summaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/kernel')
-rw-r--r--arch/arm/kernel/Makefile5
-rw-r--r--arch/arm/kernel/armksyms.c6
-rw-r--r--arch/arm/kernel/entry-armv.S32
-rw-r--r--arch/arm/kernel/entry-common.S63
-rw-r--r--arch/arm/kernel/entry-header.S112
-rw-r--r--arch/arm/kernel/head.S5
-rw-r--r--arch/arm/kernel/irq.c1
-rw-r--r--arch/arm/kernel/perf_event.c896
-rw-r--r--arch/arm/kernel/perf_event_v6.c2
-rw-r--r--arch/arm/kernel/perf_event_v7.c2
-rw-r--r--arch/arm/kernel/perf_event_xscale.c2
-rw-r--r--arch/arm/kernel/process.c56
-rw-r--r--arch/arm/kernel/psci.c299
-rw-r--r--arch/arm/kernel/psci_smp.c31
-rw-r--r--arch/arm/kernel/setup.c9
-rw-r--r--arch/arm/kernel/signal.c6
-rw-r--r--arch/arm/kernel/smp.c17
-rw-r--r--arch/arm/kernel/swp_emulate.c3
-rw-r--r--arch/arm/kernel/traps.c1
19 files changed, 222 insertions, 1326 deletions
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index e69f7a19735d..af9e59bf3831 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -71,8 +71,7 @@ obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o
obj-$(CONFIG_CPU_PJ4B) += pj4-cp0.o
obj-$(CONFIG_IWMMXT) += iwmmxt.o
obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o
-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o \
- perf_event_xscale.o perf_event_v6.o \
+obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_xscale.o perf_event_v6.o \
perf_event_v7.o
CFLAGS_pj4-cp0.o := -marm
AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt
@@ -89,7 +88,7 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o
ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y += psci.o psci-call.o
+obj-y += psci-call.o
obj-$(CONFIG_SMP) += psci_smp.o
endif
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5e5a51a99e68..f89811fb9a55 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -97,9 +97,9 @@ EXPORT_SYMBOL(mmiocpy);
#ifdef CONFIG_MMU
EXPORT_SYMBOL(copy_page);
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index cb4fb1e69778..3e1c26eb32b4 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -149,10 +149,10 @@ ENDPROC(__und_invalid)
#define SPFIX(code...)
#endif
- .macro svc_entry, stack_hole=0, trace=1
+ .macro svc_entry, stack_hole=0, trace=1, uaccess=1
UNWIND(.fnstart )
UNWIND(.save {r0 - pc} )
- sub sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+ sub sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
#ifdef CONFIG_THUMB2_KERNEL
SPFIX( str r0, [sp] ) @ temporarily saved
SPFIX( mov r0, sp )
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
ldmia r0, {r3 - r5}
add r7, sp, #S_SP - 4 @ here for interlock avoidance
mov r6, #-1 @ "" "" "" ""
- add r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+ add r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
SPFIX( addeq r2, r2, #4 )
str r3, [sp, #-4]! @ save the "real" r0 copied
@ from the exception stack
@@ -185,6 +185,11 @@ ENDPROC(__und_invalid)
@
stmia r7, {r2 - r6}
+ uaccess_save r0
+ .if \uaccess
+ uaccess_disable r0
+ .endif
+
.if \trace
#ifdef CONFIG_TRACE_IRQFLAGS
bl trace_hardirqs_off
@@ -194,7 +199,7 @@ ENDPROC(__und_invalid)
.align 5
__dabt_svc:
- svc_entry
+ svc_entry uaccess=0
mov r2, sp
dabt_helper
THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR
@@ -368,7 +373,7 @@ ENDPROC(__fiq_abt)
