx 1110 xxxx xxxx */ + /* STRHT 1111 1000 0010 xxxx xxxx 1110 xxxx xxxx */ + /* STRT 1111 1000 0100 xxxx xxxx 1110 xxxx xxxx */ + /* LDRBT 1111 1000 0001 xxxx xxxx 1110 xxxx xxxx */ + /* LDRSBT 1111 1001 0001 xxxx xxxx 1110 xxxx xxxx */ + /* LDRHT 1111 1000 0011 xxxx xxxx 1110 xxxx xxxx */ + /* LDRSHT 1111 1001 0011 xxxx xxxx 1110 xxxx xxxx */ + /* LDRT 1111 1000 0101 xxxx xxxx 1110 xxxx xxxx */ + DECODE_REJECT (0xfe800f00, 0xf8000e00), + + /* STR{,B,H} Rn,[PC...] 1111 1000 xxx0 1111 xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0xff1f0000, 0xf80f0000), + + /* STR{,B,H} PC,[Rn...] 1111 1000 xxx0 xxxx 1111 xxxx xxxx xxxx */ + DECODE_REJECT (0xff10f000, 0xf800f000), + + /* LDR (literal) 1111 1000 x101 1111 xxxx xxxx xxxx xxxx */ + DECODE_SIMULATEX(0xff7f0000, 0xf85f0000, t32_simulate_ldr_literal, + REGS(PC, ANY, 0, 0, 0)), + + /* STR (immediate) 1111 1000 0100 xxxx xxxx 1xxx xxxx xxxx */ + /* LDR (immediate) 1111 1000 0101 xxxx xxxx 1xxx xxxx xxxx */ + DECODE_OR (0xffe00800, 0xf8400800), + /* STR (immediate) 1111 1000 1100 xxxx xxxx xxxx xxxx xxxx */ + /* LDR (immediate) 1111 1000 1101 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xffe00000, 0xf8c00000, t32_emulate_ldrstr, + REGS(NOPCX, ANY, 0, 0, 0)), + + /* STR (register) 1111 1000 0100 xxxx xxxx 0000 00xx xxxx */ + /* LDR (register) 1111 1000 0101 xxxx xxxx 0000 00xx xxxx */ + DECODE_EMULATEX (0xffe00fc0, 0xf8400000, t32_emulate_ldrstr, + REGS(NOPCX, ANY, 0, 0, NOSPPC)), + + /* LDRB (literal) 1111 1000 x001 1111 xxxx xxxx xxxx xxxx */ + /* LDRSB (literal) 1111 1001 x001 1111 xxxx xxxx xxxx xxxx */ + /* LDRH (literal) 1111 1000 x011 1111 xxxx xxxx xxxx xxxx */ + /* LDRSH (literal) 1111 1001 x011 1111 xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfe5f0000, 0xf81f0000, t32_simulate_ldr_literal, + REGS(PC, NOSPPCX, 0, 0, 0)), + + /* STRB (immediate) 1111 1000 0000 xxxx xxxx 1xxx xxxx xxxx */ + /* STRH (immediate) 1111 1000 0010 xxxx xxxx 1xxx xxxx xxxx */ + /* LDRB (immediate) 1111 1000 0001 xxxx xxxx 1xxx xxxx xxxx */ + /* LDRSB (immediate) 1111 1001 0001 xxxx xxxx 1xxx xxxx xxxx */ + /* LDRH (immediate) 1111 1000 0011 xxxx xxxx 1xxx xxxx xxxx */ + /* LDRSH (immediate) 1111 1001 0011 xxxx xxxx 1xxx xxxx xxxx */ + DECODE_OR (0xfec00800, 0xf8000800), + /* STRB (immediate) 1111 1000 1000 xxxx xxxx xxxx xxxx xxxx */ + /* STRH (immediate) 1111 1000 1010 xxxx xxxx xxxx xxxx xxxx */ + /* LDRB (immediate) 1111 1000 1001 xxxx xxxx xxxx xxxx xxxx */ + /* LDRSB (immediate) 1111 1001 1001 xxxx xxxx xxxx xxxx xxxx */ + /* LDRH (immediate) 1111 1000 1011 xxxx xxxx xxxx xxxx xxxx */ + /* LDRSH (immediate) 1111 1001 1011 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0xfec00000, 0xf8800000, t32_emulate_ldrstr, + REGS(NOPCX, NOSPPCX, 0, 0, 0)), + + /* STRB (register) 1111 1000 0000 xxxx xxxx 0000 00xx xxxx */ + /* STRH (register) 1111 1000 0010 xxxx xxxx 0000 00xx xxxx */ + /* LDRB (register) 1111 1000 0001 xxxx xxxx 0000 00xx xxxx */ + /* LDRSB (register) 1111 1001 0001 xxxx xxxx 0000 00xx xxxx */ + /* LDRH (register) 1111 1000 0011 xxxx xxxx 0000 00xx xxxx */ + /* LDRSH (register) 1111 1001 0011 xxxx xxxx 0000 00xx xxxx */ + DECODE_EMULATEX (0xfe800fc0, 0xf8000000, t32_emulate_ldrstr, + REGS(NOPCX, NOSPPCX, 0, 0, NOSPPC)), + + /* Other unallocated instructions... */ + DECODE_END +}; + const union decode_item kprobe_decode_thumb32_table[] = { /* @@ -572,6 +717,14 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfe50f000, 0xf810f000, t32_table_1111_100x_x0x1__1111), + /* + * Store single data item + * 1111 1000 xxx0 xxxx xxxx xxxx xxxx xxxx + * Load single data items + * 1111 100x xxx1 xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xfe000000, 0xf8000000, t32_table_1111_100x), + /* * Coprocessor instructions * 1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx -- cgit v1.2.3 From 31656c1a9a9872e2621b2b952294bdea4c23f5bd Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 15:07:19 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb data-processing (register) instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 108 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 108 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 9be8bea2990c..7c32e5b03cee 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -661,6 +661,108 @@ static const union decode_item t32_table_1111_100x[] = { DECODE_END }; +static const union decode_item t32_table_1111_1010___1111[] = { + /* Data-processing (register) */ + + /* ??? 1111 1010 011x xxxx 1111 xxxx 1xxx xxxx */ + DECODE_REJECT (0xffe0f080, 0xfa60f080), + + /* SXTH 1111 1010 0000 1111 1111 xxxx 1xxx xxxx */ + /* UXTH 1111 1010 0001 1111 1111 xxxx 1xxx xxxx */ + /* SXTB16 1111 1010 0010 1111 1111 xxxx 1xxx xxxx */ + /* UXTB16 1111 1010 0011 1111 1111 xxxx 1xxx xxxx */ + /* SXTB 1111 1010 0100 1111 1111 xxxx 1xxx xxxx */ + /* UXTB 1111 1010 0101 1111 1111 xxxx 1xxx xxxx */ + DECODE_EMULATEX (0xff8ff080, 0xfa0ff080, t32_emulate_rd8rn16rm0_rwflags, + REGS(0, 0, NOSPPC, 0, NOSPPC)), + + + /* ??? 1111 1010 1xxx xxxx 1111 xxxx 0x11 xxxx */ + DECODE_REJECT (0xff80f0b0, 0xfa80f030), + /* ??? 1111 1010 1x11 xxxx 1111 xxxx 0xxx xxxx */ + DECODE_REJECT (0xffb0f080, 0xfab0f000), + + /* SADD16 1111 1010 1001 xxxx 1111 xxxx 0000 xxxx */ + /* SASX 1111 1010 1010 xxxx 1111 xxxx 0000 xxxx */ + /* SSAX 1111 1010 1110 xxxx 1111 xxxx 0000 xxxx */ + /* SSUB16 1111 1010 1101 xxxx 1111 xxxx 0000 xxxx */ + /* SADD8 1111 1010 1000 xxxx 1111 xxxx 0000 xxxx */ + /* SSUB8 1111 1010 1100 xxxx 1111 xxxx 0000 xxxx */ + + /* QADD16 1111 1010 1001 xxxx 1111 xxxx 0001 xxxx */ + /* QASX 1111 1010 1010 xxxx 1111 xxxx 0001 xxxx */ + /* QSAX 1111 1010 1110 xxxx 1111 xxxx 0001 xxxx */ + /* QSUB16 1111 1010 1101 xxxx 1111 xxxx 0001 xxxx */ + /* QADD8 1111 1010 1000 xxxx 1111 xxxx 0001 xxxx */ + /* QSUB8 1111 1010 1100 xxxx 1111 xxxx 0001 xxxx */ + + /* SHADD16 1111 1010 1001 xxxx 1111 xxxx 0010 xxxx */ + /* SHASX 1111 1010 1010 xxxx 1111 xxxx 0010 xxxx */ + /* SHSAX 1111 1010 1110 xxxx 1111 xxxx 0010 xxxx */ + /* SHSUB16 1111 1010 1101 xxxx 1111 xxxx 0010 xxxx */ + /* SHADD8 1111 1010 1000 xxxx 1111 xxxx 0010 xxxx */ + /* SHSUB8 1111 1010 1100 xxxx 1111 xxxx 0010 xxxx */ + + /* UADD16 1111 1010 1001 xxxx 1111 xxxx 0100 xxxx */ + /* UASX 1111 1010 1010 xxxx 1111 xxxx 0100 xxxx */ + /* USAX 1111 1010 1110 xxxx 1111 xxxx 0100 xxxx */ + /* USUB16 1111 1010 1101 xxxx 1111 xxxx 0100 xxxx */ + /* UADD8 1111 1010 1000 xxxx 1111 xxxx 0100 xxxx */ + /* USUB8 1111 1010 1100 xxxx 1111 xxxx 0100 xxxx */ + + /* UQADD16 1111 1010 1001 xxxx 1111 xxxx 0101 xxxx */ + /* UQASX 1111 1010 1010 xxxx 1111 xxxx 0101 xxxx */ + /* UQSAX 1111 1010 1110 xxxx 1111 xxxx 0101 xxxx */ + /* UQSUB16 1111 1010 1101 xxxx 1111 xxxx 0101 xxxx */ + /* UQADD8 1111 1010 1000 xxxx 1111 xxxx 0101 xxxx */ + /* UQSUB8 1111 1010 1100 xxxx 1111 xxxx 0101 xxxx */ + + /* UHADD16 1111 1010 1001 xxxx 1111 xxxx 0110 xxxx */ + /* UHASX 1111 1010 1010 xxxx 1111 xxxx 0110 xxxx */ + /* UHSAX 1111 1010 1110 xxxx 1111 xxxx 0110 xxxx */ + /* UHSUB16 1111 1010 1101 xxxx 1111 xxxx 0110 xxxx */ + /* UHADD8 1111 1010 1000 xxxx 1111 xxxx 0110 xxxx */ + /* UHSUB8 1111 1010 1100 xxxx 1111 xxxx 0110 xxxx */ + DECODE_OR (0xff80f080, 0xfa80f000), + + /* SXTAH 1111 1010 0000 xxxx 1111 xxxx 1xxx xxxx */ + /* UXTAH 1111 1010 0001 xxxx 1111 xxxx 1xxx xxxx */ + /* SXTAB16 1111 1010 0010 xxxx 1111 xxxx 1xxx xxxx */ + /* UXTAB16 1111 1010 0011 xxxx 1111 xxxx 1xxx xxxx */ + /* SXTAB 1111 1010 0100 xxxx 1111 xxxx 1xxx xxxx */ + /* UXTAB 1111 1010 0101 xxxx 1111 xxxx 1xxx xxxx */ + DECODE_OR (0xff80f080, 0xfa00f080), + + /* QADD 1111 1010 1000 xxxx 1111 xxxx 1000 xxxx */ + /* QDADD 1111 1010 1000 xxxx 1111 xxxx 1001 xxxx */ + /* QSUB 1111 1010 1000 xxxx 1111 xxxx 1010 xxxx */ + /* QDSUB 1111 1010 1000 xxxx 1111 xxxx 1011 xxxx */ + DECODE_OR (0xfff0f0c0, 0xfa80f080), + + /* SEL 1111 1010 1010 xxxx 1111 xxxx 1000 xxxx */ + DECODE_OR (0xfff0f0f0, 0xfaa0f080), + + /* LSL 1111 1010 000x xxxx 1111 xxxx 0000 xxxx */ + /* LSR 1111 1010 001x xxxx 1111 xxxx 0000 xxxx */ + /* ASR 1111 1010 010x xxxx 1111 xxxx 0000 xxxx */ + /* ROR 1111 1010 011x xxxx 1111 xxxx 0000 xxxx */ + DECODE_EMULATEX (0xff80f0f0, 0xfa00f000, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)), + + /* CLZ 1111 1010 1010 xxxx 1111 xxxx 1000 xxxx */ + DECODE_OR (0xfff0f0f0, 0xfab0f080), + + /* REV 1111 1010 1001 xxxx 1111 xxxx 1000 xxxx */ + /* REV16 1111 1010 1001 xxxx 1111 xxxx 1001 xxxx */ + /* RBIT 1111 1010 1001 xxxx 1111 xxxx 1010 xxxx */ + /* REVSH 1111 1010 1001 xxxx 1111 xxxx 1011 xxxx */ + DECODE_EMULATEX (0xfff0f0c0, 0xfa90f080, t32_emulate_rd8rn16_noflags, + REGS(NOSPPC, 0, NOSPPC, 0, SAMEAS16)), + + /* Other unallocated instructions... */ + DECODE_END +}; + const union decode_item kprobe_decode_thumb32_table[] = { /* @@ -725,6 +827,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xfe000000, 0xf8000000, t32_table_1111_100x), + /* + * Data-processing (register) + * 1111 1010 xxxx xxxx 1111 xxxx xxxx xxxx + */ + DECODE_TABLE (0xff00f000, 0xfa00f000, t32_table_1111_1010___1111), + /* * Coprocessor instructions * 1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx -- cgit v1.2.3 From 231fb150c6f8a1f226380affc5498dd9abffc9d7 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 15:15:11 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb long multiply and divide instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 55 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 7c32e5b03cee..4ef12d13c7d0 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -289,6 +289,32 @@ t32_emulate_rd8rn16_noflags(struct kprobe *p, struct pt_regs *regs) regs->uregs[rd] = rdv; } +static void __kprobes +t32_emulate_rdlo12rdhi8rn16rm0_noflags(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rdlo = (insn >> 12) & 0xf; + int rdhi = (insn >> 8) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rdlov asm("r0") = regs->uregs[rdlo]; + register unsigned long rdhiv asm("r1") = regs->uregs[rdhi]; + register unsigned long rnv asm("r2") = regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + + __asm__ __volatile__ ( + "blx %[fn]" + : "=r" (rdlov), "=r" (rdhiv) + : "0" (rdlov), "1" (rdhiv), "r" (rnv), "r" (rmv), + [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rdlo] = rdlov; + regs->uregs[rdhi] = rdhiv; +} + static const union decode_item t32_table_1110_100x_x0xx[] = { /* Load/store multiple instructions */ @@ -763,6 +789,29 @@ static const union decode_item t32_table_1111_1010___1111[] = { DECODE_END }; +static const union decode_item t32_table_1111_1011_1[] = { + /* Long multiply, long multiply accumulate, and divide */ + + /* UMAAL 1111 1011 1110 xxxx xxxx xxxx 0110 xxxx */ + DECODE_OR (0xfff000f0, 0xfbe00060), + /* SMLALxy 1111 1011 1100 xxxx xxxx xxxx 10xx xxxx */ + DECODE_OR (0xfff000c0, 0xfbc00080), + /* SMLALD{X} 1111 1011 1100 xxxx xxxx xxxx 110x xxxx */ + /* SMLSLD{X} 1111 1011 1101 xxxx xxxx xxxx 110x xxxx */ + DECODE_OR (0xffe000e0, 0xfbc000c0), + /* SMULL 1111 1011 1000 xxxx xxxx xxxx 0000 xxxx */ + /* UMULL 1111 1011 1010 xxxx xxxx xxxx 0000 xxxx */ + /* SMLAL 1111 1011 1100 xxxx xxxx xxxx 0000 xxxx */ + /* UMLAL 1111 1011 1110 xxxx xxxx xxxx 0000 xxxx */ + DECODE_EMULATEX (0xff9000f0, 0xfb800000, t32_emulate_rdlo12rdhi8rn16rm0_noflags, + REGS(NOSPPC, NOSPPC, NOSPPC, 0, NOSPPC)), + + /* SDIV 1111 1011 1001 xxxx xxxx xxxx 1111 xxxx */ + /* UDIV 1111 1011 1011 xxxx xxxx xxxx 1111 xxxx */ + /* Other unallocated instructions... */ + DECODE_END +}; + const union decode_item kprobe_decode_thumb32_table[] = { /* @@ -833,6 +882,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xff00f000, 0xfa00f000, t32_table_1111_1010___1111), + /* + * Long multiply, long multiply accumulate, and divide + * 1111 1011 1xxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xff800000, 0xfb800000, t32_table_1111_1011_1), + /* * Coprocessor instructions * 1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx -- cgit v1.2.3 From bb1085f82710f0194bf8a1b587c96ecae7f131f8 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sun, 3 Jul 2011 15:15:59 +0100 Subject: ARM: kprobes: Decode 32-bit Thumb multiply and absolute difference instructions Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-thumb.c | 49 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 4ef12d13c7d0..902ca59e8b11 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -315,6 +315,10 @@ t32_emulate_rdlo12rdhi8rn16rm0_noflags(struct kprobe *p, struct pt_regs *regs) regs->uregs[rdhi] = rdhiv; } +/* These emulation encodings are functionally equivalent... */ +#define t32_emulate_rd8rn16rm0ra12_noflags \ + t32_emulate_rdlo12rdhi8rn16rm0_noflags + static const union decode_item t32_table_1110_100x_x0xx[] = { /* Load/store multiple instructions */ @@ -789,6 +793,45 @@ static const union decode_item t32_table_1111_1010___1111[] = { DECODE_END }; +static const union decode_item t32_table_1111_1011_0[] = { + /* Multiply, multiply accumulate, and absolute difference */ + + /* ??? 1111 1011 0000 xxxx 1111 xxxx 0001 xxxx */ + DECODE_REJECT (0xfff0f0f0, 0xfb00f010), + /* ??? 1111 1011 0111 xxxx 1111 xxxx 0001 xxxx */ + DECODE_REJECT (0xfff0f0f0, 0xfb70f010), + + /* SMULxy 1111 1011 0001 xxxx 1111 xxxx 00xx xxxx */ + DECODE_OR (0xfff0f0c0, 0xfb10f000), + /* MUL 1111 1011 0000 xxxx 1111 xxxx 0000 xxxx */ + /* SMUAD{X} 1111 1011 0010 xxxx 1111 xxxx 000x xxxx */ + /* SMULWy 1111 1011 0011 xxxx 1111 xxxx 000x xxxx */ + /* SMUSD{X} 1111 1011 0100 xxxx 1111 xxxx 000x xxxx */ + /* SMMUL{R} 1111 1011 0101 xxxx 1111 xxxx 000x xxxx */ + /* USAD8 1111 1011 0111 xxxx 1111 xxxx 0000 xxxx */ + DECODE_EMULATEX (0xff80f0e0, 0xfb00f000, t32_emulate_rd8rn16rm0_rwflags, + REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)), + + /* ??? 1111 1011 0111 xxxx xxxx xxxx 0001 xxxx */ + DECODE_REJECT (0xfff000f0, 0xfb700010), + + /* SMLAxy 1111 1011 0001 xxxx xxxx xxxx 00xx xxxx */ + DECODE_OR (0xfff000c0, 0xfb100000), + /* MLA 1111 1011 0000 xxxx xxxx xxxx 0000 xxxx */ + /* MLS 1111 1011 0000 xxxx xxxx xxxx 0001 xxxx */ + /* SMLAD{X} 1111 1011 0010 xxxx xxxx xxxx 000x xxxx */ + /* SMLAWy 1111 1011 0011 xxxx xxxx xxxx 000x xxxx */ + /* SMLSD{X} 1111 1011 0100 xxxx xxxx xxxx 000x xxxx */ + /* SMMLA{R} 1111 1011 0101 xxxx xxxx xxxx 000x xxxx */ + /* SMMLS{R} 1111 1011 0110 xxxx xxxx xxxx 000x xxxx */ + /* USADA8 1111 1011 0111 xxxx xxxx xxxx 0000 xxxx */ + DECODE_EMULATEX (0xff8000c0, 0xfb000000, t32_emulate_rd8rn16rm0ra12_noflags, + REGS(NOSPPC, NOSPPCX, NOSPPC, 0, NOSPPC)), + + /* Other unallocated instructions... */ + DECODE_END +}; + static const union decode_item t32_table_1111_1011_1[] = { /* Long multiply, long multiply accumulate, and divide */ @@ -882,6 +925,12 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_TABLE (0xff00f000, 0xfa00f000, t32_table_1111_1010___1111), + /* + * Multiply, multiply accumulate, and absolute difference + * 1111 1011 0xxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xff800000, 0xfb000000, t32_table_1111_1011_0), + /* * Long multiply, long multiply accumulate, and divide * 1111 1011 1xxx xxxx xxxx xxxx xxxx xxxx -- cgit v1.2.3 From 9a5c1284a3ec76c15a8bc51b2badc29e42fc5d92 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Mon, 6 Jun 2011 12:20:25 +0100 Subject: ARM: kprobes: Migrate ARM space_1111 to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 56 +++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 31 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index c6f2c693b1b6..ea96214ef341 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -896,41 +896,35 @@ prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn, * number of tests needed. */ -static enum kprobe_insn __kprobes -space_1111(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* memory hint : 1111 0100 x001 xxxx xxxx xxxx xxxx xxxx : */ - /* PLDI : 1111 0100 x101 xxxx xxxx xxxx xxxx xxxx : */ - /* PLDW : 1111 0101 x001 xxxx xxxx xxxx xxxx xxxx : */ - /* PLD : 1111 0101 x101 xxxx xxxx xxxx xxxx xxxx : */ - if ((insn & 0xfe300000) == 0xf4100000) { - asi->insn_handler = emulate_nop; - return INSN_GOOD_NO_SLOT; - } +static const union decode_item arm_1111_table[] = { + /* Unconditional instructions */ - /* BLX(1) : 1111 101x xxxx xxxx xxxx xxxx xxxx xxxx : */ - if ((insn & 0xfe000000) == 0xfa000000) { - asi->insn_handler = simulate_blx1; - return INSN_GOOD_NO_SLOT; - } + /* memory hint 1111 0100 x001 xxxx xxxx xxxx xxxx xxxx */ + /* PLDI (immediate) 1111 0100 x101 xxxx xxxx xxxx xxxx xxxx */ + /* PLDW (immediate) 1111 0101 x001 xxxx xxxx xxxx xxxx xxxx */ + /* PLD (immediate) 1111 0101 x101 xxxx xxxx xxxx xxxx xxxx */ + DECODE_SIMULATE (0xfe300000, 0xf4100000, kprobe_simulate_nop), - /* CPS : 1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */ - /* SETEND: 1111 0001 0000 0001 xxxx xxxx 0000 xxxx */ + /* BLX (immediate) 1111 101x xxxx xxxx xxxx xxxx xxxx xxxx */ + DECODE_SIMULATE (0xfe000000, 0xfa000000, simulate_blx1), - /* SRS : 1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */ - /* RFE : 1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* CPS 1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */ + /* SETEND 1111 0001 0000 0001 xxxx xxxx 0000 xxxx */ + /* SRS 1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */ + /* RFE 1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ /* Coprocessor instructions... */ - /* MCRR2 : 1111 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */ - /* MRRC2 : 1111 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd != Rn) */ - /* LDC2 : 1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ - /* STC2 : 1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ - /* CDP2 : 1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ - /* MCR2 : 1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ - /* MRC2 : 1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ - - return INSN_REJECTED; -} + /* MCRR2 1111 1100 0100 xxxx xxxx xxxx xxxx xxxx */ + /* MRRC2 1111 1100 0101 xxxx xxxx xxxx xxxx xxxx */ + /* LDC2 1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ + /* STC2 1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ + /* CDP2 1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ + /* MCR2 1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ + /* MRC2 1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ + + /* Other unallocated instructions... */ + DECODE_END +}; static enum kprobe_insn __kprobes space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) @@ -1477,7 +1471,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) if ((insn & 0xf0000000) == 0xf0000000) - return space_1111(insn, asi); + return kprobe_decode_insn(insn, asi, arm_1111_table, false); else if ((insn & 0x0e000000) == 0x00000000) -- cgit v1.2.3 From df4fa1f8dde23db25f50e49535d2c7db0005f9ad Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 1 Jul 2011 17:32:06 +0100 Subject: ARM: kprobes: Add alu_write_pc() This writes a new value to PC which was obtained as the result of an ARM ALU instruction. For ARMv7 and later this performs interworking. On ARM kernels we shouldn't encounter any ALU instructions trying to switch to Thumb mode so support for this isn't strictly necessary. However, the approach taken in all other instruction decoding is for us to avoid unpredictable modification of the PC for security reasons. This is usually achieved by rejecting insertion of probes on problematic instruction, but for ALU instructions we can't do this as it depends on the contents of the CPU registers at the time the probe is hit. So, as we require some form of run-time checking to trap undesirable PC modification, we may as well simulate the instructions correctly, i.e. in the way they would behave in the absence of a probe. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-common.c | 15 +++++++++++++++ arch/arm/kernel/kprobes.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c index 32bb0f236684..a5394fb4e4e0 100644 --- a/arch/arm/kernel/kprobes-common.c +++ b/arch/arm/kernel/kprobes-common.c @@ -59,10 +59,25 @@ void __init test_load_write_pc_interworking(void) #endif /* !test_load_write_pc_interworking */ +#ifndef test_alu_write_pc_interworking + +bool alu_write_pc_interworks; + +void __init test_alu_write_pc_interworking(void) +{ + int arch = cpu_architecture(); + BUG_ON(arch == CPU_ARCH_UNKNOWN); + alu_write_pc_interworks = arch >= CPU_ARCH_ARMv7; +} + +#endif /* !test_alu_write_pc_interworking */ + + void __init arm_kprobe_decode_init(void) { find_str_pc_offset(); test_load_write_pc_interworking(); + test_alu_write_pc_interworking(); } diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index c442852e65e4..a6aeda0a6c7f 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -133,6 +133,34 @@ static inline void __kprobes load_write_pc(long pcv, struct pt_regs *regs) } +#if __LINUX_ARM_ARCH__ >= 7 + +#define alu_write_pc_interworks true +#define test_alu_write_pc_interworking() + +#elif __LINUX_ARM_ARCH__ <= 5 + +/* Kernels built for <= ARMv5 should never run on >= ARMv6 hardware, so... */ +#define alu_write_pc_interworks false +#define test_alu_write_pc_interworking() + +#else /* __LINUX_ARM_ARCH__ == 6 */ + +/* We could be an ARMv6 binary on ARMv7 hardware so we need a run-time check. */ +extern bool alu_write_pc_interworks; +void __init test_alu_write_pc_interworking(void); + +#endif /* __LINUX_ARM_ARCH__ == 6 */ + +static inline void __kprobes alu_write_pc(long pcv, struct pt_regs *regs) +{ + if (alu_write_pc_interworks) + bx_write_pc(pcv, regs); + else + regs->ARM_pc = pcv; +} + + void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs); void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs); -- cgit v1.2.3 From 7be7ee2d295f6a069e1e92db95bf92eea2a173cf Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 7 Jul 2011 14:03:08 +0100 Subject: ARM: kprobes: Add BLX macro This is for use by inline assembler which will be added to kprobes-arm.c It saves memory when used on newer ARM architectures and also provides correct interworking should ARM probes be required on Thumb kernels in the future. