From 71a8986d7e4845b6fca1298fe6e3233ce6fde0b7 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Thu, 18 Jul 2013 16:50:59 -0400 Subject: ARM: suspend: use hash of cpu_logical_map value to index into save array Currently we hash the MPIDR of the CPU being suspended to determine which entry in the sleep_save_sp array to use. In some situations, such as when we want to resume on another physical CPU, the MPIDR of another CPU should be used instead. So let's use the value of cpu_logical_map(smp_processor_id()) in place of the MPIDR in the suspend path. This will result in the same index being used as with the previous code unless the caller has modified cpu_logical_map() beforehand with the MPIDR of the physical CPU the suspending logical CPU will resume on. Consequently, if doing a physical CPU migration, cpu_logical_map() must be updated appropriately somewhere between cpu_pm_enter() and cpu_suspend(). The register allocation in __cpu_suspend is reworked in order to better accommodate the additional argument. Signed-off-by: Nicolas Pitre Acked-by: Lorenzo Pieralisi Reviewed-by: Dave Martin --- arch/arm/kernel/sleep.S | 26 +++++++++++--------------- arch/arm/kernel/suspend.c | 8 +++++--- 2 files changed, 16 insertions(+), 18 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index db1536b8b30b..622460201911 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -55,6 +55,7 @@ * specific registers and some other data for resume. * r0 = suspend function arg0 * r1 = suspend function + * r2 = MPIDR value the resuming CPU will use */ ENTRY(__cpu_suspend) stmfd sp!, {r4 - r11, lr} @@ -67,23 +68,18 @@ ENTRY(__cpu_suspend) mov r5, sp @ current virtual SP add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn sub sp, sp, r4 @ allocate CPU state on stack - stmfd sp!, {r0, r1} @ save suspend func arg and pointer - add r0, sp, #8 @ save pointer to save block - mov r1, r4 @ size of save block - mov r2, r5 @ virtual SP ldr r3, =sleep_save_sp + stmfd sp!, {r0, r1} @ save suspend func arg and pointer ldr r3, [r3, #SLEEP_SAVE_SP_VIRT] - ALT_SMP(mrc p15, 0, r9, c0, c0, 5) - ALT_UP_B(1f) - ldr r8, =mpidr_hash - /* - * This ldmia relies on the memory layout of the mpidr_hash - * struct mpidr_hash. - */ - ldmia r8, {r4-r7} @ r4 = mpidr mask (r5,r6,r7) = l[0,1,2] shifts - compute_mpidr_hash lr, r5, r6, r7, r9, r4 - add r3, r3, lr, lsl #2 -1: + ALT_SMP(ldr r0, =mpidr_hash) + ALT_UP_B(1f) + /* This ldmia relies on the memory layout of the mpidr_hash struct */ + ldmia r0, {r1, r6-r8} @ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts + compute_mpidr_hash r0, r6, r7, r8, r2, r1 + add r3, r3, r0, lsl #2 +1: mov r2, r5 @ virtual SP + mov r1, r4 @ size of save block + add r0, sp, #8 @ pointer to save block bl __cpu_suspend_save adr lr, BSYM(cpu_suspend_abort) ldmfd sp!, {r0, pc} @ call suspend fn diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c index 41cf3cbf756d..2835d35234ca 100644 --- a/arch/arm/kernel/suspend.c +++ b/arch/arm/kernel/suspend.c @@ -10,7 +10,7 @@ #include #include -extern int __cpu_suspend(unsigned long, int (*)(unsigned long)); +extern int __cpu_suspend(unsigned long, int (*)(unsigned long), u32 cpuid); extern void cpu_resume_mmu(void); #ifdef CONFIG_MMU @@ -21,6 +21,7 @@ extern void cpu_resume_mmu(void); int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { struct mm_struct *mm = current->active_mm; + u32 __mpidr = cpu_logical_map(smp_processor_id()); int ret; if (!idmap_pgd) @@ -32,7 +33,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) * resume (indicated by a zero return code), we need to switch * back to the correct page tables. */ - ret = __cpu_suspend(arg, fn); + ret = __cpu_suspend(arg, fn, __mpidr); if (ret == 0) { cpu_switch_mm(mm->pgd, mm); local_flush_bp_all(); @@ -44,7 +45,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) #else int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { - return __cpu_suspend(arg, fn); + u32 __mpidr = cpu_logical_map(smp_processor_id()); + return __cpu_suspend(arg, fn, __mpidr); } #define idmap_pgd NULL #endif -- cgit v1.2.3 From 5135d875e1457ef946a055003d8f80713e862135 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 27 Nov 2012 21:54:41 -0500 Subject: ARM: SMP: basic IPI triggered completion support We need a mechanism to let an inbound CPU signal that it is alive before even getting into the kernel environment i.e. from early assembly code. Using an IPI is the simplest way to achieve that. This adds some basic infrastructure to register a struct completion pointer to be "completed" when the dedicated IPI for this task is received. Signed-off-by: Nicolas Pitre --- arch/arm/include/asm/hardirq.h | 2 +- arch/arm/include/asm/smp.h | 2 ++ arch/arm/kernel/smp.c | 21 +++++++++++++++++++++ 3 files changed, 24 insertions(+), 1 deletion(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index 2740c2a2df63..3d7351c844aa 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -5,7 +5,7 @@ #include #include -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index a8cae71caceb..22a3b9b5d4a1 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -84,6 +84,8 @@ extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask); +extern int register_ipi_completion(struct completion *completion, int cpu); + struct smp_operations { #ifdef CONFIG_SMP /* diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 72024ea8a3a6..7d80a549cae5 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -66,6 +66,7 @@ enum ipi_msg_type { IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_COMPLETION, }; static DECLARE_COMPLETION(cpu_running); @@ -456,6 +457,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_COMPLETION, "completion interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -515,6 +517,19 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +static DEFINE_PER_CPU(struct completion *, cpu_completion); + +int register_ipi_completion(struct completion *completion, int cpu) +{ + per_cpu(cpu_completion, cpu) = completion; + return IPI_COMPLETION; +} + +static void ipi_complete(unsigned int cpu) +{ + complete(per_cpu(cpu_completion, cpu)); +} + /* * Main handler for inter-processor interrupts */ @@ -565,6 +580,12 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_COMPLETION: + irq_enter(); + ipi_complete(cpu); + irq_exit(); + break; + default: printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); -- cgit v1.2.3 From 49863894db3ed7bd41541b1c17733273966cea71 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 26 Sep 2013 12:36:35 +0100 Subject: ARM: perf: add support for perf registers API This patch implements the functions required for the perf registers API, allowing the perf tool to interface kernel register dumps with libunwind in order to provide userspace backtracing. Cc: Jean Pihet Signed-off-by: Will Deacon --- arch/arm/Kconfig | 2 ++ arch/arm/include/uapi/asm/Kbuild | 1 + arch/arm/include/uapi/asm/perf_regs.h | 23 +++++++++++++++++++++++ arch/arm/kernel/Makefile | 1 + arch/arm/kernel/perf_regs.c | 30 ++++++++++++++++++++++++++++++ 5 files changed, 57 insertions(+) create mode 100644 arch/arm/include/uapi/asm/perf_regs.h create mode 100644 arch/arm/kernel/perf_regs.c (limited to 'arch/arm/kernel') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 1ad6fb6c094d..899d0c6ec2c5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -51,6 +51,8 @@ config ARM select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND select HAVE_OPROFILE if (HAVE_PERF_EVENTS) select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 18d76fd5a2af..70a1c9da30ca 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ header-y += hwcap.h header-y += ioctls.h header-y += kvm_para.h header-y += mman.h +header-y += perf_regs.h header-y += posix_types.h header-y += ptrace.h header-y += setup.h diff --git a/arch/arm/include/uapi/asm/perf_regs.h b/arch/arm/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..ce59448458b2 --- /dev/null +++ b/arch/arm/include/uapi/asm/perf_regs.h @@ -0,0 +1,23 @@ +#ifndef _ASM_ARM_PERF_REGS_H +#define _ASM_ARM_PERF_REGS_H + +enum perf_event_arm_regs { + PERF_REG_ARM_R0, + PERF_REG_ARM_R1, + PERF_REG_ARM_R2, + PERF_REG_ARM_R3, + PERF_REG_ARM_R4, + PERF_REG_ARM_R5, + PERF_REG_ARM_R6, + PERF_REG_ARM_R7, + PERF_REG_ARM_R8, + PERF_REG_ARM_R9, + PERF_REG_ARM_R10, + PERF_REG_ARM_FP, + PERF_REG_ARM_IP, + PERF_REG_ARM_SP, + PERF_REG_ARM_LR, + PERF_REG_ARM_PC, + PERF_REG_ARM_MAX, +}; +#endif /* _ASM_ARM_PERF_REGS_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 5140df5f23aa..9b818ca3610b 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -78,6 +78,7 @@ obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o perf_event_cpu.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c new file mode 100644 index 000000000000..6e4379c67cbc --- /dev/null +++ b/arch/arm/kernel/perf_regs.c @@ -0,0 +1,30 @@ + +#include +#include +#include +#include +#include +#include + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM_MAX)) + return 0; + + return regs->uregs[idx]; +} + +#define REG_RESERVED (~((1ULL << PERF_REG_ARM_MAX) - 1)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} -- cgit v1.2.3 From 2dfcb802d6bd54a2353678c6434846d94b058f2c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 9 Oct 2013 13:51:29 +0100 Subject: ARM: perf: fix group validation for mixed software and hardware groups Since software events can always be scheduled, perf allows software and hardware events to be mixed together in the same event group. There are two ways in which this can come about: (1) A SW event is added to a HW group. This validates using the HW PMU of the group leader. (2) A HW event is added to a SW group. This inserts the SW events and the new HW event into a HW context, but the SW event remains the group leader. When validating the latter case, we would ideally compare the PMU of each event in the group with the relevant HW PMU. The problem is, in the face of potentially multiple HW PMUs, we don't have a handle on the relevant structure. Commit 7b9f72c62ed0 ("ARM: perf: clean up event group validation") attempting to resolve this issue, but actually made things *worse* by comparing with the leader PMU. If the leader is a SW event, then we automatically `pass' all the HW events during validation! This patch removes the check against the leader PMU. Whilst this will allow events from multiple HW PMUs to be grouped together, that should probably be dealt with in perf core as the result of a later patch. Acked-by: Mark Rutland Signed-off-by: Will Deacon --- arch/arm/kernel/perf_event.