#error "sizeof(struct pt_regs) must be a multiple of 8"
#endif
- .macro usr_entry, trace=1
+ .macro usr_entry, trace=1, uaccess=1
UNWIND(.fnstart )
UNWIND(.cantunwind ) @ don't unwind the user space
sub sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@ ENDPROC(__fiq_abt)
ARM( stmdb r0, {sp, lr}^ )
THUMB( store_user_sp_lr r0, r1, S_SP - S_PC )
+ .if \uaccess
+ uaccess_disable ip
+ .endif
+
@ Enable the alignment trap while in kernel mode
ATRAP( teq r8, r7)
ATRAP( mcrne p15, 0, r8, c1, c0, 0)
@@ -435,7 +444,7 @@ ENDPROC(__fiq_abt)
.align 5
__dabt_usr:
- usr_entry
+ usr_entry uaccess=0
kuser_cmpxchg_check
mov r2, sp
dabt_helper
@@ -458,7 +467,7 @@ ENDPROC(__irq_usr)
.align 5
__und_usr:
- usr_entry
+ usr_entry uaccess=0
mov r2, r4
mov r3, r5
@@ -484,6 +493,8 @@ __und_usr:
1: ldrt r0, [r4]
ARM_BE8(rev r0, r0) @ little endian instruction
+ uaccess_disable ip
+
@ r0 = 32-bit ARM instruction which caused the exception
@ r2 = PC value for the following instruction (:= regs->ARM_pc)
@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@ __und_usr_thumb:
2: ldrht r5, [r4]
ARM_BE8(rev16 r5, r5) @ little endian instruction
cmp r5, #0xe800 @ 32bit instruction if xx != 0
- blo __und_usr_fault_16 @ 16bit undefined instruction
+ blo __und_usr_fault_16_pan @ 16bit undefined instruction
3: ldrht r0, [r2]
ARM_BE8(rev16 r0, r0) @ little endian instruction
+ uaccess_disable ip
add r2, r2, #2 @ r2 is PC + 2, make it PC + 4
str r2, [sp, #S_PC] @ it's a 2x16bit instr, update
orr r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@ ENDPROC(no_fp)
__und_usr_fault_32:
mov r1, #4
b 1f
+__und_usr_fault_16_pan:
+ uaccess_disable ip
__und_usr_fault_16:
mov r1, #2
1: mov r0, sp
@@ -770,6 +784,8 @@ ENTRY(__switch_to)
ldr r4, [r2, #TI_TP_VALUE]
ldr r5, [r2, #TI_TP_VALUE + 4]
#ifdef CONFIG_CPU_USE_DOMAINS
+ mrc p15, 0, r6, c3, c0, 0 @ Get domain register
+ str r6, [r1, #TI_CPU_DOMAIN] @ Save old domain register
ldr r6, [r2, #TI_CPU_DOMAIN]
#endif
switch_tls r1, r4, r5, r3, r7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index b48dd4f37f80..30a7228eaceb 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -24,35 +24,55 @@
.align 5
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
/*
- * This is the fast syscall return path. We do as little as
- * possible here, and this includes saving r0 back into the SVC
- * stack.
+ * This is the fast syscall return path. We do as little as possible here,
+ * such as avoiding writing r0 to the stack. We only use this path if we
+ * have tracing and context tracking disabled - the overheads from those
+ * features make this path too inefficient.
*/
ret_fast_syscall:
UNWIND(.fnstart )
UNWIND(.cantunwind )
- disable_irq @ disable interrupts
+ disable_irq_notrace @ disable interrupts
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK
- bne __sys_trace_return
- tst r1, #_TIF_WORK_MASK
+ tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
bne fast_work_pending
- asm_trace_hardirqs_on
/* perform architecture specific actions before user return */
arch_ret_to_user r1, lr
- ct_user_enter
restore_user_regs fast = 1, offset = S_OFF
UNWIND(.fnend )
+ENDPROC(ret_fast_syscall)
-/*
- * Ok, we need to do extra processing, enter the slow path.
