From a5d5f7daa744b34477c4a12728bde0a1694a1707 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Thu, 12 Jul 2012 23:57:35 +0100 Subject: ARM: 7465/1: Handle >4GB memory sizes in device tree and mem=size@start option The memory regions which are passed to arm_add_memory() from device tree blobs via early_init_dt_add_memory_arch() can have sizes which are larger than will fit in a 32 bit integer, so switch to using a phys_addr_t to hold them, to avoid silently dropping the top 32 bits of the size. Similarly, use phys_addr_t in early_mem() so that mem=size@start command line options specifying more than 4GB behave sensibly. Acked-by: Will Deacon Signed-off-by: Peter Maydell Signed-off-by: Russell King --- arch/arm/include/asm/setup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index 23ebc0c82a3..24d284a1bfc 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -196,7 +196,7 @@ static const struct tagtable __tagtable_##fn __tag = { tag, fn } struct membank { phys_addr_t start; - unsigned long size; + phys_addr_t size; unsigned int highmem; }; @@ -217,7 +217,7 @@ extern struct meminfo meminfo; #define bank_phys_end(bank) ((bank)->start + (bank)->size) #define bank_phys_size(bank) (bank)->size -extern int arm_add_memory(phys_addr_t start, unsigned long size); +extern int arm_add_memory(phys_addr_t start, phys_addr_t size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); -- cgit v1.2.3-70-g09d2 From a76d7bd96d65fa5119adba97e1b58d95f2e78829 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 13 Jul 2012 19:15:40 +0100 Subject: ARM: 7467/1: mutex: use generic xchg-based implementation for ARMv6+ The open-coded mutex implementation for ARMv6+ cores suffers from a severe lack of barriers, so in the uncontended case we don't actually protect any accesses performed during the critical section. Furthermore, the code is largely a duplication of the ARMv6+ atomic_dec code but optimised to remove a branch instruction, as the mutex fastpath was previously inlined. Now that this is executed out-of-line, we can reuse the atomic access code for the locking (in fact, we use the xchg code as this produces shorter critical sections). This patch uses the generic xchg based implementation for mutexes on ARMv6+, which introduces barriers to the lock/unlock operations and also has the benefit of removing a fair amount of inline assembly code. Cc: Acked-by: Arnd Bergmann Acked-by: Nicolas Pitre Reported-by: Shan Kang Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/mutex.h | 119 ++----------------------------------------- 1 file changed, 4 insertions(+), 115 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h index 93226cf23ae..b1479fd04a9 100644 --- a/arch/arm/include/asm/mutex.h +++ b/arch/arm/include/asm/mutex.h @@ -7,121 +7,10 @@ */ #ifndef _ASM_MUTEX_H #define _ASM_MUTEX_H - -#if __LINUX_ARM_ARCH__ < 6 -/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */ -# include -#else - /* - * Attempting to lock a mutex on ARMv6+ can be done with a bastardized - * atomic decrement (it is not a reliable atomic decrement but it satisfies - * the defined semantics for our purpose, while being smaller and faster - * than a real atomic decrement or atomic swap. The idea is to attempt - * decrementing the lock value only once. If once decremented it isn't zero, - * or if its store-back fails due to a dispute on the exclusive store, we - * simply bail out immediately through the slow path where the lock will be - * reattempted until it succeeds. + * On pre-ARMv6 hardware this results in a swp-based implementation, + * which is the most efficient. For ARMv6+, we emit a pair of exclusive + * accesses instead. */ -static inline void -__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res; - - __asm__ ( - - "ldrex %0, [%2] \n\t" - "sub %0, %0, #1 \n\t" - "strex %1, %0, [%2] " - - : "=&r" (__res), "=&r" (__ex_flag) - : "r" (&(count)->counter) - : "cc","memory" ); - - __res |= __ex_flag; - if (unlikely(__res != 0)) - fail_fn(count); -} - -static inline int -__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res; - - __asm__ ( - - "ldrex %0, [%2] \n\t" - "sub %0, %0, #1 \n\t" - "strex %1, %0, [%2] " - - : "=&r" (__res), "=&r" (__ex_flag) - : "r" (&(count)->counter) - : "cc","memory" ); - - __res |= __ex_flag; - if (unlikely(__res != 0)) - __res = fail_fn(count); - return __res; -} - -/* - * Same trick is used for the unlock fast path. However the original value, - * rather than the result, is used to test for success in order to have - * better generated assembly. - */ -static inline void -__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res, __orig; - - __asm__ ( - - "ldrex %0, [%3] \n\t" - "add %1, %0, #1 \n\t" - "strex %2, %1, [%3] " - - : "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag) - : "r" (&(count)->counter) - : "cc","memory" ); - - __orig |= __ex_flag; - if (unlikely(__orig != 0)) - fail_fn(count); -} - -/* - * If the unlock was done on a contended lock, or if the unlock simply fails - * then the mutex remains locked. - */ -#define __mutex_slowpath_needs_to_unlock() 1 - -/* - * For __mutex_fastpath_trylock we use another construct which could be - * described as a "single value cmpxchg". - * - * This provides the needed trylock semantics like cmpxchg would, but it is - * lighter and less generic than a true cmpxchg implementation. - */ -static inline int -__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) -{ - int __ex_flag, __res, __orig; - - __asm__ ( - - "1: ldrex %0, [%3] \n\t" - "subs %1, %0, #1 \n\t" - "strexeq %2, %1, [%3] \n\t" - "movlt %0, #0 \n\t" - "cmpeq %2, #0 \n\t" - "bgt 1b " - - : "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag) - : "r" (&count->counter) - : "cc", "memory" ); - - return __orig; -} - -#endif +#include #endif -- cgit v1.2.3-70-g09d2 From b74253f78400f9a4b42da84bb1de7540b88ce7c4 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 23 Jul 2012 14:18:13 +0100 Subject: ARM: 7479/1: mm: avoid NULL dereference when flushing gate_vma with VIVT caches The vivt_flush_cache_{range,page} functions check that the mm_struct of the VMA being flushed has been active on the current CPU before performing the cache maintenance. The gate_vma has a NULL mm_struct pointer and, as such, will cause a kernel fault if we try to flush it with the above operations. This happens during ELF core dumps, which include the gate_vma as it may be useful for debugging purposes. This patch adds checks to the VIVT cache flushing functions so that VMAs with a NULL mm_struct are flushed unconditionally (the vectors page may be dirty if we use it to store the current TLS pointer). Cc: # 3.4+ Reported-by: Gilles Chanteperdrix Tested-by: Uros Bizjak Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/cacheflush.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 004c1bc95d2..e4448e16046 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -215,7 +215,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm) static inline void vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) __cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end), vma->vm_flags); } @@ -223,7 +225,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned static inline void vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { unsigned long addr = user_addr & PAGE_MASK; __cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags); } -- cgit v1.2.3-70-g09d2