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index e186ee1e63f6..bc3f2efa0d86 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -256,12 +256,11 @@ validate_event(struct pmu_hw_events *hw_events, struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct pmu *leader_pmu = event->group_leader->pmu; if (is_software_event(event)) return 1; - if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + if (event->state < PERF_EVENT_STATE_OFF) return 1; if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) -- cgit v1.2.3 From 4dc9a81715973cb137a14399420bb35b0ed7d6ef Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 31 Jul 2013 12:44:42 -0400 Subject: ARM: mm: Introduce virt_to_idmap() with an arch hook On some PAE systems (e.g. TI Keystone), memory is above the 32-bit addressable limit, and the interconnect provides an aliased view of parts of physical memory in the 32-bit addressable space. This alias is strictly for boot time usage, and is not otherwise usable because of coherency limitations. On such systems, the idmap mechanism needs to take this aliased mapping into account. This patch introduces virt_to_idmap() and a arch function pointer which can be populated by platform which needs it. Also populate necessary idmap spots with now available virt_to_idmap(). Avoided #ifdef approach to be compatible with multi-platform builds. Most architecture won't touch it and in that case virt_to_idmap() fall-back to existing virt_to_phys() macro. Cc: Russell King Acked-by: Nicolas Pitre Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/memory.h | 16 ++++++++++++++++ arch/arm/kernel/smp.c | 2 +- arch/arm/mm/idmap.c | 5 +++-- 3 files changed, 20 insertions(+), 3 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index c133bd915f48..d9b96c65e594 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -173,6 +173,7 @@ */ #define __PV_BITS_31_24 0x81000000 +extern phys_addr_t (*arch_virt_to_idmap) (unsigned long x); extern unsigned long __pv_phys_offset; #define PHYS_OFFSET __pv_phys_offset @@ -258,6 +259,21 @@ static inline void *phys_to_virt(phys_addr_t x) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) +/* + * These are for systems that have a hardware interconnect supported alias of + * physical memory for idmap purposes. Most cases should leave these + * untouched. + */ +static inline phys_addr_t __virt_to_idmap(unsigned long x) +{ + if (arch_virt_to_idmap) + return arch_virt_to_idmap(x); + else + return __virt_to_phys(x); +} + +#define virt_to_idmap(x) __virt_to_idmap((unsigned long)(x)) + /* * Virtual <-> DMA view memory address translations * Again, these are *only* valid on the kernel direct mapped RAM diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 72024ea8a3a6..a0eb830c3daf 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -80,7 +80,7 @@ void __init smp_set_ops(struct smp_operations *ops) static unsigned long get_arch_pgd(pgd_t *pgd) { - phys_addr_t pgdir = virt_to_phys(pgd); + phys_addr_t pgdir = virt_to_idmap(pgd); BUG_ON(pgdir & ARCH_PGD_MASK); return pgdir >> ARCH_PGD_SHIFT; } diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 83cb3ac27095..c0a1e48f6733 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -10,6 +10,7 @@ #include pgd_t *idmap_pgd; +phys_addr_t (*arch_virt_to_idmap) (unsigned long x); #ifdef CONFIG_ARM_LPAE static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, @@ -67,8 +68,8 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start, unsigned long addr, end; unsigned long next; - addr = virt_to_phys(text_start); - end = virt_to_phys(text_end); + addr = virt_to_idmap(text_start); + end = virt_to_idmap(text_end); prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; -- cgit v1.2.3 From f52bb722547f43caeaecbcc62db9f3c3b80ead9b Mon Sep 17 00:00:00 2001 From: Sricharan R Date: Mon, 29 Jul 2013 20:26:22 +0530 Subject: ARM: mm: Correct virt_to_phys patching for 64 bit physical addresses The current phys_to_virt patching mechanism works only for 32 bit physical addresses and this patch extends the idea for 64bit physical addresses. The 64bit v2p patching mechanism patches the higher 8 bits of physical address with a constant using 'mov' instruction and lower 32bits are patched using 'add'. While this is correct, in those platforms where the lowmem addressable physical memory spawns across 4GB boundary, a carry bit can be produced as a result of addition of lower 32bits. This has to be taken in to account and added in to the upper. The patched __pv_offset and va are added in lower 32bits, where __pv_offset can be in two's complement form when PA_START < VA_START and that can result in a false carry bit. e.g 1) PA = 0x80000000; VA = 0xC0000000 __pv_offset = PA - VA = 0xC0000000 (2's complement) 2) PA = 0x2 80000000; VA = 0xC000000 __pv_offset = PA - VA = 0x1 C0000000 So adding __pv_offset + VA should never result in a true overflow for (1). So in order to differentiate between a true carry, a __pv_offset is extended to 64bit and the upper 32bits will have 0xffffffff if __pv_offset is 2's complement. So 'mvn #0' is inserted instead of 'mov' while patching for the same reason. Since mov, add, sub instruction are to patched with different constants inside the same stub, the rotation field of the opcode is using to differentiate between them. So the above examples for v2p translation becomes for VA=0xC0000000, 1) PA[63:32] = 0xffffffff PA[31:0] = VA + 0xC0000000 --> results in a carry PA[63:32] = PA[63:32] + carry PA[63:0] = 0x0 80000000 2) PA[63:32] = 0x1 PA[31:0] = VA + 0xC0000000 --> results in a carry PA[63:32] = PA[63:32] + carry PA[63:0] = 0x2 80000000 The above ideas were suggested by Nicolas Pitre as part of the review of first and second versions of the subject patch. There is no corresponding change on the phys_to_virt() side, because computations on the upper 32-bits would be discarded anyway. Cc: Russell King Reviewed-by: Nicolas Pitre Signed-off-by: Sricharan R Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/memory.h | 37 ++++++++++++++++++++++--- arch/arm/kernel/armksyms.c | 1 + arch/arm/kernel/head.S | 63 ++++++++++++++++++++++++++++++++----------- 3 files changed, 82 insertions(+), 19 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index d9b96c65e594..6748d6295a1a 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -172,9 +172,14 @@ * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 +#define __PV_BITS_7_0 0x81 extern phys_addr_t (*arch_virt_to_idmap) (unsigned long x); -extern unsigned long __pv_phys_offset; +extern u64 __pv_phys_offset; +extern u64 __pv_offset; +extern void fixup_pv_table(const void *, unsigned long); +extern const void *__pv_table_begin, *__pv_table_end; + #define PHYS_OFFSET __pv_phys_offset #define __pv_stub(from,to,instr,type) \ @@ -186,10 +191,36 @@ extern unsigned long __pv_phys_offset; : "=r" (to) \ : "r" (from), "I" (type)) +#define __pv_stub_mov_hi(t) \ + __asm__ volatile("@ __pv_stub_mov\n" \ + "1: mov %R0, %1\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "=r" (t) \ + : "I" (__PV_BITS_7_0)) + +#define __pv_add_carry_stub(x, y) \ + __asm__ volatile("@ __pv_add_carry_stub\n" \ + "1: adds %Q0, %1, %2\n" \ + " adc %R0, %R0, #0\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "+r" (y) \ + : "r" (x), "I" (__PV_BITS_31_24) \ + : "cc") + static inline phys_addr_t __virt_to_phys(unsigned long x) { - unsigned long t; - __pv_stub(x, t, "add", __PV_BITS_31_24); + phys_addr_t t; + + if (sizeof(phys_addr_t) == 4) { + __pv_stub(x, t, "add", __PV_BITS_31_24); + } else { + __pv_stub_mov_hi(t); + __pv_add_carry_stub(x, t); + } return t; } diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index 60d3b738d420..1f031ddd0667 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -155,4 +155,5 @@ EXPORT_SYMBOL(__gnu_mcount_nc); #ifdef CONFIG_ARM_PATCH_PHYS_VIRT EXPORT_SYMBOL(__pv_phys_offset); +EXPORT_SYMBOL(__pv_offset); #endif diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 2c7cc1e03473..54547947a4e9 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -536,6 +536,14 @@ ENTRY(fixup_smp) ldmfd sp!, {r4 - r6, pc} ENDPROC(fixup_smp) +#ifdef __ARMEB_ +#define LOW_OFFSET 0x4 +#define HIGH_OFFSET 0x0 +#else +#define LOW_OFFSET 0x0 +#define HIGH_OFFSET 0x4 +#endif + #ifdef CONFIG_ARM_PATCH_PHYS_VIRT /* __fixup_pv_table - patch the stub instructions with the delta between @@ -546,17 +554,20 @@ ENDPROC(fixup_smp) __HEAD __fixup_pv_table: adr r0, 1f - ldmia r0, {r3-r5, r7} - sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET + ldmia r0, {r3-r7} + mvn ip, #0 + subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET add r4, r4, r3 @ adjust table start address add r5, r5, r3 @ adjust table end address - add r7, r7, r3 @ adjust __pv_phys_offset address - str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset + add r6, r6, r3 @ adjust __pv_phys_offset address + add r7, r7, r3 @ adjust __pv_offset address + str r8, [r6, #LOW_OFFSET] @ save computed PHYS_OFFSET to __pv_phys_offset + strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits mov r6, r3, lsr #24 @ constant for add/sub instructions teq r3, r6, lsl #24 @ must be 16MiB aligned THUMB( it ne @ cross section branch ) bne __error - str r6, [r7, #4] @ save to __pv_offset + str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits b __fixup_a_pv_table ENDPROC(__fixup_pv_table) @@ -565,10 +576,19 @@ ENDPROC(__fixup_pv_table) .long __pv_table_begin .long __pv_table_end 2: .long __pv_phys_offset + .long __pv_offset .text __fixup_a_pv_table: + adr r0, 3f + ldr r6, [r0] + add r6, r6, r3 + ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word + ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word + mov r6, r6, lsr #24 + cmn r0, #1 #ifdef CONFIG_THUMB2_KERNEL + moveq r0, #0x200000 @ set bit 21, mov to mvn instruction lsls r6, #24 beq 2f clz r7, r6 @@ -582,18 +602,28 @@ __fixup_a_pv_table: b 2f 1: add r7, r3 ldrh ip, [r7, #2] - and ip, 0x8f00 - orr ip, r6 @ mask in offset bits 31-24 + tst ip, #0x4000 + and ip, #0x8f00 + orrne ip, r6 @ mask in offset bits 31-24 + orreq ip, r0 @ mask in offset bits 7-0 strh ip, [r7, #2] + ldrheq ip, [r7] + biceq ip, #0x20 + orreq ip, ip, r0, lsr #16 + strheq ip, [r7] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot bcc 1b bx lr #else + moveq r0, #0x400000 @ set bit 22, mov to mvn instruction b 2f 1: ldr ip, [r7, r3] bic ip, ip, #0x000000ff - orr ip, ip, r6 @ mask in offset bits 31-24 + tst ip, #0xf00 @ check the rotation field + orrne ip, ip, r6 @ mask in offset bits 31-24 + biceq ip, ip, #0x400000 @ clear bit 22 + orreq ip, ip, r0 @ mask in offset bits 7-0 str ip, [r7, r3] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot @@ -602,28 +632,29 @@ __fixup_a_pv_table: #endif ENDPROC(__fixup_a_pv_table) +3: .long __pv_offset + ENTRY(fixup_pv_table) stmfd sp!, {r4 - r7, lr} - ldr r2, 2f @ get address of __pv_phys_offset mov r3, #0 @ no offset mov r4, r0 @ r0 = table start add r5, r0, r1 @ r1 = table size - ldr r6, [r2, #4] @ get __pv_offset bl __fixup_a_pv_table ldmfd sp!, {r4 - r7, pc} ENDPROC(fixup_pv_table) - .align -2: .long __pv_phys_offset - .data .globl __pv_phys_offset .type __pv_phys_offset, %object __pv_phys_offset: - .long 0 - .size __pv_phys_offset, . - __pv_phys_offset + .quad 0 + .size __pv_phys_offset, . -__pv_phys_offset + + .globl __pv_offset + .type __pv_offset, %object __pv_offset: - .long 0 + .quad 0 + .size __pv_offset, . -__pv_offset #endif #include "head-common.S" -- cgit v1.2.3 From a77e0c7b2774fd52ce6bf25c2c3ffdccb7b110ff Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 31 Jul 2013 12:44:46 -0400 Subject: ARM: mm: Recreate kernel mappings in early_paging_init() This patch adds a step in the init sequence, in order to recreate the kernel code/data page table mappings prior to full paging initialization. This is necessary on LPAE systems that run out of a physical address space outside the 4G limit. On these systems, this implementation provides a machine descriptor hook that allows the PHYS_OFFSET to be overridden in a machine specific fashion. Cc: Russell King Acked-by: Nicolas Pitre Signed-off-by: R Sricharan Signed-off-by: Santosh Shilimkar --- arch/arm/include/asm/mach/arch.h | 1 + arch/arm/kernel/setup.c | 4 ++ arch/arm/mm/mmu.c | 82 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 87 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 402a2bc6aa68..17a3fa2979e8 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -49,6 +49,7 @@ struct machine_desc { bool (*smp_init)(void); void (*fixup)(struct tag *, char **, struct meminfo *); + void (*init_meminfo)(void); void (*reserve)(void);/* reserve mem blocks */ void (*map_io)(void);/* IO mapping function */ void (*init_early)(void); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 0e1e2b3afa45..af7b7db4699e 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -73,6 +73,8 @@ __setup("fpe=", fpe_setup); #endif extern void paging_init(const struct machine_desc *desc); +extern void early_paging_init(const struct machine_desc *, + struct proc_info_list *); extern void sanity_check_meminfo(void); extern enum reboot_mode reboot_mode; extern void setup_dma_zone(const struct machine_desc *desc); @@ -878,6 +880,8 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); + + early_paging_init(mdesc, lookup_processor_type(read_cpuid_id())); sanity_check_meminfo(); arm_memblock_init(&meminfo, mdesc); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index b1d17eeb59b8..78eeeca78f5a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -28,6 +28,8 @@ #include #include #include +#include +#include #include #include @@ -1315,6 +1317,86 @@ static void __init map_lowmem(void) } } +#ifdef CONFIG_ARM_LPAE +/* + * early_paging_init() recreates boot time page table setup, allowing machines + * to switch over to a high (>4G) address space on LPAE systems + */ +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags; + unsigned long map_start, map_end; + pgd_t *pgd0, *pgdk; + pud_t *pud0, *pudk, *pud_start; + pmd_t *pmd0, *pmdk; + phys_addr_t phys; + int i; + + if (!(mdesc->init_meminfo)) + return; + + /* remap kernel code and data */ + map_start = init_mm.start_code; + map_end = init_mm.brk; + + /* get a handle on things... */ + pgd0 = pgd_offset_k(0); + pud_start = pud0 = pud_offset(pgd0, 0); + pmd0 = pmd_offset(pud0, 0); + + pgdk = pgd_offset_k(map_start); + pudk = pud_offset(pgdk, map_start); + pmdk = pmd_offset(pudk, map_start); + + mdesc->init_meminfo(); + + /* Run the patch stub to update the constants */ + fixup_pv_table(&__pv_table_begin, + (&__pv_table_end - &__pv_table_begin) << 2); + + /* + * Cache cleaning operations for self-modifying code + * We should clean the entries by MVA but running a + * for loop over every pv_table entry pointer would + * just complicate the code. + */ + flush_cache_louis(); + dsb(); + isb(); + + /* remap level 1 table */ + for (i = 0; i < PTRS_PER_PGD; pud0++, i++) { + set_pud(pud0, + __pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); + pmd0 += PTRS_PER_PMD; + } + + /* remap pmds for kernel mapping */ + phys = __pa(map_start) & PMD_MASK; + do { + *pmdk++ = __pmd(phys | pmdprot); + phys += PMD_SIZE; + } while (phys < map_end); + + flush_cache_all(); + cpu_switch_mm(pgd0, &init_mm); + cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET); + local_flush_bp_all(); + local_flush_tlb_all(); +} + +#else + +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + if (mdesc->init_meminfo) + mdesc->init_meminfo(); +} + +#endif + /* * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. -- cgit v1.2.3 From 457c2403c513c74f60d5757fd11ae927e5554a38 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 12 Feb 2013 18:59:57 +0000 Subject: ARM: asm: Add ARM_BE8() assembly helper Add ARM_BE8() helper to wrap any code conditional on being compile when CONFIG_ARM_ENDIAN_BE8 is selected and convert existing places where this is to use it. Acked-by: Nicolas Pitre Reviewed-by: Will Deacon Signed-off-by: Ben Dooks --- arch/arm/boot/compressed/head.S | 8 ++------ arch/arm/include/asm/assembler.h | 7 +++++++ arch/arm/kernel/entry-armv.S | 5 ++--- arch/arm/kernel/entry-common.S | 4 +--- arch/arm/mm/abort-ev6.S | 5 ++--- arch/arm/mm/proc-v6.S | 4 +--- arch/arm/mm/proc-v7.S | 4 +--- 7 files changed, 16 insertions(+), 21 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 75189f13cf54..c912c2a95de8 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -699,9 +699,7 @@ __armv4_mmu_cache_on: mrc p15, 0, r0, c1, c0, 0 @ read control reg orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x0030 -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables bl __common_mmu_cache_on mov r0, #0 mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs @@ -728,9 +726,7 @@ __armv7_mmu_cache_on: orr r0, r0, #1 << 22 @ U (v6 unaligned access model) @ (needed for ARM1176) #ifdef CONFIG_MMU -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg orrne r0, r0, #1 @ MMU enabled movne r1, #0xfffffffd @ domain 0 = client diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index fcc1b5bf6979..5c2285160575 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -53,6 +53,13 @@ #define put_byte_3 lsl #0 #endif +/* Select code for any configuration running in BE8 mode */ +#ifdef CONFIG_CPU_ENDIAN_BE8 +#define ARM_BE8(code...) code +#else +#define ARM_BE8(code...) +#endif + /* * Data preload for architectures that support it */ diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 9cbe70c8b0ef..55090fbb81a2 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -416,9 +416,8 @@ __und_usr: bne __und_usr_thumb sub r4, r2, #4 @ ARM instr at LR - 4 1: ldrt r0, [r4] -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r0, r0 @ little endian instruction -#endif + ARM_BE8(rev r0, r0) @ little endian instruction + @ r0 = 32-bit ARM instruction which caused the exception @ r2 = PC value for the following instruction (:= regs->ARM_pc) @ r4 = PC value for the faulting instruction diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bc6bd9683ba4..a2dcafdf1bc8 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -393,9 +393,7 @@ ENTRY(vector_swi) #else USER( ldr r10, [lr, #-4] ) @ get SWI instruction #endif -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r10, r10 @ little endian instruction -#endif + ARM_BE8(rev r10, r10) @ little endian instruction #elif defined(CONFIG_AEABI) diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 80741992a9fc..3815a8262af0 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -38,9 +38,8 @@ ENTRY(v6_early_abort) bne do_DataAbort bic r1, r1, #1 << 11 @ clear bit 11 of FSR ldr r3, [r4] @ read aborted ARM instruction -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r3, r3 -#endif + ARM_BE8(rev r3, r3) + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 1128064fddcb..45dc29f85d56 