- */
+ /* Ok, we need to do extra processing, enter the slow path. */
fast_work_pending:
str r0, [sp, #S_R0+S_OFF]! @ returned r0
-work_pending:
+ /* fall through to work_pending */
+#else
+/*
+ * The "replacement" ret_fast_syscall for when tracing or context tracking
+ * is enabled. As we will need to call out to some C functions, we save
+ * r0 first to avoid needing to save registers around each C function call.
+ */
+ret_fast_syscall:
+ UNWIND(.fnstart )
+ UNWIND(.cantunwind )
+ str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
+ disable_irq_notrace @ disable interrupts
+ ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
+ tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+ beq no_work_pending
+ UNWIND(.fnend )
+ENDPROC(ret_fast_syscall)
+
+ /* Slower path - fall through to work_pending */
+#endif
+
+ tst r1, #_TIF_SYSCALL_WORK
+ bne __sys_trace_return_nosave
+slow_work_pending:
mov r0, sp @ 'regs'
mov r2, why @ 'syscall'
bl do_work_pending
@@ -65,16 +85,19 @@ ENDPROC(ret_fast_syscall)
/*
* "slow" syscall return path. "why" tells us if this was a real syscall.
+ * IRQs may be enabled here, so always disable them. Note that we use the
+ * "notrace" version to avoid calling into the tracing code unnecessarily.
+ * do_work_pending() will update this state if necessary.
*/
ENTRY(ret_to_user)
ret_slow_syscall:
- disable_irq @ disable interrupts
+ disable_irq_notrace @ disable interrupts
ENTRY(ret_to_user_from_irq)
ldr r1, [tsk, #TI_FLAGS]
tst r1, #_TIF_WORK_MASK
- bne work_pending
+ bne slow_work_pending
no_work_pending:
- asm_trace_hardirqs_on
+ asm_trace_hardirqs_on save = 0
/* perform architecture specific actions before user return */
arch_ret_to_user r1, lr
@@ -174,6 +197,8 @@ ENTRY(vector_swi)
USER( ldr scno, [lr, #-4] ) @ get SWI instruction
#endif
+ uaccess_disable tbl
+
adr tbl, sys_call_table @ load syscall table pointer
#if defined(CONFIG_OABI_COMPAT)
@@ -252,6 +277,12 @@ __sys_trace_return:
bl syscall_trace_exit
b ret_slow_syscall
+__sys_trace_return_nosave:
+ enable_irq_notrace
+ mov r0, sp
+ bl syscall_trace_exit
+ b ret_slow_syscall
+
.align 5
#ifdef CONFIG_ALIGNMENT_TRAP
.type __cr_alignment, #object
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1a0045abead7..0d22ad206d52 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -196,7 +196,7 @@
msr cpsr_c, \rtemp @ switch back to the SVC mode
.endm
-#ifndef CONFIG_THUMB2_KERNEL
+
.macro svc_exit, rpsr, irq = 0
.if \irq != 0
@ IRQs already off
@@ -215,6 +215,10 @@
blne trace_hardirqs_off
#endif
.endif
+ uaccess_restore
+
+#ifndef CONFIG_THUMB2_KERNEL
+ @ ARM mode SVC restore
msr spsr_cxsf, \rpsr
#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +226,20 @@
strex r1, r2, [r0] @ clear the exclusive monitor
#endif
ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
+#else
+ @ Thumb mode SVC restore
+ ldr lr, [sp, #S_SP] @ top of the stack
+ ldrd r0, r1, [sp, #S_LR] @ calling lr and pc
+
+ @ We must avoid clrex due to Cortex-A15 erratum #830321
+ strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor
+
+ stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context
+ ldmia sp, {r0 - r12}
+ mov sp, lr
+ ldr lr, [sp], #4
+ rfeia sp!
+#endif
.endm
@
@@ -241,6 +259,9 @@
@ on the stack remains correct).