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index ea96214ef341..80a941100f8c 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -67,6 +67,13 @@ #define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25) +#if __LINUX_ARM_ARCH__ >= 6 +#define BLX(reg) "blx "reg" \n\t" +#else +#define BLX(reg) "mov lr, pc \n\t" \ + "mov pc, "reg" \n\t" +#endif + #define is_r15(insn, bitpos) (((insn) & (0xf << bitpos)) == (0xf << bitpos)) #define PSR_fs (PSR_f|PSR_s) -- cgit v1.2.3 From 9f596e51261f96d602aa4eaf6db7f12ce53260d6 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 17:35:36 +0100 Subject: ARM: kprobes: Add emulate_rd12rn16rm0rs8_rwflags() This is the emulation function for the instruction format used by the ARM data-processing instructions. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 80a941100f8c..6e38bd4f7efd 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -893,6 +893,41 @@ prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn, return INSN_GOOD; } +static void __kprobes +emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = (unsigned long)p->addr + 8; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + int rs = (insn >> 8) & 0xf; + + register unsigned long rdv asm("r0") = regs->uregs[rd]; + register unsigned long rnv asm("r2") = (rn == 15) ? pc + : regs->uregs[rn]; + register unsigned long rmv asm("r3") = (rm == 15) ? pc + : regs->uregs[rm]; + register unsigned long rsv asm("r1") = regs->uregs[rs]; + unsigned long cpsr = regs->ARM_cpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + BLX("%[fn]") + "mrs %[cpsr], cpsr \n\t" + : "=r" (rdv), [cpsr] "=r" (cpsr) + : "0" (rdv), "r" (rnv), "r" (rmv), "r" (rsv), + "1" (cpsr), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + if (rd == 15) + alu_write_pc(rdv, regs); + else + regs->uregs[rd] = rdv; + regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); +} + /* * For the instruction masking and comparisons in all the "space_*" * functions below, Do _not_ rearrange the order of tests unless -- cgit v1.2.3 From 3535a89ab26db6b69603abf04420ec0b6c9ac387 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Mon, 6 Jun 2011 16:52:50 +0100 Subject: ARM: kprobes: Migrate ARM data-processing (register) instructions to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 111 ++++++++++++++++++++++++------------------ 1 file changed, 63 insertions(+), 48 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 6e38bd4f7efd..8e4b7185f9fb 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -968,6 +968,68 @@ static const union decode_item arm_1111_table[] = { DECODE_END }; +static const union decode_item arm_cccc_000x_table[] = { + /* Data-processing (register) */ + + /* S PC, ... cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx */ + DECODE_REJECT (0x0e10f000, 0x0010f000), + + /* MOV IP, SP 1110 0001 1010 0000 1100 0000 0000 1101 */ + DECODE_SIMULATE (0xffffffff, 0xe1a0c00d, simulate_mov_ipsp), + + /* TST (register) cccc 0001 0001 xxxx xxxx xxxx xxx0 xxxx */ + /* TEQ (register) cccc 0001 0011 xxxx xxxx xxxx xxx0 xxxx */ + /* CMP (register) cccc 0001 0101 xxxx xxxx xxxx xxx0 xxxx */ + /* CMN (register) cccc 0001 0111 xxxx xxxx xxxx xxx0 xxxx */ + DECODE_EMULATEX (0x0f900010, 0x01100000, emulate_rd12rn16rm0rs8_rwflags, + REGS(ANY, 0, 0, 0, ANY)), + + /* MOV (register) cccc 0001 101x xxxx xxxx xxxx xxx0 xxxx */ + /* MVN (register) cccc 0001 111x xxxx xxxx xxxx xxx0 xxxx */ + DECODE_EMULATEX (0x0fa00010, 0x01a00000, emulate_rd12rn16rm0rs8_rwflags, + REGS(0, ANY, 0, 0, ANY)), + + /* AND (register) cccc 0000 000x xxxx xxxx xxxx xxx0 xxxx */ + /* EOR (register) cccc 0000 001x xxxx xxxx xxxx xxx0 xxxx */ + /* SUB (register) cccc 0000 010x xxxx xxxx xxxx xxx0 xxxx */ + /* RSB (register) cccc 0000 011x xxxx xxxx xxxx xxx0 xxxx */ + /* ADD (register) cccc 0000 100x xxxx xxxx xxxx xxx0 xxxx */ + /* ADC (register) cccc 0000 101x xxxx xxxx xxxx xxx0 xxxx */ + /* SBC (register) cccc 0000 110x xxxx xxxx xxxx xxx0 xxxx */ + /* RSC (register) cccc 0000 111x xxxx xxxx xxxx xxx0 xxxx */ + /* ORR (register) cccc 0001 100x xxxx xxxx xxxx xxx0 xxxx */ + /* BIC (register) cccc 0001 110x xxxx xxxx xxxx xxx0 xxxx */ + DECODE_EMULATEX (0x0e000010, 0x00000000, emulate_rd12rn16rm0rs8_rwflags, + REGS(ANY, ANY, 0, 0, ANY)), + + /* TST (reg-shift reg) cccc 0001 0001 xxxx xxxx xxxx 0xx1 xxxx */ + /* TEQ (reg-shift reg) cccc 0001 0011 xxxx xxxx xxxx 0xx1 xxxx */ + /* CMP (reg-shift reg) cccc 0001 0101 xxxx xxxx xxxx 0xx1 xxxx */ + /* CMN (reg-shift reg) cccc 0001 0111 xxxx xxxx xxxx 0xx1 xxxx */ + DECODE_EMULATEX (0x0f900090, 0x01100010, emulate_rd12rn16rm0rs8_rwflags, + REGS(ANY, 0, NOPC, 0, ANY)), + + /* MOV (reg-shift reg) cccc 0001 101x xxxx xxxx xxxx 0xx1 xxxx */ + /* MVN (reg-shift reg) cccc 0001 111x xxxx xxxx xxxx 0xx1 xxxx */ + DECODE_EMULATEX (0x0fa00090, 0x01a00010, emulate_rd12rn16rm0rs8_rwflags, + REGS(0, ANY, NOPC, 0, ANY)), + + /* AND (reg-shift reg) cccc 0000 000x xxxx xxxx xxxx 0xx1 xxxx */ + /* EOR (reg-shift reg) cccc 0000 001x xxxx xxxx xxxx 0xx1 xxxx */ + /* SUB (reg-shift reg) cccc 0000 010x xxxx xxxx xxxx 0xx1 xxxx */ + /* RSB (reg-shift reg) cccc 0000 011x xxxx xxxx xxxx 0xx1 xxxx */ + /* ADD (reg-shift reg) cccc 0000 100x xxxx xxxx xxxx 0xx1 xxxx */ + /* ADC (reg-shift reg) cccc 0000 101x xxxx xxxx xxxx 0xx1 xxxx */ + /* SBC (reg-shift reg) cccc 0000 110x xxxx xxxx xxxx 0xx1 xxxx */ + /* RSC (reg-shift reg) cccc 0000 111x xxxx xxxx xxxx 0xx1 xxxx */ + /* ORR (reg-shift reg) cccc 0001 100x xxxx xxxx xxxx 0xx1 xxxx */ + /* BIC (reg-shift reg) cccc 0001 110x xxxx xxxx xxxx 0xx1 xxxx */ + DECODE_EMULATEX (0x0e000090, 0x00000010, emulate_rd12rn16rm0rs8_rwflags, + REGS(ANY, ANY, NOPC, 0, ANY)), + + DECODE_END +}; + static enum kprobe_insn __kprobes space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) { @@ -1126,54 +1188,7 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) return prep_emulate_ldr_str(insn, asi); } - /* cccc 000x xxxx xxxx xxxx xxxx xxxx xxxx xxxx */ - - /* - * ALU op with S bit and Rd == 15 : - * cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx - */ - if ((insn & 0x0e10f000) == 0x0010f000) - return INSN_REJECTED; - - /* - * "mov ip, sp" is the most common kprobe'd instruction by far. - * Check and optimize for it explicitly. - */ - if (insn == 0xe1a0c00d) { - asi->insn_handler = simulate_mov_ipsp; - return INSN_GOOD_NO_SLOT; - } - - /* - * Data processing: Immediate-shift / Register-shift - * ALU op : cccc 000x xxxx xxxx xxxx xxxx xxxx xxxx - * CPY : cccc 0001 1010 xxxx xxxx 0000 0000 xxxx - * MOV : cccc 0001 101x xxxx xxxx xxxx xxxx xxxx - * *S (bit 20) updates condition codes - * ADC/SBC/RSC reads the C flag - */ - insn &= 0xfff00ff0; /* Rn = r0, Rd = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - if (insn & 0x010) { - insn &= 0xfffff0ff; /* register shift */ - insn |= 0x00000200; /* Rs = r2 */ - } - asi->insn[0] = insn; - - if ((insn & 0x0f900000) == 0x01100000) { - /* - * TST : cccc 0001 0001 xxxx xxxx xxxx xxxx xxxx - * TEQ : cccc 0001 0011 xxxx xxxx xxxx xxxx xxxx - * CMP : cccc 0001 0101 xxxx xxxx xxxx xxxx xxxx - * CMN : cccc 0001 0111 xxxx xxxx xxxx xxxx xxxx - */ - asi->insn_handler = emulate_alu_tests; - } else { - /* ALU ops which write to Rd */ - asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ - emulate_alu_rwflags : emulate_alu_rflags; - } - return INSN_GOOD; + return kprobe_decode_insn(insn, asi, arm_cccc_000x_table, false); } static enum kprobe_insn __kprobes -- cgit v1.2.3 From 8723942f7b4501c87a95b7446786e6f4ba3779cf Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 17:39:42 +0100 Subject: ARM: kprobes: Add emulate_ldrdstrd() This is an emulation function for the LDRD and STRD instructions. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 8e4b7185f9fb..2b43d056fff5 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -893,6 +893,35 @@ prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn, return INSN_GOOD; } +static void __kprobes +emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = (unsigned long)p->addr + 8; + int rt = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rtv asm("r0") = regs->uregs[rt]; + register unsigned long rt2v asm("r1") = regs->uregs[rt+1]; + register unsigned long rnv asm("r2") = (rn == 15) ? pc + : regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + + __asm__ __volatile__ ( + BLX("%[fn]") + : "=r" (rtv), "=r" (rt2v), "=r" (rnv) + : "0" (rtv), "1" (rt2v), "2" (rnv), "r" (rmv), + [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rt] = rtv; + regs->uregs[rt+1] = rt2v; + if (is_writeback(insn)) + regs->uregs[rn] = rnv; +} + static void __kprobes emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs) { -- cgit v1.2.3 From 6c8a192929af0383f4b0f14646af85208e9c3f00 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Mon, 6 Jun 2011 15:07:42 +0100 Subject: ARM: kprobes: Migrate ARM LDRD and STRD to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 37 ++++++++++++++++++++----------------- 1 file changed, 20 insertions(+), 17 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 2b43d056fff5..e590ff6603c2 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -997,6 +997,23 @@ static const union decode_item arm_1111_table[] = { DECODE_END }; +static const union decode_item arm_cccc_000x_____1xx1_table[] = { + /* LDRD/STRD lr,pc,{... cccc 000x x0x0 xxxx 111x xxxx 1101 xxxx */ + DECODE_REJECT (0x0e10e0d0, 0x0000e0d0), + + /* LDRD (register) cccc 000x x0x0 xxxx xxxx xxxx 1101 xxxx */ + /* STRD (register) cccc 000x x0x0 xxxx xxxx xxxx 1111 xxxx */ + DECODE_EMULATEX (0x0e5000d0, 0x000000d0, emulate_ldrdstrd, + REGS(NOPCWB, NOPCX, 0, 0, NOPC)), + + /* LDRD (immediate) cccc 000x x1x0 xxxx xxxx xxxx 1101 xxxx */ + /* STRD (immediate) cccc 000x x1x0 xxxx xxxx xxxx 1111 xxxx */ + DECODE_EMULATEX (0x0e5000d0, 0x004000d0, emulate_ldrdstrd, + REGS(NOPCWB, NOPCX, 0, 0, 0)), + + DECODE_END +}; + static const union decode_item arm_cccc_000x_table[] = { /* Data-processing (register) */ @@ -1192,23 +1209,9 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) } } else if ((insn & 0x0e1000d0) == 0x00000d0) { - /* STRD/LDRD */ - if ((insn & 0x0000e000) == 0x0000e000) - return INSN_REJECTED; /* Rd is LR or PC */ - if (is_writeback(insn) && is_r15(insn, 16)) - return INSN_REJECTED; /* Writeback to PC */ - - insn &= 0xfff00fff; - insn |= 0x00002000; /* Rn = r0, Rd = r2 */ - if (!(insn & (1 << 22))) { - /* Register index */ - insn &= ~0xf; - insn |= 1; /* Rm = r1 */ - } - asi->insn[0] = insn; - asi->insn_handler = - (insn & (1 << 5)) ? emulate_strd : emulate_ldrd; - return INSN_GOOD; + + return kprobe_decode_insn(insn, asi, arm_cccc_000x_____1xx1_table, + false); } /* LDRH/STRH/LDRSB/LDRSH */ -- cgit v1.2.3 From 75f115c087bbd163d1c603160f6200cb494c9997 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Tue, 7 Jun 2011 09:58:11 +0100 Subject: ARM: kprobes: Migrate ARM space_cccc_000x to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 252 +++++++++++++++++++----------------------- 1 file changed, 116 insertions(+), 136 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index e590ff6603c2..ef350a5cd9b0 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -997,7 +997,99 @@ static const union decode_item arm_1111_table[] = { DECODE_END }; +static const union decode_item arm_cccc_0001_0xx0____0xxx_table[] = { + /* Miscellaneous instructions */ + + /* MRS cpsr cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */ + DECODE_SIMULATEX(0x0ff000f0, 0x01000000, simulate_mrs, + REGS(0, NOPC, 0, 0, 0)), + + /* BX cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */ + DECODE_SIMULATE (0x0ff000f0, 0x01200010, simulate_blx2bx), + + /* BLX (register) cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */ + DECODE_SIMULATEX(0x0ff000f0, 0x01200030, simulate_blx2bx, + REGS(0, 0, 0, 0, NOPC)), + + /* CLZ cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */ + DECODE_CUSTOM (0x0ff000f0, 0x01600010, prep_emulate_rd12rm0), + + /* QADD cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx */ + /* QSUB cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx */ + /* QDADD cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx */ + /* QDSUB cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx */ + DECODE_CUSTOM (0x0f9000f0, 0x01000050, prep_emulate_rd12rn16rm0_wflags), + + /* BXJ cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */ + /* MSR cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */ + /* MRS spsr cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */ + /* BKPT 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */ + /* SMC cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */ + /* And unallocated instructions... */ + DECODE_END +}; + +static const union decode_item arm_cccc_0001_0xx0____1xx0_table[] = { + /* Halfword multiply and multiply-accumulate */ + + /* SMLALxy cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */ + DECODE_CUSTOM (0x0ff00090, 0x01400080, prep_emulate_rdhi16rdlo12rs8rm0_wflags), + + /* SMULWy cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */ + DECODE_OR (0x0ff000b0, 0x012000a0), + /* SMULxy cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */ + DECODE_CUSTOM (0x0ff00090, 0x01600080, prep_emulate_rd16rs8rm0_wflags), + + /* SMLAxy cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx */ + DECODE_OR (0x0ff00090, 0x01000080), + /* SMLAWy cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx */ + DECODE_CUSTOM (0x0ff000b0, 0x01200080, prep_emulate_rd16rn12rs8rm0_wflags), + + DECODE_END +}; + +static const union decode_item arm_cccc_0000_____1001_table[] = { + /* Multiply and multiply-accumulate */ + + /* MUL cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx */ + /* MULS cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx */ + DECODE_CUSTOM (0x0fe000f0, 0x00000090, prep_emulate_rd16rs8rm0_wflags), + + /* MLA cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx */ + /* MLAS cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx */ + DECODE_OR (0x0fe000f0, 0x00200090), + /* MLS cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx */ + DECODE_CUSTOM (0x0ff000f0, 0x00600090, prep_emulate_rd16rn12rs8rm0_wflags), + + /* UMAAL cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx */ + DECODE_OR (0x0ff000f0, 0x00400090), + /* UMULL cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx */ + /* UMULLS cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx */ + /* UMLAL cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx */ + /* UMLALS cccc 0000 1011 xxxx xxxx xxxx 1001 xxxx */ + /* SMULL cccc 0000 1100 xxxx xxxx xxxx 1001 xxxx */ + /* SMULLS cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx */ + /* SMLAL cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx */ + /* SMLALS cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx */ + DECODE_CUSTOM (0x0f8000f0, 0x00800090, prep_emulate_rdhi16rdlo12rs8rm0_wflags), + + DECODE_END +}; + +static const union decode_item arm_cccc_0001_____1001_table[] = { + /* Synchronization primitives */ + + /* SMP/SWPB cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */ + DECODE_CUSTOM (0x0fb000f0, 0x01000090, prep_emulate_rd12rn16rm0_wflags), + + /* LDREX/STREX{,D,B,H} cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */ + /* And unallocated instructions... */ + DECODE_END +}; + static const union decode_item arm_cccc_000x_____1xx1_table[] = { + /* Extra load/store instructions */ + /* LDRD/STRD lr,pc,{... cccc 000x x0x0 xxxx 111x xxxx 1101 xxxx */ DECODE_REJECT (0x0e10e0d0, 0x0000e0d0), @@ -1011,6 +1103,20 @@ static const union decode_item arm_cccc_000x_____1xx1_table[] = { DECODE_EMULATEX (0x0e5000d0, 0x004000d0, emulate_ldrdstrd, REGS(NOPCWB, NOPCX, 0, 0, 0)), + /* Reject Rd is PC */ + /* TODO: fold this into next entry when it is made a DECODE_EMULATE */ + DECODE_REJECT (0x0000f000, 0x0000f000), + + /* STRH (register) cccc 000x x0x0 xxxx xxxx xxxx 1011 xxxx */ + /* LDRH (register) cccc 000x x0x1 xxxx xxxx xxxx 1011 xxxx */ + /* LDRSB (register) cccc 000x x0x1 xxxx xxxx xxxx 1101 xxxx */ + /* LDRSH (register) cccc 000x x0x1 xxxx xxxx xxxx 1111 xxxx */ + /* STRH (immediate) cccc 000x x1x0 xxxx xxxx xxxx 1011 xxxx */ + /* LDRH (immediate) cccc 000x x1x1 xxxx xxxx xxxx 1011 xxxx */ + /* LDRSB (immediate) cccc 000x x1x1 xxxx xxxx xxxx 1101 xxxx */ + /* LDRSH (immediate) cccc 000x x1x1 xxxx xxxx xxxx 1111 xxxx */ + DECODE_CUSTOM (0x0e000090, 0x00000090, prep_emulate_ldr_str), + DECODE_END }; @@ -1079,146 +1185,20 @@ static const union decode_item arm_cccc_000x_table[] = { static enum kprobe_insn __kprobes space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) { - /* cccc 0001 0xx0 xxxx xxxx xxxx xxxx xxx0 xxxx */ - if ((insn & 0x0f900010) == 0x01000000) { - - /* MRS cpsr : cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */ - if ((insn & 0x0ff000f0) == 0x01000000) { - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - asi->insn_handler = simulate_mrs; - return INSN_GOOD_NO_SLOT; - } - - /* SMLALxy : cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */ - if ((insn & 0x0ff00090) == 0x01400080) - return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, - asi); - - /* SMULWy : cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */ - /* SMULxy : cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */ - if ((insn & 0x0ff000b0) == 0x012000a0 || - (insn & 0x0ff00090) == 0x01600080) - return prep_emulate_rd16rs8rm0_wflags(insn, asi); - - /* SMLAxy : cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx : Q */ - /* SMLAWy : cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx : Q */ - if ((insn & 0x0ff00090) == 0x01000080 || - (insn & 0x0ff000b0) == 0x01200080) - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - - /* BXJ : cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */ - /* MSR : cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */ - /* MRS spsr : cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */ - - /* Other instruction encodings aren't yet defined */ - return INSN_REJECTED; - } - - /* cccc 0001 0xx0 xxxx xxxx xxxx xxxx 0xx1 xxxx */ - else if ((insn & 0x0f900090) == 0x01000010) { - - /* BLX(2) : cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */ - /* BX : cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */ - if ((insn & 0x0ff000d0) == 0x01200010) { - if ((insn & 0x0ff000ff) == 0x0120003f) - return INSN_REJECTED; /* BLX pc */ - asi->insn_handler = simulate_blx2bx; - return INSN_GOOD_NO_SLOT; - } - - /* CLZ : cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */ - if ((insn & 0x0ff000f0) == 0x01600010) - return prep_emulate_rd12rm0(insn, asi); + if ((insn & 0x0f900080) == 0x01000000) + return kprobe_decode_insn(insn, asi, arm_cccc_0001_0xx0____0xxx_table, false); - /* QADD : cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx :Q */ - /* QSUB : cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx :Q */ - /* QDADD : cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx :Q */ - /* QDSUB : cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx :Q */ - if ((insn & 0x0f9000f0) == 0x01000050) - return prep_emulate_rd12rn16rm0_wflags(insn, asi); + if ((insn & 0x0f900090) == 0x01000080) + return kprobe_decode_insn(insn, asi, arm_cccc_0001_0xx0____1xx0_table, false); - /* BKPT : 1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */ - /* SMC : cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */ + if ((insn & 0x0f0000f0) == 0x00000090) + return kprobe_decode_insn(insn, asi, arm_cccc_0000_____1001_table, false); - /* Other instruction encodings aren't yet defined */ - return INSN_REJECTED; - } + if ((insn & 0x0f0000f0) == 0x01000090) + return kprobe_decode_insn(insn, asi, arm_cccc_0001_____1001_table, false); - /* cccc 0000 xxxx xxxx xxxx xxxx xxxx 1001 xxxx */ - else if ((insn & 0x0f0000f0) == 0x00000090) { - - /* MUL : cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx : */ - /* MULS : cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx :cc */ - /* MLA : cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx : */ - /* MLAS : cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx :cc */ - /* UMAAL : cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx : */ - /* undef : cccc 0000 0101 xxxx xxxx xxxx 1001 xxxx : */ - /* MLS : cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx : */ - /* undef : cccc 0000 0111 xxxx xxxx xxxx 1001 xxxx : */ - /* UMULL : cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx : */ - /* UMULLS : cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx :cc */ - /* UMLAL : cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx : */ - /* UMLALS : cccc 0000 1011 xxxx xxxx xxxx 1001 xxxx :cc */ - /* SMULL : cccc 0000 1100 xxxx xxxx xxxx 1001 xxxx : */ - /* SMULLS : cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx :cc */ - /* SMLAL : cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx : */ - /* SMLALS : cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx :cc */ - if ((insn & 0x00d00000) == 0x00500000) - return INSN_REJECTED; - else if ((insn & 0x00e00000) == 0x00000000) - return prep_emulate_rd16rs8rm0_wflags(insn, asi); - else if ((insn & 0x00a00000) == 0x00200000) - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - else - return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, - asi); - } - - /* cccc 000x xxxx xxxx xxxx xxxx xxxx 1xx1 xxxx */ - else if ((insn & 0x0e000090) == 0x00000090) { - - /* SWP : cccc 0001 0000 xxxx xxxx xxxx 1001 xxxx */ - /* SWPB : cccc 0001 0100 xxxx xxxx xxxx 1001 xxxx */ - /* ??? : cccc 0001 0x01 xxxx xxxx xxxx 1001 xxxx */ - /* ??? : cccc 0001 0x10 xxxx xxxx xxxx 1001 xxxx */ - /* ??? : cccc 0001 0x11 xxxx xxxx xxxx 1001 xxxx */ - /* STREX : cccc 0001 1000 xxxx xxxx xxxx 1001 xxxx */ - /* LDREX : cccc 0001 1001 xxxx xxxx xxxx 1001 xxxx */ - /* STREXD: cccc 0001 1010 xxxx xxxx xxxx 1001 xxxx */ - /* LDREXD: cccc 0001 1011 xxxx xxxx xxxx 1001 xxxx */ - /* STREXB: cccc 0001 1100 xxxx xxxx xxxx 1001 xxxx */ - /* LDREXB: cccc 0001 1101 xxxx xxxx xxxx 1001 xxxx */ - /* STREXH: cccc 0001 1110 xxxx xxxx xxxx 1001 xxxx */ - /* LDREXH: cccc 0001 1111 xxxx xxxx xxxx 1001 xxxx */ - - /* LDRD : cccc 000x xxx0 xxxx xxxx xxxx 1101 xxxx */ - /* STRD : cccc 000x xxx0 xxxx xxxx xxxx 1111 xxxx */ - /* LDRH : cccc 000x xxx1 xxxx xxxx xxxx 1011 xxxx */ - /* STRH : cccc 000x xxx0 xxxx xxxx xxxx 1011 xxxx */ - /* LDRSB : cccc 000x xxx1 xxxx xxxx xxxx 1101 xxxx */ - /* LDRSH : cccc 000x xxx1 xxxx xxxx xxxx 1111 xxxx */ - if ((insn & 0x0f0000f0) == 0x01000090) { - if ((insn & 0x0fb000f0) == 0x01000090) { - /* SWP/SWPB */ - return prep_emulate_rd12rn16rm0_wflags(insn, - asi); - } else { - /* STREX/LDREX variants and unallocaed space */ - return INSN_REJECTED; - } - - } else if ((insn & 0x0e1000d0) == 0x00000d0) { - - return kprobe_decode_insn(insn, asi, arm_cccc_000x_____1xx1_table, - false); - } - - /* LDRH/STRH/LDRSB/LDRSH */ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - return prep_emulate_ldr_str(insn, asi); - } + if ((insn & 0x0e000090) == 0x00000090) + return kprobe_decode_insn(insn, asi, arm_cccc_000x_____1xx1_table, false); return kprobe_decode_insn(insn, asi, arm_cccc_000x_table, false); } -- cgit v1.2.3 From c038f3af507943244f2522585d17614915afd324 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 8 Jun 2011 14:39:11 +0100 Subject: ARM: kprobes: Migrate ARM space_cccc_001x to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 116 ++++++++++++++++++------------------------ 1 file changed, 50 insertions(+), 66 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index ef350a5cd9b0..f2eed03f5522 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1203,72 +1203,56 @@ space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) return kprobe_decode_insn(insn, asi, arm_cccc_000x_table, false); } -static enum kprobe_insn __kprobes -space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* MOVW : cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */ - /* MOVT : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */ - if ((insn & 0x0fb00000) == 0x03000000) - return prep_emulate_rd12_modify(insn, asi); - - /* hints : cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */ - if ((insn & 0x0fff0000) == 0x03200000) { - unsigned op2 = insn & 0x000000ff; - if (op2 == 0x01 || op2 == 0x04) { - /* YIELD : cccc 0011 0010 0000 xxxx xxxx 0000 0001 */ - /* SEV : cccc 0011 0010 0000 xxxx xxxx 0000 0100 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_none; - return INSN_GOOD; - } else if (op2 <= 0x03) { - /* NOP : cccc 0011 0010 0000 xxxx xxxx 0000 0000 */ - /* WFE : cccc 0011 0010 0000 xxxx xxxx 0000 0010 */ - /* WFI : cccc 0011 0010 0000 xxxx xxxx 0000 0011 */ - /* - * We make WFE and WFI true NOPs to avoid stalls due - * to missing events whilst processing the probe. - */ - asi->insn_handler = emulate_nop; - return INSN_GOOD_NO_SLOT; - } - /* For DBG and unallocated hints it's safest to reject them */ - return INSN_REJECTED; - } +static const union decode_item arm_cccc_001x_table[] = { + /* Data-processing (immediate) */ + + /* MOVW cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */ + /* MOVT cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */ + DECODE_CUSTOM (0x0fb00000, 0x03000000, prep_emulate_rd12_modify), + + /* YIELD cccc 0011 0010 0000 xxxx xxxx 0000 0001 */ + DECODE_OR (0x0fff00ff, 0x03200001), + /* SEV cccc 0011 0010 0000 xxxx xxxx 0000 0100 */ + DECODE_EMULATE (0x0fff00ff, 0x03200004, kprobe_emulate_none), + /* NOP cccc 0011 0010 0000 xxxx xxxx 0000 0000 */ + /* WFE cccc 0011 0010 0000 xxxx xxxx 0000 0010 */ + /* WFI cccc 0011 0010 0000 xxxx xxxx 0000 0011 */ + DECODE_SIMULATE (0x0fff00fc, 0x03200000, kprobe_simulate_nop), + /* DBG cccc 0011 0010 0000 xxxx xxxx ffff xxxx */ + /* unallocated hints cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */ + /* MSR (immediate) cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0x0fb00000, 0x03200000), + + /* S PC, ... cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx */ + DECODE_REJECT (0x0e10f000, 0x0210f000), + + /* TST (immediate) cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx */ + /* TEQ (immediate) cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx */ + /* CMP (immediate) cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx */ + /* CMN (immediate) cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0f900000, 0x03100000, emulate_rd12rn16rm0rs8_rwflags, + REGS(ANY, 0, 0, 0, 0)), + + /* MOV (immediate) cccc 0011 101x xxxx xxxx xxxx xxxx xxxx */ + /* MVN (immediate) cccc 0011 111x xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0fa00000, 0x03a00000, emulate_rd12rn16rm0rs8_rwflags, + REGS(0, ANY, 0, 0, 0)), + + /* AND (immediate) cccc 0010 000x xxxx xxxx xxxx xxxx xxxx */ + /* EOR (immediate) cccc 0010 001x xxxx xxxx xxxx xxxx xxxx */ + /* SUB (immediate) cccc 0010 010x xxxx xxxx xxxx xxxx xxxx */ + /* RSB (immediate) cccc 0010 011x xxxx xxxx xxxx xxxx xxxx */ + /* ADD (immediate) cccc 0010 100x xxxx xxxx xxxx xxxx xxxx */ + /* ADC (immediate) cccc 0010 101x xxxx xxxx xxxx xxxx xxxx */ + /* SBC (immediate) cccc 0010 110x xxxx xxxx xxxx xxxx xxxx */ + /* RSC (immediate) cccc 0010 111x xxxx xxxx xxxx xxxx xxxx */ + /* ORR (immediate) cccc 0011 100x xxxx xxxx xxxx xxxx xxxx */ + /* BIC (immediate) cccc 0011 110x xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0e000000, 0x02000000, emulate_rd12rn16rm0rs8_rwflags, + REGS(ANY, ANY, 0, 0, 0)), - /* - * MSR : cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx - * ALU op with S bit and Rd == 15 : - * cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx - */ - if ((insn & 0x0fb00000) == 0x03200000 || /* MSR */ - (insn & 0x0e10f000) == 0x0210f000) /* ALU s-bit, R15 */ - return INSN_REJECTED; - - /* - * Data processing: 32-bit Immediate - * ALU op : cccc 001x xxxx xxxx xxxx xxxx xxxx xxxx - * MOV : cccc 0011 101x xxxx xxxx xxxx xxxx xxxx - * *S (bit 20) updates condition codes - * ADC/SBC/RSC reads the C flag - */ - insn &= 0xfff00fff; /* Rn = r0 and Rd = r0 */ - asi->insn[0] = insn; - - if ((insn & 0x0f900000) == 0x03100000) { - /* - * TST : cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx - * TEQ : cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx - * CMP : cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx - * CMN : cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx - */ - asi->insn_handler = emulate_alu_tests_imm; - } else { - /* ALU ops which write to Rd */ - asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ - emulate_alu_imm_rwflags : emulate_alu_imm_rflags; - } - return INSN_GOOD; -} + DECODE_END +}; static enum kprobe_insn __kprobes space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) @@ -1548,7 +1532,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) else if ((insn & 0x0e000000) == 0x02000000) - return space_cccc_001x(insn, asi); + return kprobe_decode_insn(insn, asi, arm_cccc_001x_table, false); else if ((insn & 0x0f000010) == 0x06000010) -- cgit v1.2.3 From 0e44e9a0fae65c07fa5a23bd720b6108892c96f8 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 17:23:50 +0100 Subject: ARM: kprobes: Add emulate_rd12rn16rm0_rwflags_nopc() This is the emulation function for the instruction format used by the ARM media instructions. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index f2eed03f5522..eb11a56683b6 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -957,6 +957,33 @@ emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs) regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); } +static void __kprobes +emulate_rd12rn16rm0_rwflags_nopc(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rdv asm("r0") = regs->uregs[rd]; + register unsigned long rnv asm("r2") = regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + unsigned long cpsr = regs->ARM_cpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + BLX("%[fn]") + "mrs %[cpsr], cpsr \n\t" + : "=r" (rdv), [cpsr] "=r" (cpsr) + : "0" (rdv), "r" (rnv), "r" (rmv), + "1" (cpsr), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rd] = rdv; + regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); +} + /* * For the instruction masking and comparisons in all the "space_*" * functions below, Do _not_ rearrange the order of tests unless -- cgit v1.2.3 From 2ce5d03307222b3d5b7c5e9849eb4857eb979fa9 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 8 Jun 2011 17:36:45 +0100 Subject: ARM: kprobes: Migrate ARM space_cccc_0110__1 to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 217 ++++++++++++++++++------------------------ 1 file changed, 91 insertions(+), 126 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index eb11a56683b6..62035057846a 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1281,132 +1281,97 @@ static const union decode_item arm_cccc_001x_table[] = { DECODE_END }; -static enum kprobe_insn __kprobes -space_cccc_0110__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* SEL : cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx GE: !!! */ - if ((insn & 0x0ff000f0) == 0x068000b0) { - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - insn &= 0xfff00ff0; /* Rd = r0, Rn = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_sel; - return INSN_GOOD; - } - - /* SSAT : cccc 0110 101x xxxx xxxx xxxx xx01 xxxx :Q */ - /* USAT : cccc 0110 111x xxxx xxxx xxxx xx01 xxxx :Q */ - /* SSAT16 : cccc 0110 1010 xxxx xxxx xxxx 0011 xxxx :Q */ - /* USAT16 : cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx :Q */ - if ((insn & 0x0fa00030) == 0x06a00010 || - (insn & 0x0fb000f0) == 0x06a00030) { - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - insn &= 0xffff0ff0; /* Rd = r0, Rm = r0 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_sat; - return INSN_GOOD; - } - - /* REV : cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */ - /* REV16 : cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */ - /* RBIT : cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */ - /* REVSH : cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */ - if ((insn & 0x0ff00070) == 0x06b00030 || - (insn & 0x0ff00070) == 0x06f00030) - return prep_emulate_rd12rm0(insn, asi); - - /* ??? : cccc 0110 0000 xxxx xxxx xxxx xxx1 xxxx : */ - /* SADD16 : cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx :GE */ - /* SADDSUBX : cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx :GE */ - /* SSUBADDX : cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx :GE */ - /* SSUB16 : cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx :GE */ - /* SADD8 : cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx :GE */ - /* ??? : cccc 0110 0001 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0001 xxxx xxxx xxxx 1101 xxxx : */ - /* SSUB8 : cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx :GE */ - /* QADD16 : cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx : */ - /* QADDSUBX : cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx : */ - /* QSUBADDX : cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx : */ - /* QSUB16 : cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx : */ - /* QADD8 : cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0010 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0010 xxxx xxxx xxxx 1101 xxxx : */ - /* QSUB8 : cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx : */ - /* SHADD16 : cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx : */ - /* SHADDSUBX : cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx : */ - /* SHSUBADDX : cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx : */ - /* SHSUB16 : cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx : */ - /* SHADD8 : cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0011 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0011 xxxx xxxx xxxx 1101 xxxx : */ - /* SHSUB8 : cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx : */ - /* ??? : cccc 0110 0100 xxxx xxxx xxxx xxx1 xxxx : */ - /* UADD16 : cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx :GE */ - /* UADDSUBX : cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx :GE */ - /* USUBADDX : cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx :GE */ - /* USUB16 : cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx :GE */ - /* UADD8 : cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx :GE */ - /* ??? : cccc 0110 0101 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0101 xxxx xxxx xxxx 1101 xxxx : */ - /* USUB8 : cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx :GE */ - /* UQADD16 : cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx : */ - /* UQADDSUBX : cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx : */ - /* UQSUBADDX : cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx : */ - /* UQSUB16 : cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx : */ - /* UQADD8 : cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0110 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0110 xxxx xxxx xxxx 1101 xxxx : */ - /* UQSUB8 : cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx : */ - /* UHADD16 : cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx : */ - /* UHADDSUBX : cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx : */ - /* UHSUBADDX : cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx : */ - /* UHSUB16 : cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx : */ - /* UHADD8 : cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx : */ - /* ??? : cccc 0110 0111 xxxx xxxx xxxx 1011 xxxx : */ - /* ??? : cccc 0110 0111 xxxx xxxx xxxx 1101 xxxx : */ - /* UHSUB8 : cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx : */ - if ((insn & 0x0f800010) == 0x06000010) { - if ((insn & 0x00300000) == 0x00000000 || - (insn & 0x000000e0) == 0x000000a0 || - (insn & 0x000000e0) == 0x000000c0) - return INSN_REJECTED; /* Unallocated space */ - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - } - - /* PKHBT : cccc 0110 1000 xxxx xxxx xxxx x001 xxxx : */ - /* PKHTB : cccc 0110 1000 xxxx xxxx xxxx x101 xxxx : */ - if ((insn & 0x0ff00030) == 0x06800010) - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - - /* SXTAB16 : cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTB16 : cccc 0110 1000 1111 xxxx xxxx 0111 xxxx : */ - /* ??? : cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTAB : cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTB : cccc 0110 1010 1111 xxxx xxxx 0111 xxxx : */ - /* SXTAH : cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx : */ - /* SXTH : cccc 0110 1011 1111 xxxx xxxx 0111 xxxx : */ - /* UXTAB16 : cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTB16 : cccc 0110 1100 1111 xxxx xxxx 0111 xxxx : */ - /* ??? : cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTAB : cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTB : cccc 0110 1110 1111 xxxx xxxx 0111 xxxx : */ - /* UXTAH : cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx : */ - /* UXTH : cccc 0110 1111 1111 xxxx xxxx 0111 xxxx : */ - if ((insn & 0x0f8000f0) == 0x06800070) { - if ((insn & 0x00300000) == 0x00100000) - return INSN_REJECTED; /* Unallocated space */ - - if ((insn & 0x000f0000) == 0x000f0000) - return prep_emulate_rd12rm0(insn, asi); - else - return prep_emulate_rd12rn16rm0_wflags(insn, asi); - } +static const union decode_item arm_cccc_0110_____xxx1_table[] = { + /* Media instructions */ + + /* SEL cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx */ + DECODE_EMULATEX (0x0ff000f0, 0x068000b0, emulate_rd12rn16rm0_rwflags_nopc, + REGS(NOPC, NOPC, 0, 0, NOPC)), + + /* SSAT cccc 0110 101x xxxx xxxx xxxx xx01 xxxx */ + /* USAT cccc 0110 111x xxxx xxxx xxxx xx01 xxxx */ + DECODE_OR(0x0fa00030, 0x06a00010), + /* SSAT16 cccc 0110 1010 xxxx xxxx xxxx 0011 xxxx */ + /* USAT16 cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx */ + DECODE_EMULATEX (0x0fb000f0, 0x06a00030, emulate_rd12rn16rm0_rwflags_nopc, + REGS(0, NOPC, 0, 0, NOPC)), + + /* REV cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */ + /* REV16 cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */ + /* RBIT cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */ + /* REVSH cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */ + DECODE_CUSTOM (0x0fb00070, 0x06b00030, prep_emulate_rd12rm0), + + /* ??? cccc 0110 0x00 xxxx xxxx xxxx xxx1 xxxx */ + DECODE_REJECT (0x0fb00010, 0x06000010), + /* ??? cccc 0110 0xxx xxxx xxxx xxxx 1011 xxxx */ + DECODE_REJECT (0x0f8000f0, 0x060000b0), + /* ??? cccc 0110 0xxx xxxx xxxx xxxx 1101 xxxx */ + DECODE_REJECT (0x0f8000f0, 0x060000d0), + /* SADD16 cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx */ + /* SADDSUBX cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx */ + /* SSUBADDX cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx */ + /* SSUB16 cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx */ + /* SADD8 cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx */ + /* SSUB8 cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx */ + /* QADD16 cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx */ + /* QADDSUBX cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx */ + /* QSUBADDX cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx */ + /* QSUB16 cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx */ + /* QADD8 cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx */ + /* QSUB8 cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx */ + /* SHADD16 cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx */ + /* SHADDSUBX cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx */ + /* SHSUBADDX cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx */ + /* SHSUB16 cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx */ + /* SHADD8 cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx */ + /* SHSUB8 cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx */ + /* UADD16 cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx */ + /* UADDSUBX cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx */ + /* USUBADDX cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx */ + /* USUB16 cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx */ + /* UADD8 cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx */ + /* USUB8 cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx */ + /* UQADD16 cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx */ + /* UQADDSUBX cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx */ + /* UQSUBADDX cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx */ + /* UQSUB16 cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx */ + /* UQADD8 cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx */ + /* UQSUB8 cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx */ + /* UHADD16 cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx */ + /* UHADDSUBX cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx */ + /* UHSUBADDX cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx */ + /* UHSUB16 cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx */ + /* UHADD8 cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx */ + /* UHSUB8 cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx */ + DECODE_CUSTOM (0x0f800010, 0x06000010, prep_emulate_rd12rn16rm0_wflags), + + /* PKHBT cccc 0110 1000 xxxx xxxx xxxx x001 xxxx */ + /* PKHTB cccc 0110 1000 xxxx xxxx xxxx x101 xxxx */ + DECODE_CUSTOM (0x0ff00030, 0x06800010, prep_emulate_rd12rn16rm0_wflags), + + /* ??? cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx */ + /* ??? cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx */ + DECODE_REJECT (0x0fb000f0, 0x06900070), + + /* SXTB16 cccc 0110 1000 1111 xxxx xxxx 0111 xxxx */ + /* SXTB cccc 0110 1010 1111 xxxx xxxx 0111 xxxx */ + /* SXTH cccc 0110 1011 1111 xxxx xxxx 0111 xxxx */ + /* UXTB16 cccc 0110 1100 1111 xxxx xxxx 0111 xxxx */ + /* UXTB cccc 0110 1110 1111 xxxx xxxx 0111 xxxx */ + /* UXTH cccc 0110 1111 1111 xxxx xxxx 0111 xxxx */ + DECODE_CUSTOM (0x0f8f00f0, 0x068f0070, prep_emulate_rd12rm0), + + /* SXTAB16 cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx */ + /* SXTAB cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx */ + /* SXTAH cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx */ + /* UXTAB16 cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx */ + /* UXTAB cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx */ + /* UXTAH cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx */ + DECODE_CUSTOM (0x0f8000f0, 0x06800070, prep_emulate_rd12rn16rm0_wflags), - /* Other instruction encodings aren't yet defined */ - return INSN_REJECTED; -} + DECODE_END +}; static enum kprobe_insn __kprobes space_cccc_0111__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) @@ -1563,7 +1528,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) else if ((insn & 0x0f000010) == 0x06000010) - return space_cccc_0110__1(insn, asi); + return kprobe_decode_insn(insn, asi, arm_cccc_0110_____xxx1_table, false); else