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -220,9 +220,7 @@ __v6_setup: #endif /* CONFIG_MMU */ adr r5, v6_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index c63d9bdee51e..60920f62fdf5 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -367,9 +367,7 @@ __v7_setup: #endif adr r5, v7_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables #ifdef CONFIG_SWP_EMULATE orr r5, r5, #(1 << 10) @ set SW bit in "clear" bic r6, r6, #(1 << 10) @ clear it in "mmuset" -- cgit v1.2.3 From 2f9bf9beddb1649485b47302a5aba9761cbc9084 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 1 Feb 2013 16:23:08 +0100 Subject: ARM: fixup_pv_table bug when CPU_ENDIAN_BE8 The fixup_pv_table assumes that the instructions are in the same endian configuration as the data, but when the CPU is running in BE8 the instructions stay in little-endian format. Make sure if CONFIG_CPU_ENDIAN_BE8 is set that we do all the alterations to the instructions taking in to account the LDR/STR will be swapping the data endian-ness. Since the code is only modifying a byte, we avoid dual-swapping the data, and just change the bits we clear and ORR in (in the case where the code is not thumb2). For thumb2, we add the necessary rev16 instructions to ensure that the instructions are processed in the correct format, as it was easier than re-writing the code to contain a mask and shift. Signed-off-by: Ben Dooks Reviewed-by: Dave Martin Tested-by: Thomas Petazzoni --- arch/arm/kernel/head.S | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 2c7cc1e03473..9e5906cf7d32 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -582,8 +582,10 @@ __fixup_a_pv_table: b 2f 1: add r7, r3 ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) and ip, 0x8f00 orr ip, r6 @ mask in offset bits 31-24 +ARM_BE8(rev16 ip, ip) strh ip, [r7, #2] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot @@ -592,8 +594,14 @@ __fixup_a_pv_table: #else b 2f 1: ldr ip, [r7, r3] +#ifdef CONFIG_CPU_ENDIAN_BE8 + @ in BE8, we load data in BE, but instructions still in LE + bic ip, ip, #0xff000000 + orr ip, ip, r6, lsl#24 +#else bic ip, ip, #0x000000ff orr ip, ip, r6 @ mask in offset bits 31-24 +#endif str ip, [r7, r3] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot -- cgit v1.2.3 From 97bcb0fea590d3d704f985bec08f342d28992634 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 1 Feb 2013 09:40:42 +0000 Subject: ARM: set BE8 if LE in head code If we are booting in LE and compiled for BE8, then add code to set the state to bE8. Since the instruction stream is always LE, we do not need to do anything special to the instruction. Also ensure that the secondary processors are started in the same mode. Note, we do add about 20 bytes to the kernel image, but it seems easier to do this than adding another configuration to change. Signed-off-by: Ben Dooks Reviewed-by: Dave Martin Tested-by: Thomas Petazzoni --- arch/arm/boot/compressed/head.S | 1 + arch/arm/kernel/head.S | 4 ++++ arch/arm/kernel/sleep.S | 1 + 3 files changed, 6 insertions(+) (limited to 'arch/arm/kernel') diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index c912c2a95de8..066b03480b63 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -135,6 +135,7 @@ start: .word _edata @ zImage end address THUMB( .thumb ) 1: + ARM_BE8( setend be ) @ go BE8 if compiled for BE8 mrs r9, cpsr #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install @ get into SVC mode, reversibly diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 9e5906cf7d32..a047acfa6b6d 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -77,6 +77,7 @@ __HEAD ENTRY(stext) + ARM_BE8(setend be ) @ ensure we are in BE8 mode THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. THUMB( bx r9 ) @ If this is a Thumb-2 kernel, @@ -352,6 +353,9 @@ ENTRY(secondary_startup) * the processor type - there is no need to check the machine type * as it has already been validated by the primary processor. */ + + ARM_BE8(setend be) @ ensure we are in BE8 mode + #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install_secondary #endif diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index db1536b8b30b..716343caa960 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -130,6 +130,7 @@ ENDPROC(cpu_resume_after_mmu) .data .align ENTRY(cpu_resume) +ARM_BE8(setend be) @ ensure we are in BE mode mov r1, #0 ALT_SMP(mrc p15, 0, r0, c0, c0, 5) ALT_UP_B(1f) -- cgit v1.2.3 From 2e874ea342146130206f8b39f2103f33690a7547 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 6 Feb 2013 18:44:20 +0000 Subject: ARM: twd: data endian fix Ensure the twd driver uses the correct calls to access the hardware to ensure that we do not end up with data in the wrong endian format. Reviewed-by: Will Deacon Signed-off-by: Ben Dooks --- arch/arm/kernel/smp_twd.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 2985c9f0905d..6591e26fc13f 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_PERIODIC: ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_PERIODIC; - __raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), + writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), twd_base + TWD_TIMER_LOAD); break; case CLOCK_EVT_MODE_ONESHOT: @@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode, ctrl = 0; } - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); } static int twd_set_next_event(unsigned long evt, struct clock_event_device *unused) { - unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL); + unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL); ctrl |= TWD_TIMER_CONTROL_ENABLE; - __raw_writel(evt, twd_base + TWD_TIMER_COUNTER); - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); return 0; } @@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt, */ static int twd_timer_ack(void) { - if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) { - __raw_writel(1, twd_base + TWD_TIMER_INTSTAT); + if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) { + writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT); return 1; } @@ -211,15 +211,15 @@ static void twd_calibrate_rate(void) waitjiffies += 5; /* enable, no interrupt or reload */ - __raw_writel(0x1, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL); /* maximum value */ - __raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); while (get_jiffies_64() < waitjiffies) udelay(10); - count = __raw_readl(twd_base + TWD_TIMER_COUNTER); + count = readl_relaxed(twd_base + TWD_TIMER_COUNTER); twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); @@ -277,7 +277,7 @@ static void twd_timer_setup(void) * bother with the below. */ if (per_cpu(percpu_setup_called, cpu)) { - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clockevents_register_device(clk); enable_percpu_irq(clk->irq, 0); return; @@ -290,7 +290,7 @@ static void twd_timer_setup(void) * The following is done once per CPU the first time .setup() is * called. */ - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clk->name = "local_timer"; clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT | -- cgit v1.2.3 From 099a4809133dc6548d37cc143ab0cb9c2eba97bb Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Thu, 7 Feb 2013 11:14:21 +0000 Subject: ARM: smp_scu: data endian fixes The smp_scu driver needs to use the relaxed readl/write accessors to avoid any issues with the endian mode the processor core is in. Reviewed-by: Will Deacon Signed-off-by: Ben Dooks --- arch/arm/kernel/smp_scu.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 5bc1a63284e3..1aafa0d785eb 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -28,7 +28,7 @@ */ unsigned int __init scu_get_core_count(void __iomem *scu_base) { - unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG); + unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG); return (ncores & 0x03) + 1; } @@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base) #ifdef CONFIG_ARM_ERRATA_764369 /* Cortex-A9 only */ if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { - scu_ctrl = __raw_readl(scu_base + 0x30); + scu_ctrl = readl_relaxed(scu_base + 0x30); if (!(scu_ctrl & 1)) - __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); + writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30); } #endif - scu_ctrl = __raw_readl(scu_base + SCU_CTRL); + scu_ctrl = readl_relaxed(scu_base + SCU_CTRL); /* already enabled? */ if (scu_ctrl & 1) return; scu_ctrl |= 1; - __raw_writel(scu_ctrl, scu_base + SCU_CTRL); + writel_relaxed(scu_ctrl, scu_base + SCU_CTRL); /* * Ensure that the data accessed by CPU0 before the SCU was @@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode) if (mode > 3 || mode == 1 || cpu > 3) return -EINVAL; - val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; + val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; val |= mode; - __raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu); + writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu); return 0; } -- cgit v1.2.3 From a79a0cb1d35ec422dcf493cef1bebf9fdfcfdb9a Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 19 Jul 2013 17:12:05 +0100 Subject: ARM: traps: use to get correct instruction order The trap handler needs to take into account the endian configuration of the system when loading instructions. Use to provide the necessary conversion functions. Signed-off-by: Ben Dooks Tested-by: Thomas Petazzoni --- arch/arm/kernel/traps.