@
.macro svc_exit_via_fiq
+ uaccess_restore
+#ifndef CONFIG_THUMB2_KERNEL
+ @ ARM mode restore
mov r0, sp
ldmib r0, {r1 - r14} @ abort is deadly from here onward (it will
@ clobber state restored below)
@@ -250,9 +271,27 @@
msr spsr_cxsf, r9
ldr r0, [r0, #S_R0]
ldmia r8, {pc}^
+#else
+ @ Thumb mode restore
+ add r0, sp, #S_R2
+ ldr lr, [sp, #S_LR]
+ ldr sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+ @ clobber state restored below)
+ ldmia r0, {r2 - r12}
+ mov r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+ msr cpsr_c, r1
+ sub r0, #S_R2
+ add r8, r0, #S_PC
+ ldmia r0, {r0 - r1}
+ rfeia r8
+#endif
.endm
+
.macro restore_user_regs, fast = 0, offset = 0
+ uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+ @ ARM mode restore
mov r2, sp
ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr
ldr lr, [r2, #\offset + S_PC]! @ get pc
@@ -270,72 +309,16 @@
@ after ldm {}^
add sp, sp, #\offset + S_FRAME_SIZE
movs pc, lr @ return & move spsr_svc into cpsr
- .endm
-
-#else /* CONFIG_THUMB2_KERNEL */
- .macro svc_exit, rpsr, irq = 0
- .if \irq != 0
- @ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
- @ The parent context IRQs must have been enabled to get here in
- @ the first place, so there's no point checking the PSR I bit.
- bl trace_hardirqs_on
-#endif
- .else
- @ IRQs off again before pulling preserved data off the stack
- disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
- tst \rpsr, #PSR_I_BIT
- bleq trace_hardirqs_on
- tst \rpsr, #PSR_I_BIT
- blne trace_hardirqs_off
-#endif
- .endif
- ldr lr, [sp, #S_SP] @ top of the stack
- ldrd r0, r1, [sp, #S_LR] @ calling lr and pc
-
- @ We must avoid clrex due to Cortex-A15 erratum #830321
- strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor
-
- stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context
- ldmia sp, {r0 - r12}
- mov sp, lr
- ldr lr, [sp], #4
- rfeia sp!
- .endm
-
- @
- @ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
- @
- @ For full details see non-Thumb implementation above.
- @
- .macro svc_exit_via_fiq
- add r0, sp, #S_R2
- ldr lr, [sp, #S_LR]
- ldr sp, [sp, #S_SP] @ abort is deadly from here onward (it will
- @ clobber state restored below)
- ldmia r0, {r2 - r12}
- mov r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
- msr cpsr_c, r1
- sub r0, #S_R2
- add r8, r0, #S_PC
- ldmia r0, {r0 - r1}
- rfeia r8
- .endm
-
-#ifdef CONFIG_CPU_V7M
- /*
- * Note we don't need to do clrex here as clearing the local monitor is
- * part of each exception entry and exit sequence.
- */
- .macro restore_user_regs, fast = 0, offset = 0
+#elif defined(CONFIG_CPU_V7M)
+ @ V7M restore.
+ @ Note that we don't need to do clrex here as clearing the local
+ @ monitor is part of the exception entry and exit sequence.