if ((insn & 0x0f000010) == 0x07000010) -- cgit v1.2.3 From ad2e81a78d016176b9f194414495a4ce166399e1 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Wed, 8 Jun 2011 18:09:36 +0100 Subject: ARM: kprobes: Migrate ARM space_cccc_0111__1 to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 82 +++++++++++++++++++------------------------ 1 file changed, 36 insertions(+), 46 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 62035057846a..58faacc598bf 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1373,57 +1373,47 @@ static const union decode_item arm_cccc_0110_____xxx1_table[] = { DECODE_END }; -static enum kprobe_insn __kprobes -space_cccc_0111__1(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* Undef : cccc 0111 1111 xxxx xxxx xxxx 1111 xxxx */ - if ((insn & 0x0ff000f0) == 0x03f000f0) - return INSN_REJECTED; +static const union decode_item arm_cccc_0111_____xxx1_table[] = { + /* Media instructions */ - /* SMLALD : cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */ - /* SMLSLD : cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */ - if ((insn & 0x0ff00090) == 0x07400010) - return prep_emulate_rdhi16rdlo12rs8rm0_wflags(insn, asi); - - /* SMLAD : cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx :Q */ - /* SMUAD : cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx :Q */ - /* SMLSD : cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx :Q */ - /* SMUSD : cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx : */ - /* SMMLA : cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx : */ - /* SMMUL : cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx : */ - /* USADA8 : cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx : */ - /* USAD8 : cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx : */ - if ((insn & 0x0ff00090) == 0x07000010 || - (insn & 0x0ff000d0) == 0x07500010 || - (insn & 0x0ff000f0) == 0x07800010) { - - if ((insn & 0x0000f000) == 0x0000f000) - return prep_emulate_rd16rs8rm0_wflags(insn, asi); - else - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); - } + /* UNDEFINED cccc 0111 1111 xxxx xxxx xxxx 1111 xxxx */ + DECODE_REJECT (0x0ff000f0, 0x07f000f0), - /* SMMLS : cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx : */ - if ((insn & 0x0ff000d0) == 0x075000d0) - return prep_emulate_rd16rn12rs8rm0_wflags(insn, asi); + /* SMLALD cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */ + /* SMLSLD cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */ + DECODE_CUSTOM (0x0ff00090, 0x07400010, prep_emulate_rdhi16rdlo12rs8rm0_wflags), - /* SBFX : cccc 0111 101x xxxx xxxx xxxx x101 xxxx : */ - /* UBFX : cccc 0111 111x xxxx xxxx xxxx x101 xxxx : */ - if ((insn & 0x0fa00070) == 0x07a00050) - return prep_emulate_rd12rm0(insn, asi); + /* SMUAD cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx */ + /* SMUSD cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx */ + DECODE_OR (0x0ff0f090, 0x0700f010), + /* SMMUL cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx */ + DECODE_OR (0x0ff0f0d0, 0x0750f010), + /* USAD8 cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx */ + DECODE_CUSTOM (0x0ff0f0f0, 0x0780f010, prep_emulate_rd16rs8rm0_wflags), - /* BFI : cccc 0111 110x xxxx xxxx xxxx x001 xxxx : */ - /* BFC : cccc 0111 110x xxxx xxxx xxxx x001 1111 : */ - if ((insn & 0x0fe00070) == 0x07c00010) { + /* SMLAD cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx */ + /* SMLSD cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx */ + DECODE_OR (0x0ff00090, 0x07000010), + /* SMMLA cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx */ + DECODE_OR (0x0ff000d0, 0x07500010), + /* USADA8 cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx */ + DECODE_CUSTOM (0x0ff000f0, 0x07800010, prep_emulate_rd16rn12rs8rm0_wflags), - if ((insn & 0x0000000f) == 0x0000000f) - return prep_emulate_rd12_modify(insn, asi); - else - return prep_emulate_rd12rn0_modify(insn, asi); - } + /* SMMLS cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx */ + DECODE_CUSTOM (0x0ff000d0, 0x075000d0, prep_emulate_rd16rn12rs8rm0_wflags), - return INSN_REJECTED; -} + /* SBFX cccc 0111 101x xxxx xxxx xxxx x101 xxxx */ + /* UBFX cccc 0111 111x xxxx xxxx xxxx x101 xxxx */ + DECODE_CUSTOM (0x0fa00070, 0x07a00050, prep_emulate_rd12rm0), + + /* BFC cccc 0111 110x xxxx xxxx xxxx x001 1111 */ + DECODE_CUSTOM (0x0fe0007f, 0x07c0001f, prep_emulate_rd12_modify), + + /* BFI cccc 0111 110x xxxx xxxx xxxx x001 xxxx */ + DECODE_CUSTOM (0x0fe00070, 0x07c00010, prep_emulate_rd12rn0_modify), + + DECODE_END +}; static enum kprobe_insn __kprobes space_cccc_01xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) @@ -1532,7 +1522,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) else if ((insn & 0x0f000010) == 0x07000010) - return space_cccc_0111__1(insn, asi); + return kprobe_decode_insn(insn, asi, arm_cccc_0111_____xxx1_table, false); else if ((insn & 0x0c000000) == 0x04000000) -- cgit v1.2.3 From 56d8fbddc2a2be7aa81d65e5a6f0f6093ee70c48 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 09:12:58 +0100 Subject: ARM: kprobes: Migrate ARM space_cccc_01xx to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 58faacc598bf..319e6feb0363 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1415,23 +1415,24 @@ static const union decode_item arm_cccc_0111_____xxx1_table[] = { DECODE_END }; -static enum kprobe_insn __kprobes -space_cccc_01xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* LDR : cccc 01xx x0x1 xxxx xxxx xxxx xxxx xxxx */ - /* LDRB : cccc 01xx x1x1 xxxx xxxx xxxx xxxx xxxx */ - /* LDRBT : cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */ - /* LDRT : cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */ - /* STR : cccc 01xx x0x0 xxxx xxxx xxxx xxxx xxxx */ - /* STRB : cccc 01xx x1x0 xxxx xxxx xxxx xxxx xxxx */ - /* STRBT : cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */ - /* STRT : cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */ - - if ((insn & 0x00500000) == 0x00500000 && is_r15(insn, 12)) - return INSN_REJECTED; /* LDRB into PC */ - - return prep_emulate_ldr_str(insn, asi); -} +static const union decode_item arm_cccc_01xx_table[] = { + /* Load/store word and unsigned byte */ + + /* LDRB/STRB pc,[...] cccc 01xx x0xx xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0x0c40f000, 0x0440f000), + + /* LDR cccc 01xx x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* LDRB cccc 01xx x1x1 xxxx xxxx xxxx xxxx xxxx */ + /* LDRBT cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */ + /* LDRT cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */ + /* STR cccc 01xx x0x0 xxxx xxxx xxxx xxxx xxxx */ + /* STRB cccc 01xx x1x0 xxxx xxxx xxxx xxxx xxxx */ + /* STRBT cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */ + /* STRT cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */ + DECODE_CUSTOM (0x0c000000, 0x04000000, prep_emulate_ldr_str), + + DECODE_END +}; static enum kprobe_insn __kprobes space_cccc_100x(kprobe_opcode_t insn, struct arch_specific_insn *asi) @@ -1526,7 +1527,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) else if ((insn & 0x0c000000) == 0x04000000) - return space_cccc_01xx(insn, asi); + return kprobe_decode_insn(insn, asi, arm_cccc_01xx_table, false); else if ((insn & 0x0e000000) == 0x08000000) -- cgit v1.2.3 From 0d32e7d11b5ce8b3ab11fd74123b46b88f26b3e2 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 9 Jun 2011 09:46:56 +0100 Subject: ARM: kprobes: Migrate ARM space_cccc_100x to decoding tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 319e6feb0363..b2fd2c87ffee 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1434,25 +1434,18 @@ static const union decode_item arm_cccc_01xx_table[] = { DECODE_END }; -static enum kprobe_insn __kprobes -space_cccc_100x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* LDM(2) : cccc 100x x101 xxxx 0xxx xxxx xxxx xxxx */ - /* LDM(3) : cccc 100x x1x1 xxxx 1xxx xxxx xxxx xxxx */ - if ((insn & 0x0e708000) == 0x85000000 || - (insn & 0x0e508000) == 0x85010000) - return INSN_REJECTED; - - /* LDM(1) : cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ - /* STM(1) : cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */ - - /* - * Make the instruction unconditional because the new emulation - * functions don't bother to setup the PSR context. - */ - insn = (insn | 0xe0000000) & ~0x10000000; - return kprobe_decode_ldmstm(insn, asi); -} +static const union decode_item arm_cccc_100x_table[] = { + /* Block data transfer instructions */ + + /* LDM cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* STM cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */ + DECODE_CUSTOM (0x0e400000, 0x08000000, kprobe_decode_ldmstm), + + /* STM (user registers) cccc 100x x1x0 xxxx xxxx xxxx xxxx xxxx */ + /* LDM (user registers) cccc 100x x1x1 xxxx 0xxx xxxx xxxx xxxx */ + /* LDM (exception ret) cccc 100x x1x1 xxxx 1xxx xxxx xxxx xxxx */ + DECODE_END +}; static enum kprobe_insn __kprobes space_cccc_101x(kprobe_opcode_t insn, struct arch_specific_insn *asi) @@ -1531,7 +1524,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) else if ((insn & 0x0e000000) == 0x08000000) - return space_cccc_100x(insn, asi); + return kprobe_decode_insn(insn, asi, arm_cccc_100x_table, false); else if ((insn & 0x0e000000) == 0x0a000000) -- cgit v1.2.3 From e9a92859e91acaa67337b4a820040a820906ea4c Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 10 Jun 2011 11:36:36 +0100 Subject: ARM: kprobes: Migrate remaining instruction decoding functions to tables Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 170 ++++++++++++++++++++++-------------------- 1 file changed, 90 insertions(+), 80 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index b2fd2c87ffee..f271212a7cd5 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1209,27 +1209,6 @@ static const union decode_item arm_cccc_000x_table[] = { DECODE_END }; -static enum kprobe_insn __kprobes -space_cccc_000x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - if ((insn & 0x0f900080) == 0x01000000) - return kprobe_decode_insn(insn, asi, arm_cccc_0001_0xx0____0xxx_table, false); - - if ((insn & 0x0f900090) == 0x01000080) - return kprobe_decode_insn(insn, asi, arm_cccc_0001_0xx0____1xx0_table, false); - - if ((insn & 0x0f0000f0) == 0x00000090) - return kprobe_decode_insn(insn, asi, arm_cccc_0000_____1001_table, false); - - if ((insn & 0x0f0000f0) == 0x01000090) - return kprobe_decode_insn(insn, asi, arm_cccc_0001_____1001_table, false); - - if ((insn & 0x0e000090) == 0x00000090) - return kprobe_decode_insn(insn, asi, arm_cccc_000x_____1xx1_table, false); - - return kprobe_decode_insn(insn, asi, arm_cccc_000x_table, false); -} - static const union decode_item arm_cccc_001x_table[] = { /* Data-processing (immediate) */ @@ -1447,31 +1426,96 @@ static const union decode_item arm_cccc_100x_table[] = { DECODE_END }; -static enum kprobe_insn __kprobes -space_cccc_101x(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* B : cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */ - /* BL : cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */ - asi->insn_handler = simulate_bbl; - return INSN_GOOD_NO_SLOT; -} +const union decode_item kprobe_decode_arm_table[] = { + /* + * Unconditional instructions + * 1111 xxxx xxxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0xf0000000, 0xf0000000, arm_1111_table), + + /* + * Miscellaneous instructions + * cccc 0001 0xx0 xxxx xxxx xxxx 0xxx xxxx + */ + DECODE_TABLE (0x0f900080, 0x01000000, arm_cccc_0001_0xx0____0xxx_table), + + /* + * Halfword multiply and multiply-accumulate + * cccc 0001 0xx0 xxxx xxxx xxxx 1xx0 xxxx + */ + DECODE_TABLE (0x0f900090, 0x01000080, arm_cccc_0001_0xx0____1xx0_table), + + /* + * Multiply and multiply-accumulate + * cccc 0000 xxxx xxxx xxxx xxxx 1001 xxxx + */ + DECODE_TABLE (0x0f0000f0, 0x00000090, arm_cccc_0000_____1001_table), + + /* + * Synchronization primitives + * cccc 0001 xxxx xxxx xxxx xxxx 1001 xxxx + */ + DECODE_TABLE (0x0f0000f0, 0x01000090, arm_cccc_0001_____1001_table), + + /* + * Extra load/store instructions + * cccc 000x xxxx xxxx xxxx xxxx 1xx1 xxxx + */ + DECODE_TABLE (0x0e000090, 0x00000090, arm_cccc_000x_____1xx1_table), + + /* + * Data-processing (register) + * cccc 000x xxxx xxxx xxxx xxxx xxx0 xxxx + * Data-processing (register-shifted register) + * cccc 000x xxxx xxxx xxxx xxxx 0xx1 xxxx + */ + DECODE_TABLE (0x0e000000, 0x00000000, arm_cccc_000x_table), + + /* + * Data-processing (immediate) + * cccc 001x xxxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0x0e000000, 0x02000000, arm_cccc_001x_table), + + /* + * Media instructions + * cccc 011x xxxx xxxx xxxx xxxx xxx1 xxxx + */ + DECODE_TABLE (0x0f000010, 0x06000010, arm_cccc_0110_____xxx1_table), + DECODE_TABLE (0x0f000010, 0x07000010, arm_cccc_0111_____xxx1_table), + + /* + * Load/store word and unsigned byte + * cccc 01xx xxxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0x0c000000, 0x04000000, arm_cccc_01xx_table), + + /* + * Block data transfer instructions + * cccc 100x xxxx xxxx xxxx xxxx xxxx xxxx + */ + DECODE_TABLE (0x0e000000, 0x08000000, arm_cccc_100x_table), + + /* B cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */ + /* BL cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */ + DECODE_SIMULATE (0x0e000000, 0x0a000000, simulate_bbl), + + /* + * Supervisor Call, and coprocessor instructions + */ + + /* MCRR cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx */ + /* MRRC cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx */ + /* LDC cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ + /* STC cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ + /* CDP cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ + /* MCR cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ + /* MRC cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ + /* SVC cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0x0c000000, 0x0c000000), -static enum kprobe_insn __kprobes -space_cccc_11xx(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - /* Coprocessor instructions... */ - /* MCRR : cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */ - /* MRRC : cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx : (Rd!=Rn) */ - /* LDC : cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */ - /* STC : cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */ - /* CDP : cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */ - /* MCR : cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */ - /* MRC : cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */ - - /* SVC : cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */ - - return INSN_REJECTED; -} + DECODE_END +}; static void __kprobes arm_singlestep(struct kprobe *p, struct pt_regs *regs) { @@ -1496,39 +1540,5 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) { asi->insn_singlestep = arm_singlestep; asi->insn_check_cc = kprobe_condition_checks[insn>>28]; - asi->insn[1] = KPROBE_RETURN_INSTRUCTION; - - if ((insn & 0xf0000000) == 0xf0000000) - - return kprobe_decode_insn(insn, asi, arm_1111_table, false); - - else if ((insn & 0x0e000000) == 0x00000000) - - return space_cccc_000x(insn, asi); - - else if ((insn & 0x0e000000) == 0x02000000) - - return kprobe_decode_insn(insn, asi, arm_cccc_001x_table, false); - - else if ((insn & 0x0f000010) == 0x06000010) - - return kprobe_decode_insn(insn, asi, arm_cccc_0110_____xxx1_table, false); - - else if ((insn & 0x0f000010) == 0x07000010) - - return kprobe_decode_insn(insn, asi, arm_cccc_0111_____xxx1_table, false); - - else if ((insn & 0x0c000000) == 0x04000000) - - return kprobe_decode_insn(insn, asi, arm_cccc_01xx_table, false); - - else if ((insn & 0x0e000000) == 0x08000000) - - return kprobe_decode_insn(insn, asi, arm_cccc_100x_table, false); - - else if ((insn & 0x0e000000) == 0x0a000000) - - return space_cccc_101x(insn, asi); - - return space_cccc_11xx(insn, asi); + return kprobe_decode_insn(insn, asi, kprobe_decode_arm_table, false); } -- cgit v1.2.3 From 6091dfae4f289b7316b21277c38c8cd519e47f79 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 10 Jun 2011 17:35:51 +0100 Subject: ARM: kprobes: Add emulate_rd16rn12rm0rs8_rwflags_nopc() This is the emulation function for the instruction format used by the ARM multiply-accumulate instructions. These don't allow use of PC so we don't have to add special cases for this. This function is used to replace use of prep_emulate_rd16rs8rm0_wflags and prep_emulate_rd16rn12rs8rm0_wflags. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 50 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 43 insertions(+), 7 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index f271212a7cd5..d3b0506df410 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -984,6 +984,35 @@ emulate_rd12rn16rm0_rwflags_nopc(struct kprobe *p, struct pt_regs *regs) regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); } +static void __kprobes +emulate_rd16rn12rm0rs8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 16) & 0xf; + int rn = (insn >> 12) & 0xf; + int rm = insn & 0xf; + int rs = (insn >> 8) & 0xf; + + register unsigned long rdv asm("r2") = regs->uregs[rd]; + register unsigned long rnv asm("r0") = regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + register unsigned long rsv asm("r1") = regs->uregs[rs]; + unsigned long cpsr = regs->ARM_cpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + BLX("%[fn]") + "mrs %[cpsr], cpsr \n\t" + : "=r" (rdv), [cpsr] "=r" (cpsr) + : "0" (rdv), "r" (rnv), "r" (rmv), "r" (rsv), + "1" (cpsr), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rd] = rdv; + regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); +} + /* * For the instruction masking and comparisons in all the "space_*" * functions below, Do _not_ rearrange the order of tests unless @@ -1065,12 +1094,14 @@ static const union decode_item arm_cccc_0001_0xx0____1xx0_table[] = { /* SMULWy cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */ DECODE_OR (0x0ff000b0, 0x012000a0), /* SMULxy cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */ - DECODE_CUSTOM (0x0ff00090, 0x01600080, prep_emulate_rd16rs8rm0_wflags), + DECODE_EMULATEX (0x0ff00090, 0x01600080, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, 0, NOPC, 0, NOPC)), /* SMLAxy cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx */ DECODE_OR (0x0ff00090, 0x01000080), /* SMLAWy cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx */ - DECODE_CUSTOM (0x0ff000b0, 0x01200080, prep_emulate_rd16rn12rs8rm0_wflags), + DECODE_EMULATEX (0x0ff000b0, 0x01200080, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, NOPC, NOPC, 0, NOPC)), DECODE_END }; @@ -1080,13 +1111,15 @@ static const union decode_item arm_cccc_0000_____1001_table[] = { /* MUL cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx */ /* MULS cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx */ - DECODE_CUSTOM (0x0fe000f0, 0x00000090, prep_emulate_rd16rs8rm0_wflags), + DECODE_EMULATEX (0x0fe000f0, 0x00000090, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, 0, NOPC, 0, NOPC)), /* MLA cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx */ /* MLAS cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx */ DECODE_OR (0x0fe000f0, 0x00200090), /* MLS cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx */ - DECODE_CUSTOM (0x0ff000f0, 0x00600090, prep_emulate_rd16rn12rs8rm0_wflags), + DECODE_EMULATEX (0x0ff000f0, 0x00600090, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, NOPC, NOPC, 0, NOPC)), /* UMAAL cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx */ DECODE_OR (0x0ff000f0, 0x00400090), @@ -1368,7 +1401,8 @@ static const union decode_item arm_cccc_0111_____xxx1_table[] = { /* SMMUL cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx */ DECODE_OR (0x0ff0f0d0, 0x0750f010), /* USAD8 cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx */ - DECODE_CUSTOM (0x0ff0f0f0, 0x0780f010, prep_emulate_rd16rs8rm0_wflags), + DECODE_EMULATEX (0x0ff0f0f0, 0x0780f010, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, 0, NOPC, 0, NOPC)), /* SMLAD cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx */ /* SMLSD cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx */ @@ -1376,10 +1410,12 @@ static const union decode_item arm_cccc_0111_____xxx1_table[] = { /* SMMLA cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx */ DECODE_OR (0x0ff000d0, 0x07500010), /* USADA8 cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx */ - DECODE_CUSTOM (0x0ff000f0, 0x07800010, prep_emulate_rd16rn12rs8rm0_wflags), + DECODE_EMULATEX (0x0ff000f0, 0x07800010, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, NOPCX, NOPC, 0, NOPC)), /* SMMLS cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx */ - DECODE_CUSTOM (0x0ff000d0, 0x075000d0, prep_emulate_rd16rn12rs8rm0_wflags), + DECODE_EMULATEX (0x0ff000d0, 0x075000d0, emulate_rd16rn12rm0rs8_rwflags_nopc, + REGS(NOPC, NOPC, NOPC, 0, NOPC)), /* SBFX cccc 0111 101x xxxx xxxx xxxx x101 xxxx */ /* UBFX cccc 0111 111x xxxx xxxx xxxx x101 xxxx */ -- cgit v1.2.3 From 35fab77469f8883077d8c9eda9325b38647ad3dc Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 10 Jun 2011 17:55:10 +0100 Subject: ARM: kprobes: Replace use of prep_emulate_rd12rn16rm0_wflags() These can now use emulate_rd12rn16rm0_rwflags_nopc(). Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index d3b0506df410..2131506e1193 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1074,7 +1074,8 @@ static const union decode_item arm_cccc_0001_0xx0____0xxx_table[] = { /* QSUB cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx */ /* QDADD cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx */ /* QDSUB cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx */ - DECODE_CUSTOM (0x0f9000f0, 0x01000050, prep_emulate_rd12rn16rm0_wflags), + DECODE_EMULATEX (0x0f9000f0, 0x01000050, emulate_rd12rn16rm0_rwflags_nopc, + REGS(NOPC, NOPC, 0, 0, NOPC)), /* BXJ cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */ /* MSR cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */ @@ -1140,7 +1141,8 @@ static const union decode_item arm_cccc_0001_____1001_table[] = { /* Synchronization primitives */ /* SMP/SWPB cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */ - DECODE_CUSTOM (0x0fb000f0, 0x01000090, prep_emulate_rd12rn16rm0_wflags), + DECODE_EMULATEX (0x0fb000f0, 0x01000090, emulate_rd12rn16rm0_rwflags_nopc, + REGS(NOPC, NOPC, 0, 0, NOPC)), /* LDREX/STREX{,D,B,H} cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */ /* And unallocated instructions... */ @@ -1356,11 +1358,13 @@ static const union decode_item arm_cccc_0110_____xxx1_table[] = { /* UHSUB16 cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx */ /* UHADD8 cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx */ /* UHSUB8 cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx */ - DECODE_CUSTOM (0x0f800010, 0x06000010, prep_emulate_rd12rn16rm0_wflags), + DECODE_EMULATEX (0x0f800010, 0x06000010, emulate_rd12rn16rm0_rwflags_nopc, + REGS(NOPC, NOPC, 0, 0, NOPC)), /* PKHBT cccc 0110 1000 xxxx xxxx xxxx x001 xxxx */ /* PKHTB cccc 0110 1000 xxxx xxxx xxxx x101 xxxx */ - DECODE_CUSTOM (0x0ff00030, 0x06800010, prep_emulate_rd12rn16rm0_wflags), + DECODE_EMULATEX (0x0ff00030, 0x06800010, emulate_rd12rn16rm0_rwflags_nopc, + REGS(NOPC, NOPC, 0, 0, NOPC)), /* ??? cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx */ /* ??? cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx */ @@ -1380,7 +1384,8 @@ static const union decode_item arm_cccc_0110_____xxx1_table[] = { /* UXTAB16 cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx */ /* UXTAB cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx */ /* UXTAH cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx */ - DECODE_CUSTOM (0x0f8000f0, 0x06800070, prep_emulate_rd12rn16rm0_wflags), + DECODE_EMULATEX (0x0f8000f0, 0x06800070, emulate_rd12rn16rm0_rwflags_nopc, + REGS(NOPCX, NOPC, 0, 0, NOPC)), DECODE_END }; -- cgit v1.2.3 From c82584ebdf5948bfc6f0509be1c2bef714b49a33 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 10 Jun 2011 18:10:36 +0100 Subject: ARM: kprobes: Add emulate_rd12rm0_noflags_nopc() This is the emulation function for the instruction format used by the ARM bit-field manipulation instructions. Various other instruction forms can also make use of this and it is used to replace use of prep_emulate_rd12{rm0}{_modify} Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 41 ++++++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 2131506e1193..688101f2d39a 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1013,6 +1013,26 @@ emulate_rd16rn12rm0rs8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs) regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); } +static void __kprobes +emulate_rd12rm0_noflags_nopc(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rd = (insn >> 12) & 0xf; + int rm = insn & 0xf; + + register unsigned long rdv asm("r0") = regs->uregs[rd]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + + __asm__ __volatile__ ( + BLX("%[fn]") + : "=r" (rdv) + : "0" (rdv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rd] = rdv; +} + /* * For the instruction masking and comparisons in all the "space_*" * functions below, Do _not_ rearrange the order of tests unless @@ -1068,7 +1088,8 @@ static const union decode_item arm_cccc_0001_0xx0____0xxx_table[] = { REGS(0, 0, 0, 0, NOPC)), /* CLZ cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */ - DECODE_CUSTOM (0x0ff000f0, 0x01600010, prep_emulate_rd12rm0), + DECODE_EMULATEX (0x0ff000f0, 0x01600010, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, NOPC)), /* QADD cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx */ /* QSUB cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx */ @@ -1249,7 +1270,8 @@ static const union decode_item arm_cccc_001x_table[] = { /* MOVW cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */ /* MOVT cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */ - DECODE_CUSTOM (0x0fb00000, 0x03000000, prep_emulate_rd12_modify), + DECODE_EMULATEX (0x0fb00000, 0x03000000, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, 0)), /* YIELD cccc 0011 0010 0000 xxxx xxxx 0000 0001 */ DECODE_OR (0x0fff00ff, 0x03200001), @@ -1314,7 +1336,8 @@ static const union decode_item arm_cccc_0110_____xxx1_table[] = { /* REV16 cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */ /* RBIT cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */ /* REVSH cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */ - DECODE_CUSTOM (0x0fb00070, 0x06b00030, prep_emulate_rd12rm0), + DECODE_EMULATEX (0x0fb00070, 0x06b00030, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, NOPC)), /* ??? cccc 0110 0x00 xxxx xxxx xxxx xxx1 xxxx */ DECODE_REJECT (0x0fb00010, 0x06000010), @@ -1376,7 +1399,8 @@ static const union decode_item arm_cccc_0110_____xxx1_table[] = { /* UXTB16 cccc 0110 1100 1111 xxxx xxxx 0111 xxxx */ /* UXTB cccc 0110 1110 1111 xxxx xxxx 0111 xxxx */ /* UXTH cccc 0110 1111 1111 xxxx xxxx 0111 xxxx */ - DECODE_CUSTOM (0x0f8f00f0, 0x068f0070, prep_emulate_rd12rm0), + DECODE_EMULATEX (0x0f8f00f0, 0x068f0070, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, NOPC)), /* SXTAB16 cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx */ /* SXTAB cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx */ @@ -1424,13 +1448,16 @@ static const union decode_item arm_cccc_0111_____xxx1_table[] = { /* SBFX cccc 0111 101x xxxx xxxx xxxx x101 xxxx */ /* UBFX cccc 0111 111x xxxx xxxx xxxx x101 xxxx */ - DECODE_CUSTOM (0x0fa00070, 0x07a00050, prep_emulate_rd12rm0), + DECODE_EMULATEX (0x0fa00070, 0x07a00050, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, NOPC)), /* BFC cccc 0111 110x xxxx xxxx xxxx x001 1111 */ - DECODE_CUSTOM (0x0fe0007f, 0x07c0001f, prep_emulate_rd12_modify), + DECODE_EMULATEX (0x0fe0007f, 0x07c0001f, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, 0)), /* BFI cccc 0111 110x xxxx xxxx xxxx x001 xxxx */ - DECODE_CUSTOM (0x0fe00070, 0x07c00010, prep_emulate_rd12rn0_modify), + DECODE_EMULATEX (0x0fe00070, 0x07c00010, emulate_rd12rm0_noflags_nopc, + REGS(0, NOPC, 0, 0, NOPCX)), DECODE_END }; -- cgit v1.2.3 From 12ce5d3388dab15109e94eb847c948b23b709a03 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Fri, 10 Jun 2011 18:32:15 +0100 Subject: ARM: kprobes: Add emulate_rdlo12rdhi16rn0rm8_rwflags_nopc() This is the emulation function for the instruction format used by the ARM multiply long instructions. It replaces use of prep_emulate_rdhi16rdlo12rs8rm0_wflags(). Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 39 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 36 insertions(+), 3 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 688101f2d39a..bb38ae3601c8 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1033,6 +1033,36 @@ emulate_rd12rm0_noflags_nopc(struct kprobe *p, struct pt_regs *regs) regs->uregs[rd] = rdv; } +static void __kprobes +emulate_rdlo12rdhi16rn0rm8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + int rdlo = (insn >> 12) & 0xf; + int rdhi = (insn >> 16) & 0xf; + int rn = insn & 0xf; + int rm = (insn >> 8) & 0xf; + + register unsigned long rdlov asm("r0") = regs->uregs[rdlo]; + register unsigned long rdhiv asm("r2") = regs->uregs[rdhi]; + register unsigned long rnv asm("r3") = regs->uregs[rn]; + register unsigned long rmv asm("r1") = regs->uregs[rm]; + unsigned long cpsr = regs->ARM_cpsr; + + __asm__ __volatile__ ( + "msr cpsr_fs, %[cpsr] \n\t" + BLX("%[fn]") + "mrs %[cpsr], cpsr \n\t" + : "=r" (rdlov), "=r" (rdhiv), [cpsr] "=r" (cpsr) + : "0" (rdlov), "1" (rdhiv), "r" (rnv), "r" (rmv), + "2" (cpsr), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + regs->uregs[rdlo] = rdlov; + regs->uregs[rdhi] = rdhiv; + regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK); +} + /* * For the instruction masking and comparisons in all the "space_*" * functions below, Do _not_ rearrange the order of tests unless @@ -1111,7 +1141,8 @@ static const union decode_item arm_cccc_0001_0xx0____1xx0_table[] = { /* Halfword multiply and multiply-accumulate */ /* SMLALxy cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */ - DECODE_CUSTOM (0x0ff00090, 0x01400080, prep_emulate_rdhi16rdlo12rs8rm0_wflags), + DECODE_EMULATEX (0x0ff00090, 0x01400080, emulate_rdlo12rdhi16rn0rm8_rwflags_nopc, + REGS(NOPC, NOPC, NOPC, 0, NOPC)), /* SMULWy cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */ DECODE_OR (0x0ff000b0, 0x012000a0), @@ -1153,7 +1184,8 @@ static const union decode_item arm_cccc_0000_____1001_table[] = { /* SMULLS cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx */ /* SMLAL cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx */ /* SMLALS cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx */ - DECODE_CUSTOM (0x0f8000f0, 0x00800090, prep_emulate_rdhi16rdlo12rs8rm0_wflags), + DECODE_EMULATEX (0x0f8000f0, 0x00800090, emulate_rdlo12rdhi16rn0rm8_rwflags_nopc, + REGS(NOPC, NOPC, NOPC, 0, NOPC)), DECODE_END }; @@ -1422,7 +1454,8 @@ static const union decode_item arm_cccc_0111_____xxx1_table[] = { /* SMLALD cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */ /* SMLSLD cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */ - DECODE_CUSTOM (0x0ff00090, 0x07400010, prep_emulate_rdhi16rdlo12rs8rm0_wflags), + DECODE_EMULATEX (0x0ff00090, 0x07400010, emulate_rdlo12rdhi16rn0rm8_rwflags_nopc, + REGS(NOPC, NOPC, NOPC, 0, NOPC)), /* SMUAD cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx */ /* SMUSD cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx */ -- cgit v1.2.3 From 3c48fbb1478f47a95d18a56ff2662b40cb236152 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 11 Jun 2011 13:10:49 +0100 Subject: ARM: kprobes: Add new versions of emulate_ldr() and emulate_str() These use the register calling conventions required by the new decoding table framework for calling simulated instructions. We rename the old versions of these functions to *_old for now. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 63 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 60 insertions(+), 3 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index bb38ae3601c8..d252e7821fcc 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -502,7 +502,7 @@ static void __kprobes emulate_strd(struct kprobe *p, struct pt_regs *regs) regs->uregs[rn] = rnv_wb; } -static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs) +static void __kprobes emulate_ldr_old(struct kprobe *p, struct pt_regs *regs) { insn_llret_3arg_fn_t *i_fn = (insn_llret_3arg_fn_t *)&p->ainsn.insn[0]; kprobe_opcode_t insn = p->opcode; @@ -535,7 +535,7 @@ static void __kprobes emulate_ldr(struct kprobe *p, struct pt_regs *regs) regs->uregs[rd] = rdv; } -static void __kprobes emulate_str(struct kprobe *p, struct pt_regs *regs) +static void __kprobes emulate_str_old(struct kprobe *p, struct pt_regs *regs) { insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; kprobe_opcode_t insn = p->opcode; @@ -795,7 +795,7 @@ prep_emulate_ldr_str(kprobe_opcode_t insn, struct arch_specific_insn *asi) insn |= 2; /* Rm = r2 */ } asi->insn[0] = insn; - asi->insn_handler = (insn & (1 << 20)) ? emulate_ldr : emulate_str; + asi->insn_handler = (insn & (1 << 20)) ? emulate_ldr_old : emulate_str_old; return INSN_GOOD; } @@ -922,6 +922,63 @@ emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs) regs->uregs[rn] = rnv; } +static void __kprobes +emulate_ldr(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long pc = (unsigned long)p->addr + 8; + int rt = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rtv asm("r0"); + register unsigned long rnv asm("r2") = (rn == 15) ? pc + : regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + + __asm__ __volatile__ ( + BLX("%[fn]") + : "=r" (rtv), "=r" (rnv) + : "1" (rnv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + if (rt == 15) + load_write_pc(rtv, regs); + else + regs->uregs[rt] = rtv; + + if (is_writeback(insn)) + regs->uregs[rn] = rnv; +} + +static void __kprobes +emulate_str(struct kprobe *p, struct pt_regs *regs) +{ + kprobe_opcode_t insn = p->opcode; + unsigned long rtpc = (unsigned long)p->addr + str_pc_offset; + unsigned long rnpc = (unsigned long)p->addr + 8; + int rt = (insn >> 12) & 0xf; + int rn = (insn >> 16) & 0xf; + int rm = insn & 0xf; + + register unsigned long rtv asm("r0") = (rt == 15) ? rtpc + : regs->uregs[rt]; + register unsigned long rnv asm("r2") = (rn == 15) ? rnpc + : regs->uregs[rn]; + register unsigned long rmv asm("r3") = regs->uregs[rm]; + + __asm__ __volatile__ ( + BLX("%[fn]") + : "=r" (rnv) + : "r" (rtv), "0" (rnv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn) + : "lr", "memory", "cc" + ); + + if (is_writeback(insn)) + regs->uregs[rn] = rnv; +} + static void __kprobes emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs) { -- cgit v1.2.3 From 711bf10633485e0489fec0fc35abee240dd619ae Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 11 Jun 2011 15:08:24 +0100 Subject: ARM: kprobes: Use new versions of emulate_ldr() and emulate_str() Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 44 +++++++++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 14 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index d252e7821fcc..1ee38adeb82d 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1275,19 +1275,25 @@ static const union decode_item arm_cccc_000x_____1xx1_table[] = { DECODE_EMULATEX (0x0e5000d0, 0x004000d0, emulate_ldrdstrd, REGS(NOPCWB, NOPCX, 0, 0, 0)), - /* Reject Rd is PC */ - /* TODO: fold this into next entry when it is made a DECODE_EMULATE */ - DECODE_REJECT (0x0000f000, 0x0000f000), - /* STRH (register) cccc 000x x0x0 xxxx xxxx xxxx 1011 xxxx */ + DECODE_EMULATEX (0x0e5000f0, 0x000000b0, emulate_str, + REGS(NOPCWB, NOPC, 0, 0, NOPC)), + /* LDRH (register) cccc 000x x0x1 xxxx xxxx xxxx 1011 xxxx */ /* LDRSB (register) cccc 000x x0x1 xxxx xxxx xxxx 1101 xxxx */ /* LDRSH (register) cccc 000x x0x1 xxxx xxxx xxxx 1111 xxxx */ + DECODE_EMULATEX (0x0e500090, 0x00100090, emulate_ldr, + REGS(NOPCWB, NOPC, 0, 0, NOPC)), + /* STRH (immediate) cccc 000x x1x0 xxxx xxxx xxxx 1011 xxxx */ + DECODE_EMULATEX (0x0e5000f0, 0x004000b0, emulate_str, + REGS(NOPCWB, NOPC, 0, 0, 0)), + /* LDRH (immediate) cccc 000x x1x1 xxxx xxxx xxxx 1011 xxxx */ /* LDRSB (immediate) cccc 000x x1x1 xxxx xxxx xxxx 1101 xxxx */ /* LDRSH (immediate) cccc 000x x1x1 xxxx xxxx xxxx 1111 xxxx */ - DECODE_CUSTOM (0x0e000090, 0x00000090, prep_emulate_ldr_str), + DECODE_EMULATEX (0x0e500090, 0x00500090, emulate_ldr, + REGS(NOPCWB, NOPC, 0, 0, 0)), DECODE_END }; @@ -1558,15 +1564,25 @@ static const union decode_item arm_cccc_01xx_table[] = { /* LDRB/STRB pc,[...] cccc 01xx x0xx xxxx xxxx xxxx xxxx xxxx */ DECODE_REJECT (0x0c40f000, 0x0440f000), - /* LDR cccc 01xx x0x1 xxxx xxxx xxxx xxxx xxxx */ - /* LDRB cccc 01xx x1x1 xxxx xxxx xxxx xxxx xxxx */ - /* LDRBT cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */ - /* LDRT cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */ - /* STR cccc 01xx x0x0 xxxx xxxx xxxx xxxx xxxx */ - /* STRB cccc 01xx x1x0 xxxx xxxx xxxx xxxx xxxx */ - /* STRBT cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */ - /* STRT cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */ - DECODE_CUSTOM (0x0c000000, 0x04000000, prep_emulate_ldr_str), + /* STR (immediate) cccc 010x x0x0 xxxx xxxx xxxx xxxx xxxx */ + /* STRB (immediate) cccc 010x x1x0 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0e100000, 0x04000000, emulate_str, + REGS(NOPCWB, ANY, 0, 0, 0)), + + /* LDR (immediate) cccc 010x x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* LDRB (immediate) cccc 010x x1x1 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0e100000, 0x04100000, emulate_ldr, + REGS(NOPCWB, ANY, 0, 0, 0)), + + /* STR (register) cccc 011x x0x0 xxxx xxxx xxxx xxxx xxxx */ + /* STRB (register) cccc 011x x1x0 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0e100000, 0x06000000, emulate_str, + REGS(NOPCWB, ANY, 0, 0, NOPC)), + + /* LDR (register) cccc 011x x0x1 xxxx xxxx xxxx xxxx xxxx */ + /* LDRB (register) cccc 011x x1x1 xxxx xxxx xxxx xxxx xxxx */ + DECODE_EMULATEX (0x0e100000, 0x06100000, emulate_ldr, + REGS(NOPCWB, ANY, 0, 0, NOPC)), DECODE_END }; -- cgit v1.2.3 From 465f1ea595a5040d8b9563e75e0b571a0bacb733 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Sat, 11 Jun 2011 15:16:41 +0100 Subject: ARM: kprobes: Reject probing of unprivileged load and store instructions These occur extremely rarely in the kernel and writing test cases for them is difficult. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 1ee38adeb82d..70e540b7c53b 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1262,6 +1262,13 @@ static const union decode_item arm_cccc_0001_____1001_table[] = { static const union decode_item arm_cccc_000x_____1xx1_table[] = { /* Extra load/store instructions */ + /* STRHT cccc 0000 xx10 xxxx xxxx xxxx 1011 xxxx */ + /* ??? cccc 0000 xx10 xxxx xxxx xxxx 11x1 xxxx */ + /* LDRHT cccc 0000 xx11 xxxx xxxx xxxx 1011 xxxx */ + /* LDRSBT cccc 0000 xx11 xxxx xxxx xxxx 1101 xxxx */ + /* LDRSHT cccc 0000 xx11 xxxx xxxx xxxx 1111 xxxx */ + DECODE_REJECT (0x0f200090, 0x00200090), + /* LDRD/STRD lr,pc,{... cccc 000x x0x0 xxxx 111x xxxx 1101 xxxx */ DECODE_REJECT (0x0e10e0d0, 0x0000e0d0), @@ -1564,6 +1571,12 @@ static const union decode_item arm_cccc_01xx_table[] = { /* LDRB/STRB pc,[...] cccc 01xx x0xx xxxx xxxx xxxx xxxx xxxx */ DECODE_REJECT (0x0c40f000, 0x0440f000), + /* STRT cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */ + /* LDRT cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */ + /* STRBT cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */ + /* LDRBT cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */ + DECODE_REJECT (0x0d200000, 0x04200000), + /* STR (immediate) cccc 010x x0x0 xxxx xxxx xxxx xxxx xxxx */ /* STRB (immediate) cccc 010x x1x0 xxxx xxxx xxxx xxxx xxxx */ DECODE_EMULATEX (0x0e100000, 0x04000000, emulate_str, -- cgit v1.2.3 From 0239269db6ba1ea908006fe309ade12991dd4e21 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Thu, 7 Jul 2011 18:25:20 +0100 Subject: ARM: kprobes: Decode ARM preload (immediate) instructions These were missing from the previous implementation. Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 70e540b7c53b..8a58c99f658d 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -1139,6 +1139,12 @@ static const union decode_item arm_1111_table[] = { /* PLD (immediate) 1111 0101 x101 xxxx xxxx xxxx xxxx xxxx */ DECODE_SIMULATE (0xfe300000, 0xf4100000, kprobe_simulate_nop), + /* memory hint 1111 0110 x001 xxxx xxxx xxxx xxx0 xxxx */ + /* PLDI (register) 1111 0110 x101 xxxx xxxx xxxx xxx0 xxxx */ + /* PLDW (register) 1111 0111 x001 xxxx xxxx xxxx xxx0 xxxx */ + /* PLD (register) 1111 0111 x101 xxxx xxxx xxxx xxx0 xxxx */ + DECODE_SIMULATE (0xfe300010, 0xf6100000, kprobe_simulate_nop), + /* BLX (immediate) 1111 101x xxxx xxxx xxxx xxxx xxxx xxxx */ DECODE_SIMULATE (0xfe000000, 0xfa000000, simulate_blx1), -- cgit v1.2.3 From 8f2ffa00fb3c05ec0659cd7b056c4e8e106072f1 Mon Sep 17 00:00:00 2001 From: Jon Medhurst Date: Mon, 13 Jun 2011 18:39:29 +0100 Subject: ARM: kprobes: Remove now unused code Signed-off-by: Jon Medhurst Acked-by: Nicolas Pitre --- arch/arm/kernel/kprobes-arm.c | 738 ------------------------------------------ 1 file changed, 738 deletions(-) diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 8a58c99f658d..79203ee1d039 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -74,300 +74,6 @@ "mov pc, "reg" \n\t" #endif -#define is_r15(insn, bitpos) (((insn) & (0xf << bitpos)) == (0xf << bitpos)) - -#define PSR_fs (PSR_f|PSR_s) - -#define KPROBE_RETURN_INSTRUCTION 0xe1a0f00e /* mov pc, lr */ - -typedef long (insn_0arg_fn_t)(void); -typedef long (insn_1arg_fn_t)(long); -typedef long (insn_2arg_fn_t)(long, long); -typedef long (insn_3arg_fn_t)(long, long, long); -typedef long (insn_4arg_fn_t)(long, long, long, long); -typedef long long (insn_llret_0arg_fn_t)(void); -typedef long long (insn_llret_3arg_fn_t)(long, long, long); -typedef long long (insn_llret_4arg_fn_t)(long, long, long, long); - -union reg_pair { - long long dr; -#ifdef __LITTLE_ENDIAN - struct { long r0, r1; }; -#else - struct { long r1, r0; }; -#endif -}; - -/* - * The insnslot_?arg_r[w]flags() functions below are to keep the - * msr -> *fn -> mrs instruction sequences indivisible so that - * the state of the CPSR flags aren't inadvertently modified - * just before or just after the call. - */ - -static inline long __kprobes -insnslot_0arg_rflags(long cpsr, insn_0arg_fn_t *fn) -{ - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long long __kprobes -insnslot_llret_0arg_rflags(long cpsr, insn_llret_0arg_fn_t *fn) -{ - register long ret0 asm("r0"); - register long ret1 asm("r1"); - union reg_pair fnr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret0), "=r" (ret1) - : [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - fnr.r0 = ret0; - fnr.r1 = ret1; - return fnr.dr; -} - -static inline long __kprobes -insnslot_1arg_rflags(long r0, long cpsr, insn_1arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long __kprobes -insnslot_2arg_rflags(long r0, long r1, long cpsr, insn_2arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), "r" (rr1), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long __kprobes -insnslot_3arg_rflags(long r0, long r1, long r2, long cpsr, insn_3arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), "r" (rr1), "r" (rr2), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long long __kprobes -insnslot_llret_3arg_rflags(long r0, long r1, long r2, long cpsr, - insn_llret_3arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long ret0 asm("r0"); - register long ret1 asm("r1"); - union reg_pair fnr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret0), "=r" (ret1) - : "0" (rr0), "r" (rr1), "r" (rr2), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - fnr.r0 = ret0; - fnr.r1 = ret1; - return fnr.dr; -} - -static inline long __kprobes -insnslot_4arg_rflags(long r0, long r1, long r2, long r3, long cpsr, - insn_4arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long rr3 asm("r3") = r3; - register long ret asm("r0"); - - __asm__ __volatile__ ( - "msr cpsr_fs, %[cpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - : "=r" (ret) - : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), - [cpsr] "r" (cpsr), [fn] "r" (fn) - : "lr", "cc" - ); - return ret; -} - -static inline long __kprobes -insnslot_1arg_rwflags(long r0, long *cpsr, insn_1arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long __kprobes -insnslot_2arg_rwflags(long r0, long r1, long *cpsr, insn_2arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long __kprobes -insnslot_3arg_rwflags(long r0, long r1, long r2, long *cpsr, - insn_3arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), "r" (rr2), - [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long __kprobes -insnslot_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr, - insn_4arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long rr3 asm("r3") = r3; - register long ret asm("r0"); - long oldcpsr = *cpsr; - long newcpsr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), - [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - return ret; -} - -static inline long long __kprobes -insnslot_llret_4arg_rwflags(long r0, long r1, long r2, long r3, long *cpsr, - insn_llret_4arg_fn_t *fn) -{ - register long rr0 asm("r0") = r0; - register long rr1 asm("r1") = r1; - register long rr2 asm("r2") = r2; - register long rr3 asm("r3") = r3; - register long ret0 asm("r0"); - register long ret1 asm("r1"); - long oldcpsr = *cpsr; - long newcpsr; - union reg_pair fnr; - - __asm__ __volatile__ ( - "msr cpsr_fs, %[oldcpsr] \n\t" - "mov lr, pc \n\t" - "mov pc, %[fn] \n\t" - "mrs %[newcpsr], cpsr \n\t" - : "=r" (ret0), "=r" (ret1), [newcpsr] "=r" (newcpsr) - : "0" (rr0), "r" (rr1), "r" (rr2), "r" (rr3), - [oldcpsr] "r" (oldcpsr), [fn] "r" (fn) - : "lr", "cc" - ); - *cpsr = (oldcpsr & ~PSR_fs) | (newcpsr & PSR_fs); - fnr.r0 = ret0; - fnr.r1 = ret1; - return fnr.dr; -} - /* * To avoid the complications of mimicing single-stepping on a * processor without a Next-PC or a single-step mode, and to @@ -449,450 +155,6 @@ static void __kprobes simulate_mov_ipsp(struct kprobe *p, struct pt_regs *regs) regs->uregs[12] = regs->uregs[13]; } -static void __kprobes emulate_ldrd(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; /* rm may be invalid, don't care. */ - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - - /* Not following the C calling convention here, so need asm(). */ - __asm__ __volatile__ ( - "ldr r0, %[rn] \n\t" - "ldr r1, %[rm] \n\t" - "msr cpsr_fs, %[cpsr]\n\t" - "mov lr, pc \n\t" - "mov pc, %[i_fn] \n\t" - "str r0, %[rn] \n\t" /* in case of writeback */ - "str r2, %[rd0] \n\t" - "str r3, %[rd1] \n\t" - : [rn] "+m" (rnv), - [rd0] "=m" (regs->uregs[rd]), - [rd1] "=m" (regs->uregs[rd+1]) - : [rm] "m" (rmv), - [cpsr] "r" (regs->ARM_cpsr), - [i_fn] "r" (i_fn) - : "r0", "r1", "r2", "r3", "lr", "cc" - ); - if (is_writeback(insn)) - regs->uregs[rn] = rnv; -} - -static void __kprobes emulate_strd(struct kprobe *p, struct pt_regs *regs) -{ - insn_4arg_fn_t *i_fn = (insn_4arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - /* rm/rmv may be invalid, don't care. */ - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rnv_wb; - - rnv_wb = insnslot_4arg_rflags(rnv, rmv, regs->uregs[rd], - regs->uregs[rd+1], - regs->ARM_cpsr, i_fn); - if (is_writeback(insn)) - regs->uregs[rn] = rnv_wb; -} - -static void __kprobes emulate_ldr_old(struct kprobe *p, struct pt_regs *regs) -{ - insn_llret_3arg_fn_t *i_fn = (insn_llret_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - union reg_pair fnr; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rdv; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long cpsr = regs->ARM_cpsr; - - fnr.dr = insnslot_llret_3arg_rflags(rnv, 0, rmv, cpsr, i_fn); - if (rn != 15) - regs->uregs[rn] = fnr.r0; /* Save Rn in case of writeback. */ - rdv = fnr.r1; - - if (rd == 15) { -#if __LINUX_ARM_ARCH__ >= 5 - cpsr &= ~PSR_T_BIT; - if (rdv & 0x1) - cpsr |= PSR_T_BIT; - regs->ARM_cpsr = cpsr; - rdv &= ~0x1; -#else - rdv &= ~0x2; -#endif - } - regs->uregs[rd] = rdv; -} - -static void __kprobes emulate_str_old(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long iaddr = (long)p->addr; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rdv = (rd == 15) ? iaddr + str_pc_offset : regs->uregs[rd]; - long rnv = (rn == 15) ? iaddr + 8 : regs->uregs[rn]; - long rmv = regs->uregs[rm]; /* rm/rmv may be invalid, don't care. */ - long rnv_wb; - - rnv_wb = insnslot_3arg_rflags(rnv, rdv, rmv, regs->ARM_cpsr, i_fn); - if (rn != 15) - regs->uregs[rn] = rnv_wb; /* Save Rn in case of writeback. */ -} - -static void __kprobes emulate_sat(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rm = insn & 0xf; - long rmv = regs->uregs[rm]; - - /* Writes Q flag */ - regs->uregs[rd] = insnslot_1arg_rwflags(rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_sel(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rnv = regs->uregs[rn]; - long rmv = regs->uregs[rm]; - - /* Reads GE bits */ - regs->uregs[rd] = insnslot_2arg_rflags(rnv, rmv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_none(struct kprobe *p, struct pt_regs *regs) -{ - insn_0arg_fn_t *i_fn = (insn_0arg_fn_t *)&p->ainsn.insn[0]; - - insnslot_0arg_rflags(regs->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_nop(struct kprobe *p, struct pt_regs *regs) -{ -} - -static void __kprobes -emulate_rd12_modify(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - long rdv = regs->uregs[rd]; - - regs->uregs[rd] = insnslot_1arg_rflags(rdv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd12rn0_modify(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = insn & 0xf; - long rdv = regs->uregs[rd]; - long rnv = regs->uregs[rn]; - - regs->uregs[rd] = insnslot_2arg_rflags(rdv, rnv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes emulate_rd12rm0(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rm = insn & 0xf; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = insnslot_1arg_rflags(rmv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd12rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - int rm = insn & 0xf; - long rnv = regs->uregs[rn]; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = - insnslot_2arg_rwflags(rnv, rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd16rn12rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 16) & 0xf; - int rn = (insn >> 12) & 0xf; - int rs = (insn >> 8) & 0xf; - int rm = insn & 0xf; - long rnv = regs->uregs[rn]; - long rsv = regs->uregs[rs]; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = - insnslot_3arg_rwflags(rnv, rsv, rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rd16rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_2arg_fn_t *i_fn = (insn_2arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 16) & 0xf; - int rs = (insn >> 8) & 0xf; - int rm = insn & 0xf; - long rsv = regs->uregs[rs]; - long rmv = regs->uregs[rm]; - - regs->uregs[rd] = - insnslot_2arg_rwflags(rsv, rmv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_rdhi16rdlo12rs8rm0_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_llret_4arg_fn_t *i_fn = (insn_llret_4arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - union reg_pair fnr; - int rdhi = (insn >> 16) & 0xf; - int rdlo = (insn >> 12) & 0xf; - int rs = (insn >> 8) & 0xf; - int rm = insn & 0xf; - long rsv = regs->uregs[rs]; - long rmv = regs->uregs[rm]; - - fnr.dr = insnslot_llret_4arg_rwflags(regs->uregs[rdhi], - regs->uregs[rdlo], rsv, rmv, - ®s->ARM_cpsr, i_fn); - regs->uregs[rdhi] = fnr.r0; - regs->uregs[rdlo] = fnr.r1; -} - -static void __kprobes -emulate_alu_imm_rflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; - - regs->uregs[rd] = insnslot_1arg_rflags(rnv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_imm_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; - long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; - - regs->uregs[rd] = insnslot_1arg_rwflags(rnv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_tests_imm(struct kprobe *p, struct pt_regs *regs) -{ - insn_1arg_fn_t *i_fn = (insn_1arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - int rn = (insn >> 16) & 0xf; - long rnv = (rn == 15) ? (long)p->addr + 8 : regs->uregs[rn]; - - insnslot_1arg_rwflags(rnv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_rflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; /* rn/rnv/rs/rsv may be */ - int rs = (insn >> 8) & 0xf; /* invalid, don't care. */ - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rsv = regs->uregs[rs]; - - regs->uregs[rd] = - insnslot_3arg_rflags(rnv, rmv, rsv, regs->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_rwflags(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rd = (insn >> 12) & 0xf; - int rn = (insn >> 16) & 0xf; /* rn/rnv/rs/rsv may be */ - int rs = (insn >> 8) & 0xf; /* invalid, don't care. */ - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rsv = regs->uregs[rs]; - - regs->uregs[rd] = - insnslot_3arg_rwflags(rnv, rmv, rsv, ®s->ARM_cpsr, i_fn); -} - -static void __kprobes -emulate_alu_tests(struct kprobe *p, struct pt_regs *regs) -{ - insn_3arg_fn_t *i_fn = (insn_3arg_fn_t *)&p->ainsn.insn[0]; - kprobe_opcode_t insn = p->opcode; - long ppc = (long)p->addr + 8; - int rn = (insn >> 16) & 0xf; - int rs = (insn >> 8) & 0xf; /* rs/rsv may be invalid, don't care. */ - int rm = insn & 0xf; - long rnv = (rn == 15) ? ppc : regs->uregs[rn]; - long rmv = (rm == 15) ? ppc : regs->uregs[rm]; - long rsv = regs->uregs[rs]; - - insnslot_3arg_rwflags(rnv, rmv, rsv, ®s->ARM_cpsr, i_fn); -} - -static enum kprobe_insn __kprobes -prep_emulate_ldr_str(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - int not_imm = (insn & (1 << 26)) ? (insn & (1 << 25)) - : (~insn & (1 << 22)); - - if (is_writeback(insn) && is_r15(insn, 16)) - return INSN_REJECTED; /* Writeback to PC */ - - insn &= 0xfff00fff; - insn |= 0x00001000; /* Rn = r0, Rd = r1 */ - if (not_imm) { - insn &= ~0xf; - insn |= 2; /* Rm = r2 */ - } - asi->insn[0] = insn; - asi->insn_handler = (insn & (1 << 20)) ? emulate_ldr_old : emulate_str_old; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12_modify(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xffff0fff; /* Rd = r0 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12_modify; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12rn0_modify(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xffff0ff0; /* Rd = r0 */ - insn |= 0x00000001; /* Rn = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12rn0_modify; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12rm0(kprobe_opcode_t insn, struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xffff0ff0; /* Rd = r0, Rm = r0 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12rm0; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd12rn16rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 12)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xfff00ff0; /* Rd = r0, Rn = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd12rn16rm0_rwflags; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd16rs8rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 16)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xfff0f0f0; /* Rd = r0, Rs = r0 */ - insn |= 0x00000001; /* Rm = r1 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd16rs8rm0_rwflags; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rd16rn12rs8rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 16)) - return INSN_REJECTED; /* Rd is PC */ - - insn &= 0xfff000f0; /* Rd = r0, Rn = r0 */ - insn |= 0x00000102; /* Rs = r1, Rm = r2 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rd16rn12rs8rm0_rwflags; - return INSN_GOOD; -} - -static enum kprobe_insn __kprobes -prep_emulate_rdhi16rdlo12rs8rm0_wflags(kprobe_opcode_t insn, - struct arch_specific_insn *asi) -{ - if (is_r15(insn, 16) || is_r15(insn, 12)) - return INSN_REJECTED; /* RdHi or RdLo is PC */ - - insn &= 0xfff000f0; /* RdHi = r0, RdLo = r1 */ - insn |= 0x00001203; /* Rs = r2, Rm = r3 */ - asi->insn[0] = insn; - asi->insn_handler = emulate_rdhi16rdlo12rs8rm0_rwflags; - return INSN_GOOD; -} - static void __kprobes emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs) { -- cgit v1.2.3 From 650320181a08b64d4421c65c639cf47ad8cc2cd6 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 18 Jul 2011 15:05:10 -0400 Subject: ARM: change ARM_DMA_ZONE_SIZE into a variable Having this value defined at compile time prevents multiple machines with conflicting definitions to coexist. Move it to a variable in preparation for having a per machine value selected at run time. This is relevant only when CONFIG_ZONE_DMA is selected. Signed-off-by: Nicolas Pitre --- arch/arm/include/asm/dma.h | 9 ++++++--- arch/arm/mm/init.c | 25 ++++++++++++++++--------- 2 files changed, 22 insertions(+), 12 deletions(-) diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h index 42005542932b..fcf15de8cadb 100644 --- a/arch/arm/include/asm/dma.h +++ b/arch/arm/include/asm/dma.h @@ -6,10 +6,13 @@ /* * This is the maximum virtual address which can be DMA'd from. */ -#ifndef ARM_DMA_ZONE_SIZE -#define MAX_DMA_ADDRESS 0xffffffff +#ifndef CONFIG_ZONE_DMA +#define MAX_DMA_ADDRESS 0xffffffffUL #else -#define MAX_DMA_ADDRESS (PAGE_OFFSET + ARM_DMA_ZONE_SIZE) +#define MAX_DMA_ADDRESS ({ \ + extern unsigned long arm_dma_zone_size; \ + arm_dma_zone_size ? \ + (PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; }) #endif #ifdef CONFIG_ISA_DMA_API diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 17d6cd0c57ed..4a8a01e0c3ab 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -212,6 +213,14 @@ static void __init arm_bootmem_init(unsigned long start_pfn, } #ifdef CONFIG_ZONE_DMA + +#ifdef ARM_DMA_ZONE_SIZE +unsigned long arm_dma_zone_size = ARM_DMA_ZONE_SIZE; +#else +unsigned long arm_dma_zone_size __read_mostly; +#endif +EXPORT_SYMBOL(arm_dma_zone_size); + /* * The DMA mask corresponding to the maximum bus address allocatable * using GFP_DMA. The default here places no restriction on DMA @@ -275,19 +284,17 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, #endif } -#ifdef ARM_DMA_ZONE_SIZE -#ifndef CONFIG_ZONE_DMA -#error ARM_DMA_ZONE_SIZE set but no DMA zone to limit allocations -#endif - +#ifdef CONFIG_ZONE_DMA /* * Adjust the sizes according to any special requirements for * this machine type. */ - arm_adjust_dma_zone(zone_size, zhole_size, - ARM_DMA_ZONE_SIZE >> PAGE_SHIFT); - - arm_dma_limit = PHYS_OFFSET + ARM_DMA_ZONE_SIZE - 1; + if (arm_dma_zone_size) { + arm_adjust_dma_zone(zone_size, zhole_size, + arm_dma_zone_size >> PAGE_SHIFT); + arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; + } else + arm_dma_limit = 0xffffffff; #endif free_area_init_node(0, zone_size, min, zhole_size); -- cgit v1.2.3 From 4fddcaebb9014b4814f859420595cc419400fba6 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:08 -0400 Subject: ARM: add dma_zone_size to the machine_desc structure Signed-off-by: Nicolas Pitre --- arch/arm/include/asm/mach/arch.h | 4 ++++ arch/arm/kernel/setup.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 946f4d778f71..3281fb4b12e3 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -23,6 +23,10 @@ struct machine_desc { unsigned int nr_irqs; /* number of IRQs */ +#ifdef CONFIG_ZONE_DMA + unsigned long dma_zone_size; /* size of DMA-able area */ +#endif + unsigned int video_start; /* start of video RAM */ unsigned int video_end; /* end of video RAM */ diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ed11fb08b05a..e0db84d7e384 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -916,6 +916,12 @@ void __init setup_arch(char **cmdline_p) cpu_init(); tcm_init(); +#ifdef CONFIG_ZONE_DMA + if (mdesc->dma_zone_size) { + extern unsigned long arm_dma_zone_size; + arm_dma_zone_size = mdesc->dma_zone_size; + } +#endif #ifdef CONFIG_MULTI_IRQ_HANDLER handle_arch_irq = mdesc->handle_irq; #endif -- cgit v1.2.3 From f68deabf3dc6c13fb80ec28575d0153c59f7ecce Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:08 -0400 Subject: ARM: mach-davinci: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-davinci/board-da830-evm.c | 1 + arch/arm/mach-davinci/board-da850-evm.c | 1 + arch/arm/mach-davinci/board-dm355-evm.c | 1 + arch/arm/mach-davinci/board-dm355-leopard.c | 1 + arch/arm/mach-davinci/board-dm365-evm.c | 1 + arch/arm/mach-davinci/board-dm644x-evm.c | 1 + arch/arm/mach-davinci/board-dm646x-evm.c | 2 ++ arch/arm/mach-davinci/board-mityomapl138.c | 1 + arch/arm/mach-davinci/board-neuros-osd2.c | 1 + arch/arm/mach-davinci/board-omapl138-hawk.c | 1 + arch/arm/mach-davinci/board-sffsdr.c | 1 + arch/arm/mach-davinci/board-tnetv107x-evm.c | 1 + arch/arm/mach-davinci/include/mach/memory.h | 7 ------- 13 files changed, 13 insertions(+), 7 deletions(-) diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c index 8bc3701aa05c..84fd78684868 100644 --- a/arch/arm/mach-davinci/board-da830-evm.c +++ b/arch/arm/mach-davinci/board-da830-evm.c @@ -681,4 +681,5 @@ MACHINE_START(DAVINCI_DA830_EVM, "DaVinci DA830/OMAP-L137/AM17x EVM") .init_irq = cp_intc_init, .timer = &davinci_timer, .init_machine = da830_evm_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index a7b41bf505f1..29671ef07152 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -1261,4 +1261,5 @@ MACHINE_START(DAVINCI_DA850_EVM, "DaVinci DA850/OMAP-L138/AM18x EVM") .init_irq = cp_intc_init, .timer = &davinci_timer, .init_machine = da850_evm_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c index 6e7cad13352c..241a6bd67408 100644 --- a/arch/arm/mach-davinci/board-dm355-evm.c +++ b/arch/arm/mach-davinci/board-dm355-evm.c @@ -356,4 +356,5 @@ MACHINE_START(DAVINCI_DM355_EVM, "DaVinci DM355 EVM") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = dm355_evm_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index 543f9911b281..bee284ca7fd6 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -275,4 +275,5 @@ MACHINE_START(DM355_LEOPARD, "DaVinci DM355 leopard") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = dm355_leopard_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index c67f684ee3e5..9844fa4cadc9 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -617,5 +617,6 @@ MACHINE_START(DAVINCI_DM365_EVM, "DaVinci DM365 EVM") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = dm365_evm_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index 556bbd468db3..95607a191e03 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -717,4 +717,5 @@ MACHINE_START(DAVINCI_EVM, "DaVinci DM644x EVM") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = davinci_evm_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index f6ac9ba74878..6d03643b9bd1 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -802,6 +802,7 @@ MACHINE_START(DAVINCI_DM6467_EVM, "DaVinci DM646x EVM") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = evm_init, + .dma_zone_size = SZ_128M, MACHINE_END MACHINE_START(DAVINCI_DM6467TEVM, "DaVinci DM6467T EVM") @@ -810,5 +811,6 @@ MACHINE_START(DAVINCI_DM6467TEVM, "DaVinci DM6467T EVM") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = evm_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c index 606a6f27ed6c..b8d59ca49027 100644 --- a/arch/arm/mach-davinci/board-mityomapl138.c +++ b/arch/arm/mach-davinci/board-mityomapl138.c @@ -570,4 +570,5 @@ MACHINE_START(MITYOMAPL138, "MityDSP-L138/MityARM-1808") .init_irq = cp_intc_init, .timer = &davinci_timer, .init_machine = mityomapl138_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c index 3e7be2de96de..d60a80028ba3 100644 --- a/arch/arm/mach-davinci/board-neuros-osd2.c +++ b/arch/arm/mach-davinci/board-neuros-osd2.c @@ -277,4 +277,5 @@ MACHINE_START(NEUROS_OSD2, "Neuros OSD2") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = davinci_ntosd2_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c index 67c38d0ecd10..237332a11421 100644 --- a/arch/arm/mach-davinci/board-omapl138-hawk.c +++ b/arch/arm/mach-davinci/board-omapl138-hawk.c @@ -343,4 +343,5 @@ MACHINE_START(OMAPL138_HAWKBOARD, "AM18x/OMAP-L138 Hawkboard") .init_irq = cp_intc_init, .timer = &davinci_timer, .init_machine = omapl138_hawk_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c index 61ac96d8f00d..5f4385c0a089 100644 --- a/arch/arm/mach-davinci/board-sffsdr.c +++ b/arch/arm/mach-davinci/board-sffsdr.c @@ -156,4 +156,5 @@ MACHINE_START(SFFSDR, "Lyrtech SFFSDR") .init_irq = davinci_irq_init, .timer = &davinci_timer, .init_machine = davinci_sffsdr_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/board-tnetv107x-evm.c b/arch/arm/mach-davinci/board-tnetv107x-evm.c index 1a656e882262..782892065682 100644 --- a/arch/arm/mach-davinci/board-tnetv107x-evm.c +++ b/arch/arm/mach-davinci/board-tnetv107x-evm.c @@ -282,4 +282,5 @@ MACHINE_START(TNETV107X, "TNETV107X EVM") .init_irq = cp_intc_init, .timer = &davinci_timer, .init_machine = tnetv107x_evm_board_init, + .dma_zone_size = SZ_128M, MACHINE_END diff --git a/arch/arm/mach-davinci/include/mach/memory.h b/arch/arm/mach-davinci/include/mach/memory.h index 491249ef209c..78731944a70c 100644 --- a/arch/arm/mach-davinci/include/mach/memory.h +++ b/arch/arm/mach-davinci/include/mach/memory.h @@ -41,11 +41,4 @@ */ #define CONSISTENT_DMA_SIZE (14<<20) -/* - * Restrict DMA-able region to workaround silicon bug. The bug - * restricts buffers available for DMA to video hardware to be - * below 128M - */ -#define ARM_DMA_ZONE_SIZE SZ_128M - #endif /* __ASM_ARCH_MEMORY_H */ -- cgit v1.2.3 From 5065c71d7567a98de0550708e5427a187033d8a3 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:08 -0400 Subject: ARM: mach-h720x: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-h720x/h7201-eval.c | 1 + arch/arm/mach-h720x/h7202-eval.c | 1 + arch/arm/mach-h720x/include/mach/memory.h | 7 ------- 3 files changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/arm/mach-h720x/h7201-eval.c b/arch/arm/mach-h720x/h7201-eval.c index 629454d71c8d..65f1bea958e5 100644 --- a/arch/arm/mach-h720x/h7201-eval.c +++ b/arch/arm/mach-h720x/h7201-eval.c @@ -33,4 +33,5 @@ MACHINE_START(H7201, "Hynix GMS30C7201") .map_io = h720x_map_io, .init_irq = h720x_init_irq, .timer = &h7201_timer, + .dma_zone_size = SZ_256M, MACHINE_END diff --git a/arch/arm/mach-h720x/h7202-eval.c b/arch/arm/mach-h720x/h7202-eval.c index e9f46b696354..884584a09752 100644 --- a/arch/arm/mach-h720x/h7202-eval.c +++ b/arch/arm/mach-h720x/h7202-eval.c @@ -76,4 +76,5 @@ MACHINE_START(H7202, "Hynix HMS30C7202") .init_irq = h7202_init_irq, .timer = &h7202_timer, .init_machine = init_eval_h7202, + .dma_zone_size = SZ_256M, MACHINE_END diff --git a/arch/arm/mach-h720x/include/mach/memory.h b/arch/arm/mach-h720x/include/mach/memory.h index b0b3baec9acf..96dcf50c51d3 100644 --- a/arch/arm/mach-h720x/include/mach/memory.h +++ b/arch/arm/mach-h720x/include/mach/memory.h @@ -8,11 +8,4 @@ #define __ASM_ARCH_MEMORY_H #define PLAT_PHYS_OFFSET UL(0x40000000) -/* - * This is the maximum DMA address that can be DMAd to. - * There should not be more than (0xd0000000 - 0xc0000000) - * bytes of RAM. - */ -#define ARM_DMA_ZONE_SIZE SZ_256M - #endif -- cgit v1.2.3 From 7553ee777b513c3bc8f45bb9fc75fb1bbc584ba1 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:09 -0400 Subject: ARM: mach-ixp4xx: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-ixp4xx/avila-setup.c | 6 ++++++ arch/arm/mach-ixp4xx/coyote-setup.c | 3 +++ arch/arm/mach-ixp4xx/dsmg600-setup.c | 3 +++ arch/arm/mach-ixp4xx/fsg-setup.c | 3 +++ arch/arm/mach-ixp4xx/gateway7001-setup.c | 3 +++ arch/arm/mach-ixp4xx/goramo_mlr.c | 3 +++ arch/arm/mach-ixp4xx/gtwx5715-setup.c | 3 +++ arch/arm/mach-ixp4xx/include/mach/memory.h | 4 ---- arch/arm/mach-ixp4xx/ixdp425-setup.c | 12 ++++++++++++ arch/arm/mach-ixp4xx/nas100d-setup.c | 3 +++ arch/arm/mach-ixp4xx/nslu2-setup.c | 3 +++ arch/arm/mach-ixp4xx/vulcan-setup.c | 3 +++ arch/arm/mach-ixp4xx/wg302v2-setup.c | 3 +++ 13 files changed, 48 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c index 73745ff102d5..ee19c1d383aa 100644 --- a/arch/arm/mach-ixp4xx/avila-setup.c +++ b/arch/arm/mach-ixp4xx/avila-setup.c @@ -169,6 +169,9 @@ MACHINE_START(AVILA, "Gateworks Avila Network Platform") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = avila_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END /* @@ -184,6 +187,9 @@ MACHINE_START(LOFT, "Giant Shoulder Inc Loft board") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = avila_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif diff --git a/arch/arm/mach-ixp4xx/coyote-setup.c b/arch/arm/mach-ixp4xx/coyote-setup.c index 355e3de38733..e24564b5d935 100644 --- a/arch/arm/mach-ixp4xx/coyote-setup.c +++ b/arch/arm/mach-ixp4xx/coyote-setup.c @@ -114,6 +114,9 @@ MACHINE_START(ADI_COYOTE, "ADI Engineering Coyote") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = coyote_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c index d398229cfaa5..03e54515e8b3 100644 --- a/arch/arm/mach-ixp4xx/dsmg600-setup.c +++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c @@ -284,4 +284,7 @@ MACHINE_START(DSMG600, "D-Link DSM-G600 RevA") .init_irq = ixp4xx_init_irq, .timer = &dsmg600_timer, .init_machine = dsmg600_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c index 727ee39ce11c..23a8b3614568 100644 --- a/arch/arm/mach-ixp4xx/fsg-setup.c +++ b/arch/arm/mach-ixp4xx/fsg-setup.c @@ -275,5 +275,8 @@ MACHINE_START(FSG, "Freecom FSG-3") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = fsg_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/gateway7001-setup.c b/arch/arm/mach-ixp4xx/gateway7001-setup.c index 9dc0b4eaa65a..d4f851bdd9a4 100644 --- a/arch/arm/mach-ixp4xx/gateway7001-setup.c +++ b/arch/arm/mach-ixp4xx/gateway7001-setup.c @@ -101,5 +101,8 @@ MACHINE_START(GATEWAY7001, "Gateway 7001 AP") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = gateway7001_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c index 3e8c0e33b59c..5f00ad224fe0 100644 --- a/arch/arm/mach-ixp4xx/goramo_mlr.c +++ b/arch/arm/mach-ixp4xx/goramo_mlr.c @@ -501,4 +501,7 @@ MACHINE_START(GORAMO_MLR, "MultiLink") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = gmlr_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/gtwx5715-setup.c b/arch/arm/mach-ixp4xx/gtwx5715-setup.c index 77abead36227..3790dffd3c30 100644 --- a/arch/arm/mach-ixp4xx/gtwx5715-setup.c +++ b/arch/arm/mach-ixp4xx/gtwx5715-setup.c @@ -169,6 +169,9 @@ MACHINE_START(GTWX5715, "Gemtek GTWX5715 (Linksys WRV54G)") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = gtwx5715_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/include/mach/memory.h b/arch/arm/mach-ixp4xx/include/mach/memory.h index 34e79404671a..4caf1761f1e2 100644 --- a/arch/arm/mach-ixp4xx/include/mach/memory.h +++ b/arch/arm/mach-ixp4xx/include/mach/memory.h @@ -14,8 +14,4 @@ */ #define PLAT_PHYS_OFFSET UL(0x00000000) -#ifdef CONFIG_PCI -#define ARM_DMA_ZONE_SIZE SZ_64M -#endif - #endif diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c index dca4f7f9f4f7..6a2927956bf6 100644 --- a/arch/arm/mach-ixp4xx/ixdp425-setup.c +++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c @@ -258,6 +258,9 @@ MACHINE_START(IXDP425, "Intel IXDP425 Development Platform") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = ixdp425_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif @@ -269,6 +272,9 @@ MACHINE_START(IXDP465, "Intel IXDP465 Development Platform") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = ixdp425_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif @@ -280,6 +286,9 @@ MACHINE_START(IXCDP1100, "Intel IXCDP1100 Development Platform") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = ixdp425_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif @@ -291,5 +300,8 @@ MACHINE_START(KIXRP435, "Intel KIXRP435 Reference Platform") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = ixdp425_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c index f18fee748878..afb51879d9a4 100644 --- a/arch/arm/mach-ixp4xx/nas100d-setup.c +++ b/arch/arm/mach-ixp4xx/nas100d-setup.c @@ -319,4 +319,7 @@ MACHINE_START(NAS100D, "Iomega NAS 100d") .init_irq = ixp4xx_init_irq, .timer = &ixp4xx_timer, .init_machine = nas100d_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c index f79b62eb7614..69e40f2cf092 100644 --- a/arch/arm/mach-ixp4xx/nslu2-setup.c +++ b/arch/arm/mach-ixp4xx/nslu2-setup.c @@ -305,4 +305,7 @@ MACHINE_START(NSLU2, "Linksys NSLU2") .init_irq = ixp4xx_init_irq, .timer = &nslu2_timer, .init_machine = nslu2_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c index 4e72cfdd3c46..045336c833af 100644 --- a/arch/arm/mach-ixp4xx/vulcan-setup.c +++ b/arch/arm/mach-ixp4xx/vulcan-setup.c @@ -241,4 +241,7 @@ MACHINE_START(ARCOM_VULCAN, "Arcom/Eurotech Vulcan") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = vulcan_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-ixp4xx/wg302v2-setup.c b/arch/arm/mach-ixp4xx/wg302v2-setup.c index 5d148c7bc4fb..40b9fad800b8 100644 --- a/arch/arm/mach-ixp4xx/wg302v2-setup.c +++ b/arch/arm/mach-ixp4xx/wg302v2-setup.c @@ -102,5 +102,8 @@ MACHINE_START(WG302V2, "Netgear WG302 v2 / WAG302 v2") .timer = &ixp4xx_timer, .boot_params = 0x0100, .init_machine = wg302v2_init, +#if defined(CONFIG_PCI) + .dma_zone_size = SZ_64M, +#endif MACHINE_END #endif -- cgit v1.2.3 From 805e88dc40bbcc924797cfcac524931774c6e46c Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:09 -0400 Subject: ARM: mach-pxa: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-pxa/cm-x2xx.c | 3 +++ arch/arm/mach-pxa/include/mach/memory.h | 4 ---- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-pxa/cm-x2xx.c b/arch/arm/mach-pxa/cm-x2xx.c index a10996782476..bc55d07566ca 100644 --- a/arch/arm/mach-pxa/cm-x2xx.c +++ b/arch/arm/mach-pxa/cm-x2xx.c @@ -518,4 +518,7 @@ MACHINE_START(ARMCORE, "Compulab CM-X2XX") .init_irq = cmx2xx_init_irq, .timer = &pxa_timer, .init_machine = cmx2xx_init, +#ifdef CONFIG_PCI + .dma_zone_size = SZ_64M, +#endif MACHINE_END diff --git a/arch/arm/mach-pxa/include/mach/memory.h b/arch/arm/mach-pxa/include/mach/memory.h index 07734f37f8fd..d05a59727d66 100644 --- a/arch/arm/mach-pxa/include/mach/memory.h +++ b/arch/arm/mach-pxa/include/mach/memory.h @@ -17,8 +17,4 @@ */ #define PLAT_PHYS_OFFSET UL(0xa0000000) -#if defined(CONFIG_MACH_ARMCORE) && defined(CONFIG_PCI) -#define ARM_DMA_ZONE_SIZE SZ_64M -#endif - #endif -- cgit v1.2.3 From 00e9125e061022dcba2daea95491d5400c47789b Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:09 -0400 Subject: ARM: mach-realview: move from ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-realview/include/mach/memory.h | 4 ---- arch/arm/mach-realview/realview_eb.c | 3 +++ arch/arm/mach-realview/realview_pb1176.c | 3 +++ arch/arm/mach-realview/realview_pb11mp.c | 3 +++ arch/arm/mach-realview/realview_pba8.c | 3 +++ arch/arm/mach-realview/realview_pbx.c | 3 +++ 6 files changed, 15 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-realview/include/mach/memory.h b/arch/arm/mach-realview/include/mach/memory.h index 1759fa673eea..2022e092f0ca 100644 --- a/arch/arm/mach-realview/include/mach/memory.h +++ b/arch/arm/mach-realview/include/mach/memory.h @@ -29,10 +29,6 @@ #define PLAT_PHYS_OFFSET UL(0x00000000) #endif -#ifdef CONFIG_ZONE_DMA -#define ARM_DMA_ZONE_SIZE SZ_256M -#endif - #ifdef CONFIG_SPARSEMEM /* diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c index 10e75faba4c9..7a4e3b18cb3e 100644 --- a/arch/arm/mach-realview/realview_eb.c +++ b/arch/arm/mach-realview/realview_eb.c @@ -470,4 +470,7 @@ MACHINE_START(REALVIEW_EB, "ARM-RealView EB") .init_irq = gic_init_irq, .timer = &realview_eb_timer, .init_machine = realview_eb_init, +#ifdef CONFIG_ZONE_DMA + .dma_zone_size = SZ_256M, +#endif MACHINE_END diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c index eab6070f66d0..ad5671acb66a 100644 --- a/arch/arm/mach-realview/realview_pb1176.c +++ b/arch/arm/mach-realview/realview_pb1176.c @@ -365,4 +365,7 @@ MACHINE_START(REALVIEW_PB1176, "ARM-RealView PB1176") .init_irq = gic_init_irq, .timer = &realview_pb1176_timer, .init_machine = realview_pb1176_init, +#ifdef CONFIG_ZONE_DMA + .dma_zone_size = SZ_256M, +#endif MACHINE_END diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c index b2985fc7cd4e..b43644b3685e 100644 --- a/arch/arm/mach-realview/realview_pb11mp.c +++ b/arch/arm/mach-realview/realview_pb11mp.c @@ -367,4 +367,7 @@ MACHINE_START(REALVIEW_PB11MP, "ARM-RealView PB11MPCore") .init_irq = gic_init_irq, .timer = &realview_pb11mp_timer, .init_machine = realview_pb11mp_init, +#ifdef CONFIG_ZONE_DMA + .dma_zone_size = SZ_256M, +#endif MACHINE_END diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c index fb6866558760..763e8f38c15d 100644 --- a/arch/arm/mach-realview/realview_pba8.c +++ b/arch/arm/mach-realview/realview_pba8.c @@ -317,4 +317,7 @@ MACHINE_START(REALVIEW_PBA8, "ARM-RealView PB-A8") .init_irq = gic_init_irq, .timer = &realview_pba8_timer, .init_machine = realview_pba8_init, +#ifdef CONFIG_ZONE_DMA + .dma_zone_size = SZ_256M, +#endif MACHINE_END diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c index 92ace2cf2b2c..363b0ab56150 100644 --- a/arch/arm/mach-realview/realview_pbx.c +++ b/arch/arm/mach-realview/realview_pbx.c @@ -400,4 +400,7 @@ MACHINE_START(REALVIEW_PBX, "ARM-RealView PBX") .init_irq = gic_init_irq, .timer = &realview_pbx_timer, .init_machine = realview_pbx_init, +#ifdef CONFIG_ZONE_DMA + .dma_zone_size = SZ_256M, +#endif MACHINE_END -- cgit v1.2.3 From e9107ab623648587a044ee925c1708655bdf9813 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:09 -0400 Subject: ARM: mach-sa1100: move ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-sa1100/assabet.c | 3 +++ arch/arm/mach-sa1100/badge4.c | 3 +++ arch/arm/mach-sa1100/include/mach/memory.h | 4 ---- arch/arm/mach-sa1100/jornada720.c | 3 +++ 4 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index 5778274a8260..26257df19b63 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -453,4 +453,7 @@ MACHINE_START(ASSABET, "Intel-Assabet") .init_irq = sa1100_init_irq, .timer = &sa1100_timer, .init_machine = assabet_init, +#ifdef CONFIG_SA1111 + .dma_zone_size = SZ_1M, +#endif MACHINE_END diff --git a/arch/arm/mach-sa1100/badge4.c b/arch/arm/mach-sa1100/badge4.c index 4f19ff868b00..b4311b0a4395 100644 --- a/arch/arm/mach-sa1100/badge4.c +++ b/arch/arm/mach-sa1100/badge4.c @@ -306,4 +306,7 @@ MACHINE_START(BADGE4, "Hewlett-Packard Laboratories BadgePAD 4") .map_io = badge4_map_io, .init_irq = sa1100_init_irq, .timer = &sa1100_timer, +#ifdef CONFIG_SA1111 + .dma_zone_size = SZ_1M, +#endif MACHINE_END diff --git a/arch/arm/mach-sa1100/include/mach/memory.h b/arch/arm/mach-sa1100/include/mach/memory.h index cff31ee246b7..12d376795abc 100644 --- a/arch/arm/mach-sa1100/include/mach/memory.h +++ b/arch/arm/mach-sa1100/include/mach/memory.h @@ -14,10 +14,6 @@ */ #define PLAT_PHYS_OFFSET UL(0xc0000000) -#ifdef CONFIG_SA1111 -#define ARM_DMA_ZONE_SIZE SZ_1M -#endif - /* * Because of the wide memory address space between physical RAM banks on the * SA1100, it's much convenient to use Linux's SparseMEM support to implement diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c index 491ac9f20fb4..176c066aec7e 100644 --- a/arch/arm/mach-sa1100/jornada720.c +++ b/arch/arm/mach-sa1100/jornada720.c @@ -369,4 +369,7 @@ MACHINE_START(JORNADA720, "HP Jornada 720") .init_irq = sa1100_init_irq, .timer = &sa1100_timer, .init_machine = jornada720_mach_init, +#ifdef CONFIG_SA1111 + .dma_zone_size = SZ_1M, +#endif MACHINE_END -- cgit v1.2.3 From fded1ef9c55e30d91508487c45334c8947cc5f7b Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 5 Jul 2011 22:28:09 -0400 Subject: ARM: mach-shark: move ARM_DMA_ZONE_SIZE to mdesc->dma_zone_size Signed-off-by: Nicolas Pitre --- arch/arm/mach-shark/core.c | 1 + arch/arm/mach-shark/include/mach/memory.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c index 5cf7f94c1f31..ac2873c8014b 100644 --- a/arch/arm/mach-shark/core.c +++ b/arch/arm/mach-shark/core.c @@ -156,4 +156,5 @@ MACHINE_START(SHARK, "Shark") .map_io = shark_map_io, .init_irq = shark_init_irq, .timer = &shark_timer, + .dma_zone_size = SZ_4M, MACHINE_END diff --git a/arch/arm/mach-shark/include/mach/memory.h b/arch/arm/mach-shark/include/mach/memory.h index 4c0831f83b0c..1cf8d6962617 100644 --- a/arch/arm/mach-shark/include/mach/memory.h +++ b/arch/arm/mach-shark/include/mach/memory.h @@ -17,8 +17,6 @@ */ #define PLAT_PHYS_OFFSET UL(0x08000000) -#define ARM_DMA_ZONE_SIZE SZ_4M - /* * Cache flushing area */ -- cgit v1.2.3 From fb89fcfb151698776be6c900aec8161b01990e92 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 18 Jul 2011 15:17:15 -0400 Subject: ARM: ARM_DMA_ZONE_SIZE is no more One less dependency on mach/memory.h. Signed-off-by: Nicolas Pitre --- arch/arm/include/asm/dma.h | 2 -- arch/arm/mm/init.c | 5 ----- 2 files changed, 7 deletions(-) diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h index fcf15de8cadb..628670e9d7c9 100644 --- a/arch/arm/include/asm/dma.h +++ b/arch/arm/include/asm/dma.h @@ -1,8 +1,6 @@ #ifndef __ASM_ARM_DMA_H #define __ASM_ARM_DMA_H -#include - /* * This is the maximum virtual address which can be DMA'd from. */ diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 4a8a01e0c3ab..90a38c6baca4 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include @@ -214,11 +213,7 @@ static void __init arm_bootmem_init(unsigned long start_pfn, #ifdef CONFIG_ZONE_DMA -#ifdef ARM_DMA_ZONE_SIZE -unsigned long arm_dma_zone_size = ARM_DMA_ZONE_SIZE; -#else unsigned long arm_dma_zone_size __read_mostly; -#endif EXPORT_SYMBOL(arm_dma_zone_size); /* -- cgit v1.2.3 From 4348810a241a330d3d143d62d7c988ec8b2e6629 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 5 Jul 2011 09:01:13 +0100 Subject: ARM: btc: avoid invalidating the branch target cache on kernel TLB maintanence Kernel space needs very little in the way of BTC maintanence as most mappings which are created and destroyed are non-executable, and so could never enter the instruction stream. The case which does warrant BTC maintanence is when a module is loaded. This creates a new executable mapping, but at that point the pages have not been initialized with code and data, so at that point they contain unpredictable information. Invalidating the BTC at this stage serves little useful purpose. Before we execute module code, we call flush_icache_range(), which deals with the BTC maintanence requirements. This ensures that we have a BTC maintanence operation before we execute code via the newly created mapping. Signed-off-by: Russell King --- arch/arm/include/asm/tlbflush.h | 58 +++++++---------------------------------- arch/arm/mm/tlb-fa.S | 4 +-- arch/arm/mm/tlb-v6.S | 4 +-- arch/arm/mm/tlb-v7.S | 6 ----- 4 files changed, 12 insertions(+), 60 deletions(-) diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index d2005de383b8..8077145698ff 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -34,16 +34,12 @@ #define TLB_V6_D_ASID (1 << 17) #define TLB_V6_I_ASID (1 << 18) -#define TLB_BTB (1 << 28) - /* Unified Inner Shareable TLB operations (ARMv7 MP extensions) */ #define TLB_V7_UIS_PAGE (1 << 19) #define TLB_V7_UIS_FULL (1 << 20) #define TLB_V7_UIS_ASID (1 << 21) -/* Inner Shareable BTB operation (ARMv7 MP extensions) */ -#define TLB_V7_IS_BTB (1 << 22) - +#define TLB_BARRIER (1 << 28) #define TLB_L2CLEAN_FR (1 << 29) /* Feroceon */ #define TLB_DCLEAN (1 << 30) #define TLB_WB (1 << 31) @@ -58,7 +54,7 @@ * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction * fr - Feroceon (v4wbi with non-outer-cacheable page table walks) - * fa - Faraday (v4 with write buffer with UTLB and branch target buffer (BTB)) + * fa - Faraday (v4 with write buffer with UTLB) * v6wbi - ARMv6 with write buffer with I TLB flush entry instruction * v7wbi - identical to v6wbi */ @@ -99,7 +95,7 @@ # define v4_always_flags (-1UL) #endif -#define fa_tlb_flags (TLB_WB | TLB_BTB | TLB_DCLEAN | \ +#define fa_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ TLB_V4_U_FULL | TLB_V4_U_PAGE) #ifdef CONFIG_CPU_TLB_FA @@ -166,7 +162,7 @@ # define v4wb_always_flags (-1UL) #endif -#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \ +#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ TLB_V6_I_FULL | TLB_V6_D_FULL | \ TLB_V6_I_PAGE | TLB_V6_D_PAGE | \ TLB_V6_I_ASID | TLB_V6_D_ASID) @@ -184,9 +180,9 @@ # define v6wbi_always_flags (-1UL) #endif -#define v7wbi_tlb_flags_smp (TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \ +#define v7wbi_tlb_flags_smp (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID) -#define v7wbi_tlb_flags_up (TLB_WB | TLB_DCLEAN | TLB_BTB | \ +#define v7wbi_tlb_flags_up (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \ TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID) #ifdef CONFIG_CPU_TLB_V7 @@ -341,15 +337,7 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_V7_UIS_FULL)) asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc"); - if (tlb_flag(TLB_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc"); - dsb(); - isb(); - } - if (tlb_flag(TLB_V7_IS_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc"); + if (tlb_flag(TLB_BARRIER)) { dsb(); isb(); } @@ -389,17 +377,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc"); #endif - if (tlb_flag(TLB_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc"); - dsb(); - } - if (tlb_flag(TLB_V7_IS_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc"); + if (tlb_flag(TLB_BARRIER)) dsb(); - isb(); - } } static inline void @@ -439,17 +418,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc"); #endif - if (tlb_flag(TLB_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc"); - dsb(); - } - if (tlb_flag(TLB_V7_IS_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc"); + if (tlb_flag(TLB_BARRIER)) dsb(); - isb(); - } } static inline void local_flush_tlb_kernel_page(unsigned long kaddr) @@ -482,15 +452,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_V7_UIS_PAGE)) asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc"); - if (tlb_flag(TLB_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero) : "cc"); - dsb(); - isb(); - } - if (tlb_flag(TLB_V7_IS_BTB)) { - /* flush the branch target cache */ - asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero) : "cc"); + if (tlb_flag(TLB_BARRIER)) { dsb(); isb(); } diff --git a/arch/arm/mm/tlb-fa.S b/arch/arm/mm/tlb-fa.S index 9694f1f6f485..d887a31faaae 100644 --- a/arch/arm/mm/tlb-fa.S +++ b/arch/arm/mm/tlb-fa.S @@ -46,7 +46,6 @@ ENTRY(fa_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mcr p15, 0, r3, c7, c5, 6 @ invalidate BTB mcr p15, 0, r3, c7, c10, 4 @ data write barrier mov pc, lr @@ -60,9 +59,8 @@ ENTRY(fa_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mcr p15, 0, r3, c7, c5, 6 @ invalidate BTB mcr p15, 0, r3, c7, c10, 4 @ data write barrier - mcr p15, 0, r3, c7, c5, 4 @ prefetch flush + mcr p15, 0, r3, c7, c5, 4 @ prefetch flush (isb) mov pc, lr __INITDATA diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S index 73d7d89b04c4..ffe06a69a6e5 100644 --- a/arch/arm/mm/tlb-v6.S +++ b/arch/arm/mm/tlb-v6.S @@ -54,7 +54,6 @@ ENTRY(v6wbi_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mcr p15, 0, ip, c7, c5, 6 @ flush BTAC/BTB mcr p15, 0, ip, c7, c10, 4 @ data synchronization barrier mov pc, lr @@ -83,9 +82,8 @@ ENTRY(v6wbi_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB mcr p15, 0, r2, c7, c10, 4 @ data synchronization barrier - mcr p15, 0, r2, c7, c5, 4 @ prefetch flush + mcr p15, 0, r2, c7, c5, 4 @ prefetch flush (isb) mov pc, lr __INIT diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index 53cd5b454673..86bb71664508 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -48,9 +48,6 @@ ENTRY(v7wbi_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov ip, #0 - ALT_SMP(mcr p15, 0, ip, c7, c1, 6) @ flush BTAC/BTB Inner Shareable - ALT_UP(mcr p15, 0, ip, c7, c5, 6) @ flush BTAC/BTB dsb mov pc, lr ENDPROC(v7wbi_flush_user_tlb_range) @@ -75,9 +72,6 @@ ENTRY(v7wbi_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov r2, #0 - ALT_SMP(mcr p15, 0, r2, c7, c1, 6) @ flush BTAC/BTB Inner Shareable - ALT_UP(mcr p15, 0, r2, c7, c5, 6) @ flush BTAC/BTB dsb isb mov pc, lr -- cgit v1.2.3 From 540b573875bd26dfe39aa18d22dc195f275fc0df Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Wed, 13 Jul 2011 15:53:30 +0100 Subject: ARM: 6999/1: head, zImage: Always Enter the kernel in ARM state Currently, the documented kernel entry requirements are not explicit about whether the kernel should be entered in ARM or Thumb, leading to an ambiguitity about how to enter Thumb-2 kernels. As a result, the kernel is reliant on the zImage decompressor to enter the kernel proper in the correct instruction set state. This patch changes the boot entry protocol for head.S and Image to be the same as for zImage: in all cases, the kernel is now entered in ARM. Documentation/arm/Booting is updated to reflect this new policy. A different rule will be needed for Cortex-M class CPUs as and when support for those lands in mainline, since these CPUs don't support the ARM instruction set at all: a note is added to the effect that the kernel must be entered in Thumb on such systems. Signed-off-by: Dave Martin Acked-by: Nicolas Pitre Signed-off-by: Russell King --- Documentation/arm/Booting | 5 +++++ arch/arm/boot/compressed/head.S | 3 ++- arch/arm/kernel/head-nommu.S | 8 ++++++++ arch/arm/kernel/head.S | 8 ++++++++ 4 files changed, 23 insertions(+), 1 deletion(-) diff --git a/Documentation/arm/Booting b/Documentation/arm/Booting index 4e686a2ed91e..a341d87d276e 100644 --- a/Documentation/arm/Booting +++ b/Documentation/arm/Booting @@ -164,3 +164,8 @@ In either case, the following conditions must be met: - The boot loader is expected to call the kernel image by jumping directly to the first instruction of the kernel image. + On CPUs supporting the ARM instruction set, the entry must be + made in ARM state, even for a Thumb-2 kernel. + + On CPUs supporting only the Thumb instruction set such as + Cortex-M class CPUs, the entry must be made in Thumb state. diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index f9da41921c52..51af7091d84d 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -353,7 +353,8 @@ not_relocated: mov r0, #0 mov r0, #0 @ must be zero mov r1, r7 @ restore architecture number mov r2, r8 @ restore atags pointer - mov pc, r4 @ call kernel + ARM( mov pc, r4 ) @ call kernel + THUMB( bx r4 ) @ entry point is always ARM .align 2 .type LC0, #object diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 6b1e0ad9ec3b..d46f25968bec 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -32,8 +32,16 @@ * numbers for r1. * */ + .arm + __HEAD ENTRY(stext) + + THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. + THUMB( bx r9 ) @ If this is a Thumb-2 kernel, + THUMB( .thumb ) @ switch to Thumb now. + THUMB(1: ) + setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode @ and irqs disabled #ifndef CONFIG_CPU_CP15 diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 278c1b0ebb2e..742b6108a001 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -71,8 +71,16 @@ * crap here - that's what the boot loader (or in extreme, well justified * circumstances, zImage) is for. */ + .arm + __HEAD ENTRY(stext) + + THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. + THUMB( bx r9 ) @ If this is a Thumb-2 kernel, + THUMB( .thumb ) @ switch to Thumb now. + THUMB(1: ) + setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode @ and irqs disabled mrc p15, 0, r9, c0, c0 @ get processor id -- cgit v1.2.3 From 140d5dc1d7d86d766951b7a9aef5b66f1dfdfae2 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 13 Jul 2011 16:32:58 +0100 Subject: ARM: 7000/1: LPAE: Use long long printk format for displaying the pud Currently using just long but this is not enough for the LPAE format (64-bit entries). Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index bc0e1d88fd3b..ee7692341576 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -94,7 +94,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr) pud = pud_offset(pgd, addr); if (PTRS_PER_PUD != 1) - printk(", *pud=%08lx", pud_val(*pud)); + printk(", *pud=%08llx", (long long)pud_val(*pud)); if (pud_none(*pud)) break; -- cgit v1.2.3 From 7f294e4983b67be802277d139522837b3ce5769f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 8 Jul 2011 09:57:15 +0100 Subject: ARM: 6981/2: mmci: adjust calculation of f_min The ARM version maximum clock divider is 512 whereas for the ST variants it's 257. Let's use DIV_ROUND_UP() for both cases so we can see clearly what's going on here. [Use DIV_ROUND_UP to clarify elder code] Signed-off-by: Ulf Hansson Reviewed-by: Sebastian Rasmussen Signed-off-by: Linus Walleij Signed-off-by: Russell King --- drivers/mmc/host/mmci.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 7721de942c69..c471cdb1a0ba 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1061,7 +1061,15 @@ static int __devinit mmci_probe(struct amba_device *dev, } mmc->ops = &mmci_ops; - mmc->f_min = (host->mclk + 511) / 512; + /* + * The ARM and ST versions of the block have slightly different + * clock divider equations which means that the minimum divider + * differs too. + */ + if (variant->st_clkdiv) + mmc->f_min = DIV_ROUND_UP(host->mclk, 257); + else + mmc->f_min = DIV_ROUND_UP(host->mclk, 512); /* * If the platform data supplies a maximum operating * frequency, this takes precedence. Else, we fall back -- cgit v1.2.3 From 2ef75701d1711a1feee2a82b42a2597ddc05f88b Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 21 Jul 2011 14:51:13 +0100 Subject: ARM: CPU hotplug: fix abuse of irqdesc->node irqdesc's node member is supposed to mark the numa node number for the interrupt. Our use of it is non-standard. Remove this, replacing the functionality with a test of the affinity mask. Signed-off-by: Russell King --- arch/arm/common/gic.c | 1 - arch/arm/kernel/irq.c | 10 ++-------- 2 files changed, 2 insertions(+), 9 deletions(-) diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 4ddd0a6ac7ff..635d9857b07a 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -189,7 +189,6 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bit = 1 << (cpu + shift); spin_lock(&irq_controller_lock); - d->node = cpu; val = readl_relaxed(reg) & ~mask; writel_relaxed(val | bit, reg); spin_unlock(&irq_controller_lock); diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 83bbad03fcc6..d7aa5c97877c 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -166,15 +166,9 @@ void migrate_irqs(void) bool affinity_broken = false; raw_spin_lock(&desc->lock); - do { - if (desc->action == NULL) - break; - - if (d->node != cpu) - break; - + if (desc->action != NULL && + cpumask_test_cpu(smp_processor_id(), d->affinity)) affinity_broken = migrate_one_irq(d); - } while (0); raw_spin_unlock(&desc->lock); if (affinity_broken && printk_ratelimit()) -- cgit v1.2.3 From 5dfc54e087c15f823ee9b6541d2f0f314e69cbed Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 21 Jul 2011 15:00:57 +0100 Subject: ARM: GIC: avoid routing interrupts to offline CPUs The irq_set_affinity() method can be called with masks which include offline CPUs. This allows offline CPUs to have interrupts routed to them by writing to /proc/irq/*/smp_affinity after hotplug has taken a CPU offline. Fix this by ensuring that we select a target CPU present in both the required affinity and the online CPU mask. Ensure that we return IRQ_SET_MASK_OK (which happens to be 0) on success to ensure generic code copies the new mask into the irq_data structure. Signed-off-by: Russell King --- arch/arm/common/gic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 635d9857b07a..7bdd91766d65 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -179,10 +179,10 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, { void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3); unsigned int shift = (d->irq % 4) * 8; - unsigned int cpu = cpumask_first(mask_val); + unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask); u32 val, mask, bit; - if (cpu >= 8) + if (cpu >= 8 || cpu >= nr_cpu_ids) return -EINVAL; mask = 0xff << shift; @@ -193,7 +193,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, writel_relaxed(val | bit, reg); spin_unlock(&irq_controller_lock); - return 0; + return IRQ_SET_MASK_OK; } #endif -- cgit v1.2.3 From ca15af19ac07908c8ca386f6d944a18aa343b868 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 21 Jul 2011 15:07:56 +0100 Subject: ARM: CPU hotplug: pass in proper affinity mask on IRQ migration Now that the GIC takes care of selecting a target interrupt from the affinity mask, we don't need all this complexity in the core code anymore. Just detect when we need to break affinity. Signed-off-by: Russell King --- arch/arm/kernel/irq.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index d7aa5c97877c..ab63c05290e5 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -133,17 +133,15 @@ int __init arch_probe_nr_irqs(void) static bool migrate_one_irq(struct irq_data *d) { - unsigned int cpu = cpumask_any_and(d->affinity, cpu_online_mask); + const struct cpumask *affinity = d->affinity; bool ret = false; - if (cpu >= nr_cpu_ids) { - cpu = cpumask_any(cpu_online_mask); + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + affinity cpu_online_mask; ret = true; } - pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", d->irq, d->node, cpu); - - d->chip->irq_set_affinity(d, cpumask_of(cpu), true); + d->chip->irq_set_affinity(d, affinity, true); return ret; } -- cgit v1.2.3 From 78359cb86b8c4c8946f6732eac2757fa5e1d4de4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 21 Jul 2011 15:14:21 +0100 Subject: ARM: CPU hotplug: ensure we migrate all IRQs off a downed CPU Our selection of interrupts to consider for IRQ migration is sub- standard. We were potentially including per-CPU interrupts in our migration strategy, but omitting chained interrupts. This caused some interrupts to remain on a downed CPU. We were also trying to migrate interrupts which were not migratable, resulting in an OOPS. Instead, iterate over all interrupts, skipping per-CPU interrupts or interrupts whose affinity does not include the downed CPU, and attempt to set the affinity for every one else if their chip implements irq_set_affinity(). Signed-off-by: Russell King --- arch/arm/kernel/irq.c | 39 ++++++++++++++++++++++++++++----------- 1 file changed, 28 insertions(+), 11 deletions(-) diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index ab63c05290e5..0f928a131af8 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -131,46 +131,63 @@ int __init arch_probe_nr_irqs(void) #ifdef CONFIG_HOTPLUG_CPU -static bool migrate_one_irq(struct irq_data *d) +static bool migrate_one_irq(struct irq_desc *desc) { + struct irq_data *d = irq_desc_get_irq_data(desc); const struct cpumask *affinity = d->affinity; + struct irq_chip *c; bool ret = false; + /* + * If this is a per-CPU interrupt, or the affinity does not + * include this CPU, then we have nothing to do. + */ + if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) + return false; + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - affinity cpu_online_mask; + affinity = cpu_online_mask; ret = true; } - d->chip->irq_set_affinity(d, affinity, true); + c = irq_data_get_irq_chip(d); + if (c->irq_set_affinity) + c->irq_set_affinity(d, affinity, true); + else + pr_debug("IRQ%u: unable to set affinity\n", d->irq); return ret; } /* - * The CPU has been marked offline. Migrate IRQs off this CPU. If - * the affinity settings do not allow other CPUs, force them onto any + * The current CPU has been marked offline. Migrate IRQs off this CPU. + * If the affinity settings do not allow other CPUs, force them onto any * available CPU. + * + * Note: we must iterate over all IRQs, whether they have an attached + * action structure or not, as we need to get chained interrupts too. */ void migrate_irqs(void) { - unsigned int i, cpu = smp_processor_id(); + unsigned int i; struct irq_desc *desc; unsigned long flags; local_irq_save(flags); for_each_irq_desc(i, desc) { - struct irq_data *d = &desc->irq_data; bool affinity_broken = false; + if (!desc) + continue; + raw_spin_lock(&desc->lock); - if (desc->action != NULL && - cpumask_test_cpu(smp_processor_id(), d->affinity)) - affinity_broken = migrate_one_irq(d); + affinity_broken = migrate_one_irq(desc); raw_spin_unlock(&desc->lock); if (affinity_broken && printk_ratelimit()) - pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu); + pr_warning("IRQ%u no longer affine to CPU%u\n", i, + smp_processor_id()); } local_irq_restore(flags); -- cgit v1.2.3 From 6645cb61f3a1186a71475385d33f875dd8fb38bf Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 21 Jul 2011 14:42:40 +0100 Subject: ARM: Fix build errors caused by adding generic macros Commit 66a625a (ARM: mm: proc-macros: Add generic proc/cache/tlb struct definition macros) introduced build errors when PM_SLEEP is not enabled. The per-CPU do_suspend/do_resume functions are defined via the preprocessor to constant 0. However, the macros which use these were converted to assembly, resulting in undefined references to these functions. Fix that by moving the ! ifdef section into proc-macros.S and deleting it from all effected proc-*.S files. Acked-by: Dave Martin Signed-off-by: Russell King --- arch/arm/mm/proc-arm920.S | 3 --- arch/arm/mm/proc-arm926.S | 3 --- arch/arm/mm/proc-macros.S | 5 +++++ arch/arm/mm/proc-sa1100.S | 3 --- arch/arm/mm/proc-v6.S | 3 --- arch/arm/mm/proc-v7.S | 3 --- arch/arm/mm/proc-xsc3.S | 3 --- arch/arm/mm/proc-xscale.S | 3 --- 8 files changed, 5 insertions(+), 21 deletions(-) diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 0dea376feaaa..92bd102e3982 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -406,9 +406,6 @@ ENTRY(cpu_arm920_do_resume) PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE b cpu_resume_mmu ENDPROC(cpu_arm920_do_resume) -#else -#define cpu_arm920_do_suspend 0 -#define cpu_arm920_do_resume 0 #endif __CPUINIT diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index b2f9bde8ecef..2bbcf053dffd 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -421,9 +421,6 @@ ENTRY(cpu_arm926_do_resume) PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE b cpu_resume_mmu ENDPROC(cpu_arm926_do_resume) -#else -#define cpu_arm926_do_suspend 0 -#define cpu_arm926_do_resume 0 #endif __CPUINIT diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 4ae9b4407074..307a4def8d3a 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -276,8 +276,13 @@ ENTRY(\name\()_processor_functions) .if \suspend .word cpu_\name\()_suspend_size +#ifdef CONFIG_PM_SLEEP .word cpu_\name\()_do_suspend .word cpu_\name\()_do_resume +#else + .word 0 + .word 0 +#endif .else .word 0 .word 0 diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index c7e08cab55a8..e71587852cae 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -200,9 +200,6 @@ ENTRY(cpu_sa1100_do_resume) PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE b cpu_resume_mmu ENDPROC(cpu_sa1100_do_resume) -#else -#define cpu_sa1100_do_suspend 0 -#define cpu_sa1100_do_resume 0 #endif __CPUINIT diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index aedf3c5dbe4e..219138d2f158 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -169,9 +169,6 @@ ENDPROC(cpu_v6_do_resume) cpu_resume_l1_flags: ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP) ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP) -#else -#define cpu_v6_do_suspend 0 -#define cpu_v6_do_resume 0 #endif string cpu_v6_name, "ARMv6-compatible processor" diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 54d1a63517c5..a30e78542ccf 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -263,9 +263,6 @@ ENDPROC(cpu_v7_do_resume) cpu_resume_l1_flags: ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP) ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP) -#else -#define cpu_v7_do_suspend 0 -#define cpu_v7_do_resume 0 #endif __CPUINIT diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 1508f9bc526a..64f1fc7edf0a 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -445,9 +445,6 @@ ENTRY(cpu_xsc3_do_resume) ldr r3, =0x542e @ section flags b cpu_resume_mmu ENDPROC(cpu_xsc3_do_resume) -#else -#define cpu_xsc3_do_suspend 0 -#define cpu_xsc3_do_resume 0 #endif __CPUINIT diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 76a804605010..fbc06e55b87a 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -554,9 +554,6 @@ ENTRY(cpu_xscale_do_resume) PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE b cpu_resume_mmu ENDPROC(cpu_xscale_do_resume) -#else -#define cpu_xscale_do_suspend 0 -#define cpu_xscale_do_resume 0 #endif __CPUINIT -- cgit v1.2.3 From 24daa15aabaf9ef655f7ca868366c8a4c87397f3 Mon Sep 17 00:00:00 2001 From: Petr Štetiar Date: Sat, 9 Jul 2011 14:18:36 +0100 Subject: ARM: 6997/1: ep93xx: increase NR_BANKS to 16 for support of 128MB RAM I've got hands on one ts-7300 board, which is equiped with 128MB RAM in two 64MB memory chips, so it's 16 banks/8MB each. Without this patch, the bootmem init code complains about small NR_BANKS number and only lower 64MB is accessible. Cc: Ryan Mallon Acked-by: H Hartley Sweeten Signed-off-by: Petr Štetiar Signed-off-by: Russell King --- arch/arm/include/asm/setup.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index ee2ad8ae07af..b13720d2c98a 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -192,7 +192,11 @@ static struct tagtable __tagtable_##fn __tag = { tag, fn } /* * Memory map description */ -#define NR_BANKS 8 +#ifdef CONFIG_ARCH_EP93XX +# define NR_BANKS 16 +#else +# define NR_BANKS 8 +#endif struct membank { phys_addr_t start; -- cgit v1.2.3 From 4cde7e0dca98e0e93dceb174d83f766d0d637c23 Mon Sep 17 00:00:00 2001 From: Heechul Yun Date: Tue, 19 Jul 2011 13:26:54 +0100 Subject: ARM: 6998/2: kernel: use proper memory barriers for bitops Improve scalability by avoiding costly and unnecessary L2 cache sync in handling bitops. Signed-off-by: Heechul Yun Acked-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/bitops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index b4892a06442c..f4280593dfa3 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -26,8 +26,8 @@ #include #include -#define smp_mb__before_clear_bit() mb() -#define smp_mb__after_clear_bit() mb() +#define smp_mb__before_clear_bit() smp_mb() +#define smp_mb__after_clear_bit() smp_mb() /* * These functions are the basis of our bit ops. -- cgit v1.2.3 From e7d59db91a346f5069692e3b1f4e0afd100096dc Mon Sep 17 00:00:00 2001 From: Mikael Pettersson Date: Fri, 22 Jul 2011 16:47:26 +0100 Subject: ARM: 7004/1: fix traps.h compile warnings Building kernel 3.0 for an n2100 (plat-iop) results in: In file included from arch/arm/plat-iop/cp6.c:20: /tmp/linux-3.0/arch/arm/include/asm/traps.h:12: warning: 'struct pt_regs' declared inside parameter list /tmp/linux-3.0/arch/arm/include/asm/traps.h:12: warning: its scope is only this definition or declaration, which is probably not what you want /tmp/linux-3.0/arch/arm/include/asm/traps.h:48: warning: 'struct pt_regs' declared inside parameter list /tmp/linux-3.0/arch/arm/include/asm/traps.h:48: warning: 'struct task_struct' declared inside parameter list arch/arm/plat-iop/cp6.c:45: warning: initialization from incompatible pointer type Nothing here depends on the layout of pt_regs or task_struct, so this can be fixed by adding forward struct declarations to asm/traps.h. Signed-off-by: Mikael Pettersson Signed-off-by: Russell King --- arch/arm/include/asm/traps.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h index f90756dc16dc..5b29a6673625 100644 --- a/arch/arm/include/asm/traps.h +++ b/arch/arm/include/asm/traps.h @@ -3,6 +3,9 @@ #include +struct pt_regs; +struct task_struct; + struct undef_hook { struct list_head node; u32 instr_mask; -- cgit v1.2.3