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 8fcda140358d..caf96da27360 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -34,6 +34,7 @@ #include #include #include +#include static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" }; @@ -402,25 +403,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (processor_mode(regs) == SVC_MODE) { #ifdef CONFIG_THUMB2_KERNEL if (thumb_mode(regs)) { - instr = ((u16 *)pc)[0]; + instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]); if (is_wide_instruction(instr)) { - instr <<= 16; - instr |= ((u16 *)pc)[1]; + u16 inst2; + inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]); + instr = __opcode_thumb32_compose(instr, inst2); } } else #endif - instr = *(u32 *) pc; + instr = __mem_to_opcode_arm(*(u32 *) pc); } else if (thumb_mode(regs)) { if (get_user(instr, (u16 __user *)pc)) goto die_sig; + instr = __mem_to_opcode_thumb16(instr); if (is_wide_instruction(instr)) { unsigned int instr2; if (get_user(instr2, (u16 __user *)pc+1)) goto die_sig; - instr <<= 16; - instr |= instr2; + instr2 = __mem_to_opcode_thumb16(instr2); + instr = __opcode_thumb32_compose(instr, instr2); } } else if (get_user(instr, (u32 __user *)pc)) { + instr = __mem_to_opcode_arm(instr); goto die_sig; } -- cgit v1.2.3 From f592d323bc2353db871d1e840f05b27e0730fb10 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 19 Jul 2013 18:27:23 +0100 Subject: ARM: module: correctly relocate instructions in BE8 When in BE8 mode, our instructions are not in the same ordering as the data, so use to take this into account. Note, also requires modules to be built --be8 Signed-off-by: Ben Dooks Reviewed-by: Dave Martin --- arch/arm/kernel/module.c | 57 +++++++++++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 23 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 084dc8896986..5fdb4038f969 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -24,6 +24,7 @@ #include #include #include +#include #ifdef CONFIG_XIP_KERNEL /* @@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, Elf32_Sym *sym; const char *symname; s32 offset; + u32 tmp; #ifdef CONFIG_THUMB2_KERNEL u32 upper, lower, sign, j1, j2; #endif @@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - offset = (*(u32 *)loc & 0x00ffffff) << 2; + offset = __mem_to_opcode_arm(*(u32 *)loc); + offset = (offset & 0x00ffffff) << 2; if (offset & 0x02000000) offset -= 0x04000000; @@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, } offset >>= 2; + offset &= 0x00ffffff; - *(u32 *)loc &= 0xff000000; - *(u32 *)loc |= offset & 0x00ffffff; + *(u32 *)loc &= __opcode_to_mem_arm(0xff000000); + *(u32 *)loc |= __opcode_to_mem_arm(offset); break; case R_ARM_V4BX: @@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, * other bits to re-code instruction as * MOV PC,Rm. */ - *(u32 *)loc &= 0xf000000f; - *(u32 *)loc |= 0x01a0f000; + *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f); + *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000); break; case R_ARM_PREL31: @@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - offset = *(u32 *)loc; + offset = tmp = __mem_to_opcode_arm(*(u32 *)loc); offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff); offset = (offset ^ 0x8000) - 0x8000; @@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS) offset >>= 16; - *(u32 *)loc &= 0xfff0f000; - *(u32 *)loc |= ((offset & 0xf000) << 4) | - (offset & 0x0fff); + tmp &= 0xfff0f000; + tmp |= ((offset & 0xf000) << 4) | + (offset & 0x0fff); + + *(u32 *)loc = __opcode_to_mem_arm(tmp); break; #ifdef CONFIG_THUMB2_KERNEL case R_ARM_THM_CALL: case R_ARM_THM_JUMP24: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * 25 bit signed address range (Thumb-2 BL and B.W @@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, sign = (offset >> 24) & 1; j1 = sign ^ (~(offset >> 23) & 1); j2 = sign ^ (~(offset >> 22) & 1); - *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) | + upper = (u16)((upper & 0xf800) | (sign << 10) | ((offset >> 12) & 0x03ff)); - *(u16 *)(loc + 2) = (u16)((lower & 0xd000) | - (j1 << 13) | (j2 << 11) | - ((offset >> 1) & 0x07ff)); + lower = (u16)((lower & 0xd000) | + (j1 << 13) | (j2 << 11) | + ((offset >> 1) & 0x07ff)); + + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * MOVT/MOVW instructions encoding in Thumb-2: @@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS) offset >>= 16; - *(u16 *)loc = (u16)((upper & 0xfbf0) | - ((offset & 0xf000) >> 12) | - ((offset & 0x0800) >> 1)); - *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) | - ((offset & 0x0700) << 4) | - (offset & 0x00ff)); + upper = (u16)((upper & 0xfbf0) | + ((offset & 0xf000) >> 12) | + ((offset & 0x0800) >> 1)); + lower = (u16)((lower & 0x8f00) | + ((offset & 0x0700) << 4) | + (offset & 0x00ff)); + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; #endif -- cgit v1.2.3 From 63328070eff2f4fd730c86966a0dbc976147c39f Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Thu, 25 Jul 2013 14:38:03 +0100 Subject: ARM: Correct BUG() assembly to ensure it is endian-agnostic Currently BUG() uses .word or .hword to create the necessary illegal instructions. However if we are building BE8 then these get swapped by the linker into different illegal instructions in the text. This means that the BUG() macro does not get trapped properly. Change to using to provide the necessary ARM instruction building as we cannot rely on gcc/gas having the `.inst` instructions which where added to try and resolve this issue (reported by Dave Martin ). Signed-off-by: Ben Dooks Reviewed-by: Dave Martin --- arch/arm/include/asm/bug.h | 10 ++++++---- arch/arm/kernel/traps.c | 8 +++++--- 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 7af5c6c3653a..b274bde24905 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -2,6 +2,8 @@ #define _ASMARM_BUG_H #include +#include +#include #ifdef CONFIG_BUG @@ -12,10 +14,10 @@ */ #ifdef CONFIG_THUMB2_KERNEL #define BUG_INSTR_VALUE 0xde02 -#define BUG_INSTR_TYPE ".hword " +#define BUG_INSTR(__value) __inst_thumb16(__value) #else #define BUG_INSTR_VALUE 0xe7f001f2 -#define BUG_INSTR_TYPE ".word " +#define BUG_INSTR(__value) __inst_arm(__value) #endif @@ -33,7 +35,7 @@ #define __BUG(__file, __line, __value) \ do { \ - asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \ + asm volatile("1:\t" BUG_INSTR(__value) "\n" \ ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ "2:\t.asciz " #__file "\n" \ ".popsection\n" \ @@ -48,7 +50,7 @@ do { \ #define __BUG(__file, __line, __value) \ do { \ - asm volatile(BUG_INSTR_TYPE #__value); \ + asm volatile(BUG_INSTR(__value) "\n"); \ unreachable(); \ } while (0) #endif /* CONFIG_DEBUG_BUGVERBOSE */ diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index caf96da27360..6125f259b7b5 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -342,15 +342,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs, int is_valid_bugaddr(unsigned long pc) { #ifdef CONFIG_THUMB2_KERNEL - unsigned short bkpt; + u16 bkpt; + u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE); #else - unsigned long bkpt; + u32 bkpt; + u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif if (probe_kernel_address((unsigned *)pc, bkpt)) return 0; - return bkpt == BUG_INSTR_VALUE; + return bkpt == insn; } #endif -- cgit v1.2.3 From 574e2b5111e13827da501771b27d92e6e3f2e3d7 Mon Sep 17 00:00:00 2001 From: Victor Kamensky Date: Tue, 27 Aug 2013 22:41:57 -0700 Subject: ARM: signal: sigreturn_codes should be endian neutral to work in BE8 In case of BE8 kernel data is in BE order whereas code stays in LE order. Move sigreturn_codes to separate .S file and use proper assembler mnemonics for these code snippets. In this case compiler will take care of proper instructions byteswaps for BE8 case. Change assumes that sufficiently Thumb-capable tools are used to build kernel. Problem was discovered during ltp testing of BE system: all rt_sig* tests failed. Tested against the same tests in both BE and LE modes. Signed-off-by: Victor Kamensky Reviewed-by: Dave Martin Signed-off-by: Ben Dooks --- arch/arm/kernel/Makefile | 3 +- arch/arm/kernel/signal.c | 24 +----------- arch/arm/kernel/sigreturn_codes.S | 80 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 83 insertions(+), 24 deletions(-) create mode 100644 arch/arm/kernel/sigreturn_codes.S (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 5140df5f23aa..39c9834461b4 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -17,7 +17,8 @@ CFLAGS_REMOVE_return_address.o = -pg obj-y := elf.o entry-common.o irq.o opcodes.o \ process.o ptrace.o return_address.o \ - setup.o signal.o stacktrace.o sys_arm.o time.o traps.o + setup.o signal.o sigreturn_codes.o \ + stacktrace.o sys_arm.o time.o traps.o obj-$(CONFIG_ATAGS) += atags_parse.o obj-$(CONFIG_ATAGS_PROC) += atags_proc.o diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index ab3304225272..64845fc4152a 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -21,29 +21,7 @@ #include #include -/* - * For ARM syscalls, we encode the syscall number into the instruction. - */ -#define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)) -#define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)) - -/* - * With EABI, the syscall number has to be loaded into r7. - */ -#define MOV_R7_NR_SIGRETURN (0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -/* - * For Thumb syscalls, we pass the syscall number via r7. We therefore - * need two 16-bit instructions. - */ -#define SWI_THUMB_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define SWI_THUMB_RT_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -static const unsigned long sigreturn_codes[7] = { - MOV_R7_NR_SIGRETURN, SWI_SYS_SIGRETURN, SWI_THUMB_SIGRETURN, - MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN, -}; +extern const unsigned long sigreturn_codes[7]; static unsigned long signal_return_offset; diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S new file mode 100644 index 000000000000..3c5d0f2170fd --- /dev/null +++ b/arch/arm/kernel/sigreturn_codes.S @@ -0,0 +1,80 @@ +/* + * sigreturn_codes.S - code sinpets for sigreturn syscalls + * + * Created by: Victor Kamensky, 2013-08-13 + * Copyright: (C) 2013 Linaro Limited + * + * 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. + */ + +#include + +/* + * For ARM syscalls, we encode the syscall number into the instruction. + * With EABI, the syscall number has to be loaded into r7. As result + * ARM syscall sequence snippet will have move and svc in .arm encoding + * + * For Thumb syscalls, we pass the syscall number via r7. We therefore + * need two 16-bit instructions in .thumb encoding + * + * Please note sigreturn_codes code are not executed in place. Instead + * they just copied by kernel into appropriate places. Code inside of + * arch/arm/kernel/signal.c is very sensitive to layout of these code + * snippets. + */ + +#if __LINUX_ARM_ARCH__ <= 4 + /* + * Note we manually set minimally required arch that supports + * required thumb opcodes for early arch versions. It is OK + * for this file to be used in combination with other + * lower arch variants, since these code snippets are only + * used as input data. + */ + .arch armv4t +#endif + + .section .rodata + .global sigreturn_codes + .type sigreturn_codes, #object + + .arm + +sigreturn_codes: + + /* ARM sigreturn syscall code snippet */ + mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn syscall code snippet */ + .thumb + movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* ARM sigreturn_rt syscall code snippet */ + .arm + mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn_rt syscall code snippet */ + .thumb + movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* + * Note on addtional space: setup_return in signal.c + * algorithm uses two words copy regardless whether + * it is thumb case or not, so we need additional + * word after real last entry. + */ + .arm + .space 4 + + .size sigreturn_codes, . - sigreturn_codes -- cgit v1.2.3 From 830fd4d6de1785942e34babe0a8984f72b534b25 Mon Sep 17 00:00:00 2001 From: Sricharan R Date: Tue, 29 Oct 2013 07:29:56 +0100 Subject: ARM: 7870/1: head: Fix the missing underscore in __ARMEB__ macro and .align keyword Commit 'f52bb722547f43caeaecbcc62db9f3c3b80ead9b' Author: Sricharan R ARM: mm: Correct virt_to_phys patching for 64 bit physical addresses introduced a __ARMEB__ macro usage in a new place, but missed the second underscore. So correcting it here. Also a explicit .align keyword is needed for the label with .long data-type to be aligned on the 4 byte boundary. Otherwise this can cause problem for thumb2 build. So adding it here. Signed-off-by: Sricharan R Signed-off-by: Russell King --- arch/arm/kernel/head.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 54547947a4e9..32402ba6710a 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -536,7 +536,7 @@ ENTRY(fixup_smp) ldmfd sp!, {r4 - r6, pc} ENDPROC(fixup_smp) -#ifdef __ARMEB_ +#ifdef __ARMEB__ #define LOW_OFFSET 0x4 #define HIGH_OFFSET 0x0 #else @@ -632,6 +632,7 @@ __fixup_a_pv_table: #endif ENDPROC(__fixup_a_pv_table) + .align 3: .long __pv_offset ENTRY(fixup_pv_table) -- cgit v1.2.3 From 92871b94a5f9892e324c31960678387922c75049 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 9 Oct 2013 17:26:44 +0100 Subject: ARM: 7855/1: Add check for Cortex-A15 errata 798181 ECO The work-around for A15 errata 798181 is not needed if appropriate ECO fixes have been applied to r3p2 and earlier core revisions. This can be checked by reading REVIDR register bits 4 and 9. If only bit 4 is set, then the IPI broadcast can be skipped. Signed-off-by: Rob Herring Reviewed-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/cputype.h | 1 + arch/arm/include/asm/tlbflush.h | 48 +++++++++++++++-------------------------- arch/arm/kernel/setup.c | 2 ++ arch/arm/kernel/smp_tlb.c | 36 +++++++++++++++++++++++++++++-- 4 files changed, 54 insertions(+), 33 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 9672e978d50d..acdde76b39bb 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -10,6 +10,7 @@ #define CPUID_TLBTYPE 3 #define CPUID_MPUIR 4 #define CPUID_MPIDR 5 +#define CPUID_REVIDR 6 #ifdef CONFIG_CPU_V7M #define CPUID_EXT_PFR0 0x40 diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 38960264040c..def9e570199f 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -560,37 +560,6 @@ static inline void __flush_bp_all(void) asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero)); } -#include -#ifdef CONFIG_ARM_ERRATA_798181 -static inline int erratum_a15_798181(void) -{ - unsigned int midr = read_cpuid_id(); - - /* Cortex-A15 r0p0..r3p2 affected */ - if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2) - return 0; - return 1; -} - -static inline void dummy_flush_tlb_a15_erratum(void) -{ - /* - * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0. - */ - asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); - dsb(ish); -} -#else -static inline int erratum_a15_798181(void) -{ - return 0; -} - -static inline void dummy_flush_tlb_a15_erratum(void) -{ -} -#endif - /* * flush_pmd_entry * @@ -697,4 +666,21 @@ extern void flush_bp_all(void); #endif +#ifndef __ASSEMBLY__ +#ifdef CONFIG_ARM_ERRATA_798181 +extern void erratum_a15_798181_init(void); +#else +static inline void erratum_a15_798181_init(void) {} +#endif +extern bool (*erratum_a15_798181_handler)(void); + +static inline bool erratum_a15_798181(void) +{ + if (unlikely(IS_ENABLED(CONFIG_ARM_ERRATA_798181) && + erratum_a15_798181_handler)) + return erratum_a15_798181_handler(); + return false; +} +#endif + #endif diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 0e1e2b3afa45..a4852dea088b 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -599,6 +599,8 @@ static void __init setup_processor(void) elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); #endif + erratum_a15_798181_init(); + feat_v6_fixup(); cacheid_init(); diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index 83ccca303df8..95d063620b76 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -70,6 +70,40 @@ static inline void ipi_flush_bp_all(void *ignored) local_flush_bp_all(); } +#ifdef CONFIG_ARM_ERRATA_798181 +bool (*erratum_a15_798181_handler)(void); + +static bool erratum_a15_798181_partial(void) +{ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(ish); + return false; +} + +static bool erratum_a15_798181_broadcast(void) +{ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(ish); + return true; +} + +void erratum_a15_798181_init(void) +{ + unsigned int midr = read_cpuid_id(); + unsigned int revidr = read_cpuid(CPUID_REVIDR); + + /* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */ + if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 || + (revidr & 0x210) == 0x210) { + return; + } + if (revidr & 0x10) + erratum_a15_798181_handler = erratum_a15_798181_partial; + else + erratum_a15_798181_handler = erratum_a15_798181_broadcast; +} +#endif + static void ipi_flush_tlb_a15_erratum(void *arg) { dmb(); @@ -80,7 +114,6 @@ static void broadcast_tlb_a15_erratum(void) if (!erratum_a15_798181()) return; - dummy_flush_tlb_a15_erratum(); smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1); } @@ -92,7 +125,6 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) if (!erratum_a15_798181()) return; - dummy_flush_tlb_a15_erratum(); this_cpu = get_cpu(); a15_erratum_get_cpumask(this_cpu, mm, &mask); smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); -- cgit v1.2.3 From 1436c1aa626d0bc0e35c5c5231127086e80ab24a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 21 Oct 2013 13:17:08 +0100 Subject: ARM: 7862/1: pcpu: replace __get_cpu_var_uses This is the ARM part of Christoph's patchset cleaning up the various uses of __get_cpu_var across the tree. The idea is to convert __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and fewer registers are used when code is generated. [will: fixed debug ref counting checks and pcpu array accesses] Acked-by: Catalin Marinas Signed-off-by: Christoph Lameter Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/hw_breakpoint.c | 14 +++++++------- arch/arm/kernel/kprobes.c | 8 ++++---- arch/arm/kernel/perf_event_cpu.c | 2 +- arch/arm/kvm/arm.c | 6 +++--- arch/arm64/kernel/debug-monitors.c | 13 ++++++------- arch/arm64/kernel/hw_breakpoint.c | 22 +++++++++++----------- arch/arm64/kernel/perf_event.c | 4 ++-- 7 files changed, 34 insertions(+), 35 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 7b95de601357..3d446605cbf8 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -344,13 +344,13 @@ int arch_install_hw_breakpoint(struct perf_event *bp) /* Breakpoint */ ctrl_base = ARM_BASE_BCR; val_base = ARM_BASE_BVR; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; } else { /* Watchpoint */ ctrl_base = ARM_BASE_WCR; val_base = ARM_BASE_WVR; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; } @@ -396,12 +396,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { /* Breakpoint */ base = ARM_BASE_BCR; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; } else { /* Watchpoint */ base = ARM_BASE_WCR; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; } @@ -697,7 +697,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < core_num_wrps; ++i) { rcu_read_lock(); @@ -768,7 +768,7 @@ static void watchpoint_single_step_handler(unsigned long pc) struct perf_event *wp, **slots; struct arch_hw_breakpoint *info; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < core_num_wrps; ++i) { rcu_read_lock(); @@ -802,7 +802,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); /* The exception entry code places the amended lr in the PC. */ addr = regs->ARM_pc; diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 170e9f34003f..a7b621ece23d 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -171,13 +171,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } static void __kprobes set_current_kprobe(struct kprobe *p) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } static void __kprobes @@ -421,10 +421,10 