.if \offset
add sp, #\offset
.endif
v7m_exception_slow_exit ret_r0 = \fast
- .endm
-#else /* ifdef CONFIG_CPU_V7M */
- .macro restore_user_regs, fast = 0, offset = 0
+#else
+ @ Thumb mode restore
mov r2, sp
load_user_sp_lr r2, r3, \offset + S_SP @ calling sp, lr
ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr
@@ -353,9 +336,8 @@
.endif
add sp, sp, #S_FRAME_SIZE - S_SP
movs pc, lr @ return & move spsr_svc into cpsr
- .endm
-#endif /* ifdef CONFIG_CPU_V7M / else */
#endif /* !CONFIG_THUMB2_KERNEL */
+ .endm
/*
* Context tracking subsystem. Used to instrument transitions
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 29e2991465cb..04286fd9e09c 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -464,10 +464,7 @@ __enable_mmu:
#ifdef CONFIG_ARM_LPAE
mcrr p15, 0, r4, r5, c2 @ load TTBR0
#else
- mov r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
- domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
- domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
- domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+ mov r5, #DACR_INIT
mcr p15, 0, r5, c3, c0, 0 @ load domain access register
mcr p15, 0, r4, c2, c0, 0 @ load page table pointer
#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index baf8edebe26f..5ff4826cb154 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -39,6 +39,7 @@
#include <linux/export.h>
#include <asm/hardware/cache-l2x0.h>
+#include <asm/outercache.h>
#include <asm/exception.h>
#include <asm/mach/arch.h>
#include <asm/mach/irq.h>
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
deleted file mode 100644
index 54272e0be713..000000000000
--- a/arch/arm/kernel/perf_event.c
+++ /dev/null
@@ -1,896 +0,0 @@
-#undef DEBUG
-
-/*
- * ARM performance counter support.
- *
- * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
- * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
- *
- * This code is based on the sparc64 perf event code, which is in turn based
- * on the x86 code.
- */
-#define pr_fmt(fmt) "hw perfevents: " fmt
-
-#include <linux/bitmap.h>
-#include <linux/cpumask.h>
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/irq.h>
-#include <linux/irqdesc.h>
-
-#include <asm/cputype.h>
-#include <asm/irq_regs.h>
-#include <asm/pmu.h>
-
-static int
-armpmu_map_cache_event(const unsigned (*cache_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u64 config)
-{
- unsigned int cache_type, cache_op, cache_result, ret;
-
- cache_type = (config >> 0) & 0xff;
- if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
- return -EINVAL;
-
- cache_op = (config >> 8) & 0xff;
- if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
- return -EINVAL;
-
- cache_result = (config >> 16) & 0xff;
- if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
- return -EINVAL;
-
- ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
-
- if (ret == CACHE_OP_UNSUPPORTED)
- return -ENOENT;
-
- return ret;
-}
-
-static int
-armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
-{
- int mapping;
-
- if (config >= PERF_COUNT_HW_MAX)
- return -EINVAL;
-
- mapping = (*event_map)[config];
- return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
-}
-
-static int
-armpmu_map_raw_event(u32 raw_event_mask, u64 config)
-{
- return (int)(config & raw_event_mask);
-}
-
-int
-armpmu_map_event(struct perf_event *event,
- const unsigned (*event_map)[PERF_COUNT_HW_MAX],
- const unsigned (*cache_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u32 raw_event_mask)
-{
- u64 config = event->attr.config;
- int type = event->attr.type;
-
- if (type == event->pmu->type)
- return armpmu_map_raw_event(raw_event_mask, config);
-
- switch (type) {
- case PERF_TYPE_HARDWARE:
- return armpmu_map_hw_event(event_map, config);
- case PERF_TYPE_HW_CACHE:
- return armpmu_map_cache_event(cache_map, config);
- case PERF_TYPE_RAW:
- return armpmu_map_raw_event(raw_event_mask, config);
- }
-
- return -ENOENT;
-}
-
-int armpmu_event_set_period(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
- s64 left = local64_read(&hwc->period_left);
- s64 period = hwc->sample_period;
- int ret = 0;
-
- if (unlikely(left <= -period)) {
- left = period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- if (unlikely(left <= 0)) {
- left += period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- /*
- * Limit the maximum period to prevent the counter value
- * from overtaking the one we are about to program. In
- * effect we are reducing max_period to account for
- * interrupt latency (and we are being very conservative).