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) continue; if (ri->rp && ri->rp->handler) { - __get_cpu_var(current_kprobe) = &ri->rp->kp; + __this_cpu_write(current_kprobe, &ri->rp->kp); get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->rp->handler(ri, regs); - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } orig_ret_address = (unsigned long)ri->ret_addr; diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 8d6147b2001f..d85055cd24ba 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(perf_num_counters); static struct pmu_hw_events *cpu_pmu_get_cpu_events(void) { - return &__get_cpu_var(cpu_hw_events); + return this_cpu_ptr(&cpu_hw_events); } static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 9c697db2787e..aea7ccb8d397 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -65,7 +65,7 @@ static bool vgic_present; static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { BUG_ON(preemptible()); - __get_cpu_var(kvm_arm_running_vcpu) = vcpu; + __this_cpu_write(kvm_arm_running_vcpu, vcpu); } /** @@ -75,7 +75,7 @@ static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) struct kvm_vcpu *kvm_arm_get_running_vcpu(void) { BUG_ON(preemptible()); - return __get_cpu_var(kvm_arm_running_vcpu); + return __this_cpu_read(kvm_arm_running_vcpu); } /** @@ -815,7 +815,7 @@ static void cpu_init_hyp_mode(void *dummy) boot_pgd_ptr = kvm_mmu_get_boot_httbr(); pgd_ptr = kvm_mmu_get_httbr(); - stack_page = __get_cpu_var(kvm_arm_hyp_stack_page); + stack_page = __this_cpu_read(kvm_arm_hyp_stack_page); hyp_stack_ptr = stack_page + PAGE_SIZE; vector_ptr = (unsigned long)__kvm_hyp_vector; diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index cbfacf7fb438..6a0a9b132d7a 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -27,7 +27,6 @@ #include #include -#include #include #include @@ -89,8 +88,8 @@ early_param("nodebugmon", early_debug_disable); * Keep track of debug users on each core. * The ref counts are per-cpu so we use a local_t type. */ -static DEFINE_PER_CPU(local_t, mde_ref_count); -static DEFINE_PER_CPU(local_t, kde_ref_count); +static DEFINE_PER_CPU(int, mde_ref_count); +static DEFINE_PER_CPU(int, kde_ref_count); void enable_debug_monitors(enum debug_el el) { @@ -98,11 +97,11 @@ void enable_debug_monitors(enum debug_el el) WARN_ON(preemptible()); - if (local_inc_return(&__get_cpu_var(mde_ref_count)) == 1) + if (this_cpu_inc_return(mde_ref_count) == 1) enable = DBG_MDSCR_MDE; if (el == DBG_ACTIVE_EL1 && - local_inc_return(&__get_cpu_var(kde_ref_count)) == 1) + this_cpu_inc_return(kde_ref_count) == 1) enable |= DBG_MDSCR_KDE; if (enable && debug_enabled) { @@ -118,11 +117,11 @@ void disable_debug_monitors(enum debug_el el) WARN_ON(preemptible()); - if (local_dec_and_test(&__get_cpu_var(mde_ref_count))) + if (this_cpu_dec_return(mde_ref_count) == 0) disable = ~DBG_MDSCR_MDE; if (el == DBG_ACTIVE_EL1 && - local_dec_and_test(&__get_cpu_var(kde_ref_count))) + this_cpu_dec_return(kde_ref_count) == 0) disable &= ~DBG_MDSCR_KDE; if (disable) { diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 329218ca9ffb..ff516f6691e4 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -184,14 +184,14 @@ int arch_install_hw_breakpoint(struct perf_event *bp) /* Breakpoint */ ctrl_reg = AARCH64_DBG_REG_BCR; val_reg = AARCH64_DBG_REG_BVR; - slots = __get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; reg_enable = !debug_info->bps_disabled; } else { /* Watchpoint */ ctrl_reg = AARCH64_DBG_REG_WCR; val_reg = AARCH64_DBG_REG_WVR; - slots = __get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; reg_enable = !debug_info->wps_disabled; } @@ -230,12 +230,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { /* Breakpoint */ base = AARCH64_DBG_REG_BCR; - slots = __get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; } else { /* Watchpoint */ base = AARCH64_DBG_REG_WCR; - slots = __get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; } @@ -505,11 +505,11 @@ static void toggle_bp_registers(int reg, enum debug_el el, int enable) switch (reg) { case AARCH64_DBG_REG_BCR: - slots = __get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; break; case AARCH64_DBG_REG_WCR: - slots = __get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; break; default: @@ -546,7 +546,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr, struct debug_info *debug_info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); addr = instruction_pointer(regs); debug_info = ¤t->thread.debug; @@ -596,7 +596,7 @@ unlock: user_enable_single_step(current); } else { toggle_bp_registers(AARCH64_DBG_REG_BCR, DBG_ACTIVE_EL1, 0); - kernel_step = &__get_cpu_var(stepping_kernel_bp); + kernel_step = this_cpu_ptr(&stepping_kernel_bp); if (*kernel_step != ARM_KERNEL_STEP_NONE) return 0; @@ -623,7 +623,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); debug_info = ¤t->thread.debug; for (i = 0; i < core_num_wrps; ++i) { @@ -698,7 +698,7 @@ unlock: user_enable_single_step(current); } else { toggle_bp_registers(AARCH64_DBG_REG_WCR, DBG_ACTIVE_EL1, 0); - kernel_step = &__get_cpu_var(stepping_kernel_bp); + kernel_step = this_cpu_ptr(&stepping_kernel_bp); if (*kernel_step != ARM_KERNEL_STEP_NONE) return 0; @@ -722,7 +722,7 @@ int reinstall_suspended_bps(struct pt_regs *regs) struct debug_info *debug_info = ¤t->thread.debug; int handled_exception = 0, *kernel_step; - kernel_step = &__get_cpu_var(stepping_kernel_bp); + kernel_step = this_cpu_ptr(&stepping_kernel_bp); /* * Called from single-step exception handler. diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index cea1594ff933..6983ed5a351a 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1044,7 +1044,7 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -1257,7 +1257,7 @@ device_initcall(register_pmu_driver); static struct pmu_hw_events *armpmu_get_cpu_events(void) { - return &__get_cpu_var(cpu_hw_events); + return this_cpu_ptr(&cpu_hw_events); } static void __init cpu_pmu_init(struct arm_pmu *armpmu) -- cgit v1.2.3 From 6a5014aa037495a14ea083b621ed97fd0c3c7e9e Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 22 Oct 2013 17:53:16 +0100 Subject: ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments The DTB and/or the kernel command line may pass 64-bit addresses regardless of kernel configuration, so update arm_add_memory() to take 64-bit arguments independently of the phys_addr_t size. This allows non-wrapping handling of high memory banks such as the second memory bank of APE6EVM (at 0x2_0000_0000) in case of 32-bit phys_addr_t. Signed-off-by: Magnus Damm Signed-off-by: Russell King --- arch/arm/include/asm/setup.h | 2 +- arch/arm/kernel/setup.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index c50f05609501..8d6a089dfb76 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -49,7 +49,7 @@ 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, phys_addr_t size); +extern int arm_add_memory(u64 start, u64 size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index a4852dea088b..5ec4443af08b 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -621,7 +621,7 @@ void __init dump_machine_table(void) /* can't use cpu_relax() here as it may require MMU setup */; } -int __init arm_add_memory(phys_addr_t start, phys_addr_t size) +int __init arm_add_memory(u64 start, u64 size) { struct membank *bank = &meminfo.bank[meminfo.nr_banks]; @@ -671,8 +671,8 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) static int __init early_mem(char *p) { static int usermem __initdata = 0; - phys_addr_t size; - phys_addr_t start; + u64 size; + u64 start; char *endp; /* -- cgit v1.2.3 From 6d7d5da7d75c6df676c8b72d32b02ff024438f0c Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 22 Oct 2013 17:59:54 +0100 Subject: ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t Use CONFIG_ARCH_PHYS_ADDR_T_64BIT to determine if ignoring or truncating of memory banks is neccessary. This may be needed in the case of 64-bit memory bank addresses but when phys_addr_t is kept 32-bit. Signed-off-by: Magnus Damm Signed-off-by: Russell King --- arch/arm/kernel/setup.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 5ec4443af08b..53c3901f7ee3 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -624,6 +624,7 @@ void __init dump_machine_table(void) int __init arm_add_memory(u64 start, u64 size) { struct membank *bank = &meminfo.bank[meminfo.nr_banks]; + u64 aligned_start; if (meminfo.nr_banks >= NR_BANKS) { printk(KERN_CRIT "NR_BANKS too low, " @@ -636,10 +637,16 @@ int __init arm_add_memory(u64 start, u64 size) * Size is appropriately rounded down, start is rounded up. */ size -= start & ~PAGE_MASK; - bank->start = PAGE_ALIGN(start); + aligned_start = PAGE_ALIGN(start); -#ifndef CONFIG_ARM_LPAE - if (bank->start + size < bank->start) { +#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT + if (aligned_start > ULONG_MAX) { + printk(KERN_CRIT "Ignoring memory at 0x%08llx outside " + "32-bit physical address space\n", (long long)start); + return -EINVAL; + } + + if (aligned_start + size > ULONG_MAX) { printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in " "32-bit physical address space\n", (long long)start); /* @@ -647,10 +654,11 @@ int __init arm_add_memory(u64 start, u64 size) * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB. * This means we lose a page after masking. */ - size = ULONG_MAX - bank->start; + size = ULONG_MAX - aligned_start; } #endif + bank->start = aligned_start; bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1); /* -- cgit v1.2.3 From e16b31bf47738f4498d7ce632e12d7d2a6a2492a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 4 Nov 2013 11:42:29 +0100 Subject: ARM: 7876/1: clear Thumb-2 IT state on exception handling The exception handling code fails to clear the IT state, potentially leading to incorrect execution of the fixup if the size