- */
- if (left > (armpmu->max_period >> 1))
- left = armpmu->max_period >> 1;
-
- local64_set(&hwc->prev_count, (u64)-left);
-
- armpmu->write_counter(event, (u64)(-left) & 0xffffffff);
-
- perf_event_update_userpage(event);
-
- return ret;
-}
-
-u64 armpmu_event_update(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
- u64 delta, prev_raw_count, new_raw_count;
-
-again:
- prev_raw_count = local64_read(&hwc->prev_count);
- new_raw_count = armpmu->read_counter(event);
-
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count)
- goto again;
-
- delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
-
- local64_add(delta, &event->count);
- local64_sub(delta, &hwc->period_left);
-
- return new_raw_count;
-}
-
-static void
-armpmu_read(struct perf_event *event)
-{
- armpmu_event_update(event);
-}
-
-static void
-armpmu_stop(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
-
- /*
- * ARM pmu always has to update the counter, so ignore
- * PERF_EF_UPDATE, see comments in armpmu_start().
- */
- if (!(hwc->state & PERF_HES_STOPPED)) {
- armpmu->disable(event);
- armpmu_event_update(event);
- hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
- }
-}
-
-static void armpmu_start(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
-
- /*
- * ARM pmu always has to reprogram the period, so ignore
- * PERF_EF_RELOAD, see the comment below.
- */
- if (flags & PERF_EF_RELOAD)
- WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
-
- hwc->state = 0;
- /*
- * Set the period again. Some counters can't be stopped, so when we
- * were stopped we simply disabled the IRQ source and the counter
- * may have been left counting. If we don't do this step then we may
- * get an interrupt too soon or *way* too late if the overflow has
- * happened since disabling.
- */
- armpmu_event_set_period(event);
- armpmu->enable(event);
-}
-
-static void
-armpmu_del(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
- struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
-
- armpmu_stop(event, PERF_EF_UPDATE);
- hw_events->events[idx] = NULL;
- clear_bit(idx, hw_events->used_mask);
- if (armpmu->clear_event_idx)
- armpmu->clear_event_idx(hw_events, event);
-
- perf_event_update_userpage(event);
-}
-
-static int
-armpmu_add(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
- struct hw_perf_event *hwc = &event->hw;
- int idx;
- int err = 0;
-
- /* An event following a process won't be stopped earlier */
- if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
- return -ENOENT;
-
- perf_pmu_disable(event->pmu);
-
- /* If we don't have a space for the counter then finish early. */
- idx = armpmu->get_event_idx(hw_events, event);
- if (idx < 0) {
- err = idx;
- goto out;
- }
-
- /*
- * If there is an event in the counter we are going to use then make
- * sure it is disabled.
- */
- event->hw.idx = idx;
- armpmu->disable(event);
- hw_events->events[idx] = event;
-
- hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
- if (flags & PERF_EF_START)
- armpmu_start(event, PERF_EF_RELOAD);
-
- /* Propagate our changes to the userspace mapping. */
- perf_event_update_userpage(event);
-
-out:
- perf_pmu_enable(event->pmu);
- return err;
-}
-
-static int
-validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events,
- struct perf_event *event)
-{
- struct arm_pmu *armpmu;
-
- if (is_software_event(event))
- return 1;
-
- /*
- * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The
- * core perf code won't check that the pmu->ctx == leader->ctx
- * until after pmu->event_init(event).
- */
- if (event->pmu != pmu)
- return 0;
-
- if (event->state < PERF_EVENT_STATE_OFF)
- return 1;
-
- if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
- return 1;
-
- armpmu = to_arm_pmu(event->pmu);
- return armpmu->get_event_idx(hw_events, event) >= 0;
-}
-
-static int
-validate_group(struct perf_event *event)
-{
- struct perf_event *sibling, *leader = event->group_leader;
- struct pmu_hw_events fake_pmu;
-
- /*
- * Initialise the fake PMU. We only need to populate the
- * used_mask for the purposes of validation.