of the IT block is more than one. Let fixup_exception do the IT sanitizing if a fixup has been found, and restore CPSR from the stack when returning from a data abort. Cc: Will Deacon Cc: stable@vger.kernel.org Reviewed-by: Catalin Marinas Signed-off-by: Marc Zyngier Signed-off-by: Russell King --- arch/arm/kernel/entry-armv.S | 1 + arch/arm/mm/extable.c | 7 ++++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 9cbe70c8b0ef..ec3e5cf46308 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -192,6 +192,7 @@ __dabt_svc: svc_entry mov r2, sp dabt_helper + THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR svc_exit r5 @ return from exception UNWIND(.fnend ) ENDPROC(__dabt_svc) diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c index 9d285626bc7d..312e15e6d00b 100644 --- a/arch/arm/mm/extable.c +++ b/arch/arm/mm/extable.c @@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs) const struct exception_table_entry *fixup; fixup = search_exception_tables(instruction_pointer(regs)); - if (fixup) + if (fixup) { regs->ARM_pc = fixup->fixup; +#ifdef CONFIG_THUMB2_KERNEL + /* Clear the IT state to avoid nasty surprises in the fixup */ + regs->ARM_cpsr &= ~PSR_IT_MASK; +#endif + } return fixup != NULL; } -- cgit v1.2.3 From 6ecf830e5029598732e04067e325d946097519cb Mon Sep 17 00:00:00 2001 From: "T.J. Purtell" Date: Wed, 6 Nov 2013 18:38:05 +0100 Subject: ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode The ARM architecture reference specifies that the IT state bits in the PSR must be all zeros in ARM mode or behavior is unspecified. On the Qualcomm Snapdragon S4/Krait architecture CPUs the processor continues to consider the IT state bits while in ARM mode. This makes it so that some instructions are skipped by the CPU. Signed-off-by: T.J. Purtell [rmk+kernel@arm.linux.org.uk: fixed whitespace formatting in patch] Signed-off-by: Russell King --- arch/arm/kernel/signal.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index ab3304225272..1aa5ecdd1b3d 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -375,12 +375,18 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig, */ thumb = handler & 1; - if (thumb) { - cpsr |= PSR_T_BIT; #if __LINUX_ARM_ARCH__ >= 7 - /* clear the If-Then Thumb-2 execution state */ - cpsr &= ~PSR_IT_MASK; + /* + * Clear the If-Then Thumb-2 execution state + * ARM spec requires this to be all 000s in ARM mode + * Snapdragon S4/Krait misbehaves on a Thumb=>ARM + * signal transition without this. + */ + cpsr &= ~PSR_IT_MASK; #endif + + if (thumb) { + cpsr |= PSR_T_BIT; } else cpsr &= ~PSR_T_BIT; } -- cgit v1.2.3 From bf18525fd793101df42a1344ecc48b49b62e48c9 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 29 Oct 2013 20:32:56 +0100 Subject: ARM: 7872/1: Support arch_irq_work_raise() via self IPIs By default, IRQ work is run from the tick interrupt (see irq_work_run() in update_process_times()). When we're in full NOHZ mode, restarting the tick requires the use of IRQ work and if the only place we run IRQ work is in the tick interrupt we have an unbreakable cycle. Implement arch_irq_work_raise() via self IPIs to break this cycle and get the tick started again. Note that we implement this via IPIs which are only available on SMP builds. This shouldn't be a problem because full NOHZ is only supported on SMP builds anyway. Signed-off-by: Stephen Boyd Reviewed-by: Kevin Hilman Cc: Frederic Weisbecker Signed-off-by: Russell King --- arch/arm/include/asm/hardirq.h | 2 +- arch/arm/kernel/smp.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index 2740c2a2df63..3d7351c844aa 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -5,7 +5,7 @@ #include #include -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 72024ea8a3a6..bf9a0d6d91dc 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -66,6 +67,7 @@ enum ipi_msg_type { IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_IRQ_WORK, }; static DECLARE_COMPLETION(cpu_running); @@ -448,6 +450,13 @@ void arch_send_call_function_single_ipi(int cpu) smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); } +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); +} +#endif + static const char *ipi_types[NR_IPI] = { #define S(x,s) [x] = s S(IPI_WAKEUP, "CPU wakeup interrupts"), @@ -456,6 +465,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_IRQ_WORK, "IRQ work interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -565,6 +575,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; +#ifdef CONFIG_IRQ_WORK + case IPI_IRQ_WORK: + irq_enter(); + irq_work_run(); + irq_exit(); + break; +#endif + default: printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); -- cgit v1.2.3 From c682e51dbc9837f4aa61180775e9ca4f2a463adf Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Sat, 9 Nov 2013 00:38:24 +0100 Subject: ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise() If we're running a kernel compiled with SMP_ON_UP=y and the hardware only supports UP operation there isn't any smp_cross_call function assigned. Unfortunately, we call smp_cross_call() unconditionally in arch_irq_work_raise() and crash the kernel on UP devices. Check to make sure we're running on an SMP device before calling smp_cross_call() here. Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = c0004000 [00000000] *pgd=00000000 Internal error: Oops: 80000005 [#1] SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.12.0-rc6-00018-g8d45144-dirty #16 task: de05b440 ti: de05c000 task.ti: de05c000 PC is at 0x0 LR is at arch_irq_work_raise+0x3c/0x48 pc : [<00000000>] lr : [] psr: 60000193 sp : de05dd60 ip : 00000001 fp : 00000000 r10: c085e2f0 r9 : de05c000 r8 : c07be0a4 r7 : de05c000 r6 : de05c000 r5 : c07c5778 r4 : c0824554 r3 : 00000000 r2 : 00000000 r1 : 00000006 r0 : c0529a58 Flags: nZCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c5387d Table: 80004019 DAC: 00000017 Process swapper/0 (pid: 1, stack limit = 0xde05c248) Stack: (0xde05dd60 to 0xde05e000) dd60: c07b9dbc c00cb2dc 00000001 c08242c0 c08242c0 60000113 c07be0a8 c00b0590 dd80: de05c000 c085e2f0 c08242c0 c08242c0 c1414c28 c00b07cc de05b440 c1414c28 dda0: c08242c0 c00b0af8 c0862bb0 c0862db0 c1414cd8 de05c028 c0824840 de05ddb8 ddc0: 00000000 00000009 00000001 00000024 c07be0a8 c07be0a4 de05c000 c085e2f0 dde0: 00000000 c004a4b0 00000010 de00d2dc 00000054 00000100 00000024 00000000 de00: de05c028 0000000a ffff8ae7 00200040 00000016 de05c000 60000193 de05c000 de20: 00000054 00000000 00000000 00000000 00000000 c004a704 00000000 de05c008 de40: c07ba254 c004aa1c c07c5778 c0014b70 fa200000 00000054 de05de80 c0861244 de60: 00000000 c0008634 de05b440 c051c778 20000113 ffffffff de05deb4 c051d0a4 de80: 00000001 00000001 00000000 de05b440 c082afac de057ac0 de057ac0 de0443c0 dea0: 00000000 00000000 00000000 00000000 c082afbc de05dec8 c009f2a0 c051c778 dec0: 20000113 ffffffff 00000000 c016edb0 00000000 000002b0 de057ac0 de057ac0 dee0: 00000000 c016ee40 c0875e50 de05df2e de057ac0 00000000 00000013 00000000 df00: 00000000 c016f054 de043600 de0443c0 c008eb38 de004ec0 c0875e50 c008eb44 df20: 00000012 00000000 00000000 3931f0f8 00000000 00000000 00000014 c0822e84 df40: 00000000 c008ed2c 00000000 00000000 00000000 c07b7490 c07b7490 c075ab3c df60: 00000000 c00701ac 00000002 00000000 c0070160 dffadb73 7bf8edb4 00000000 df80: c051092c 00000000 00000000 00000000 00000000 00000000 00000000 c0510934 dfa0: de05aa40 00000000 c051092c c0013ce8 00000000 00000000 00000000 00000000 dfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 dfe0: 00000000 00000000 00000000 00000000 00000013 00000000 07efffe5 4dfac6f5 [] (arch_irq_work_raise+0x3c/0x48) from [] (irq_work_queue+0xe4/0xf8) [] (irq_work_queue+0xe4/0xf8) from [] (rcu_accelerate_cbs+0x1d4/0x1d8) [] (rcu_accelerate_cbs+0x1d4/0x1d8) from [] (rcu_start_gp+0x34/0x48) [] (rcu_start_gp+0x34/0x48) from [] (rcu_process_callbacks+0x318/0x608) [] (rcu_process_callbacks+0x318/0x608) from [] (__do_softirq+0x114/0x2a0) [] (__do_softirq+0x114/0x2a0) from [] (do_softirq+0x6c/0x74) [] (do_softirq+0x6c/0x74) from [] (irq_exit+0xac/0x100) [] (irq_exit+0xac/0x100) from [] (handle_IRQ+0x54/0xb4) [] (handle_IRQ+0x54/0xb4) from [] (omap3_intc_handle_irq+0x60/0x74) [] (omap3_intc_handle_irq+0x60/0x74) from [] (__irq_svc+0x44/0x5c) Exception stack(0xde05de80 to 0xde05dec8) de80: 00000001 00000001 00000000 de05b440 c082afac de057ac0 de057ac0 de0443c0 dea0: 00000000 00000000 00000000 00000000 c082afbc de05dec8 c009f2a0 c051c778 dec0: 20000113 ffffffff [] (__irq_svc+0x44/0x5c) from [] (_raw_spin_unlock_irq+0x28/0x2c) [] (_raw_spin_unlock_irq+0x28/0x2c) from [] (proc_alloc_inum+0x30/0xa8) [] (proc_alloc_inum+0x30/0xa8) from [] (proc_register+0x18/0x130) [] (proc_register+0x18/0x130) from [] (proc_mkdir_data+0x44/0x6c) [] (proc_mkdir_data+0x44/0x6c) from [] (register_irq_proc+0x6c/0x128) [] (register_irq_proc+0x6c/0x128) from [] (init_irq_proc+0x74/0xb0) [] (init_irq_proc+0x74/0xb0) from [] (kernel_init_freeable+0x84/0x1c8) [] (kernel_init_freeable+0x84/0x1c8) from [] (kernel_init+0x8/0x150) [] (kernel_init+0x8/0x150) from [] (ret_from_fork+0x14/0x2c) Code: bad PC value Fixes: bf18525fd79 "ARM: 7872/1: Support arch_irq_work_raise() via self IPIs" Reported-by: Olof Johansson Signed-off-by: Stephen Boyd Tested-by: Olof Johansson Signed-off-by: Russell King --- arch/arm/kernel/smp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/arm/kernel') diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index bf9a0d6d91dc..e115cbb0d25a 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -453,7 +453,8 @@ void arch_send_call_function_single_ipi(int cpu) #ifdef CONFIG_IRQ_WORK void arch_irq_work_raise(void) { - smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); + if (is_smp()) + smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); } #endif -- cgit v1.2.3