- */
- memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask));
-
- if (!validate_event(event->pmu, &fake_pmu, leader))
- return -EINVAL;
-
- list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
- if (!validate_event(event->pmu, &fake_pmu, sibling))
- return -EINVAL;
- }
-
- if (!validate_event(event->pmu, &fake_pmu, event))
- return -EINVAL;
-
- return 0;
-}
-
-static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
-{
- struct arm_pmu *armpmu;
- struct platform_device *plat_device;
- struct arm_pmu_platdata *plat;
- int ret;
- u64 start_clock, finish_clock;
-
- /*
- * we request the IRQ with a (possibly percpu) struct arm_pmu**, but
- * the handlers expect a struct arm_pmu*. The percpu_irq framework will
- * do any necessary shifting, we just need to perform the first
- * dereference.
- */
- armpmu = *(void **)dev;
- plat_device = armpmu->plat_device;
- plat = dev_get_platdata(&plat_device->dev);
-
- start_clock = sched_clock();
- if (plat && plat->handle_irq)
- ret = plat->handle_irq(irq, armpmu, armpmu->handle_irq);
- else
- ret = armpmu->handle_irq(irq, armpmu);
- finish_clock = sched_clock();
-
- perf_sample_event_took(finish_clock - start_clock);
- return ret;
-}
-
-static void
-armpmu_release_hardware(struct arm_pmu *armpmu)
-{
- armpmu->free_irq(armpmu);
-}
-
-static int
-armpmu_reserve_hardware(struct arm_pmu *armpmu)
-{
- int err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
- if (err) {
- armpmu_release_hardware(armpmu);
- return err;
- }
-
- return 0;
-}
-
-static void
-hw_perf_event_destroy(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- atomic_t *active_events = &armpmu->active_events;
- struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
-
- if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
- armpmu_release_hardware(armpmu);
- mutex_unlock(pmu_reserve_mutex);
- }
-}
-
-static int
-event_requires_mode_exclusion(struct perf_event_attr *attr)
-{
- return attr->exclude_idle || attr->exclude_user ||
- attr->exclude_kernel || attr->exclude_hv;
-}
-
-static int
-__hw_perf_event_init(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
- int mapping;
-
- mapping = armpmu->map_event(event);
-
- if (mapping < 0) {
- pr_debug("event %x:%llx not supported\n", event->attr.type,
- event->attr.config);
- return mapping;
- }
-
- /*
- * We don't assign an index until we actually place the event onto
- * hardware. Use -1 to signify that we haven't decided where to put it
- * yet. For SMP systems, each core has it's own PMU so we can't do any
- * clever allocation or constraints checking at this point.
- */
- hwc->idx = -1;
- hwc->config_base = 0;
- hwc->config = 0;
- hwc->event_base = 0;
-
- /*
- * Check whether we need to exclude the counter from certain modes.
- */
- if ((!armpmu->set_event_filter ||
- armpmu->set_event_filter(hwc, &event->attr)) &&
- event_requires_mode_exclusion(&event->attr)) {
- pr_debug("ARM performance counters do not support "
- "mode exclusion\n");
- return -EOPNOTSUPP;
- }
-
- /*
- * Store the event encoding into the config_base field.
- */
- hwc->config_base |= (unsigned long)mapping;
-
- if (!is_sampling_event(event)) {
- /*
- * For non-sampling runs, limit the sample_period to half
- * of the counter width. That way, the new counter value
- * is far less likely to overtake the previous one unless
- * you have some serious IRQ latency issues.
- */
- hwc->sample_period = armpmu->max_period >> 1;
- hwc->last_period = hwc->sample_period;
- local64_set(&hwc->period_left, hwc->sample_period);
- }
-
- if (event->group_leader != event) {
- if (validate_group(event) != 0)
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int armpmu_event_init(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- int err = 0;
- atomic_t *active_events = &armpmu->active_events;
-
- /*
- * Reject CPU-affine events for CPUs that are of a different class to
- * that which this PMU handles. Process-following events (where
- * event->cpu == -1) can be migrated between CPUs, and thus we have to
- * reject them later (in armpmu_add) if they're scheduled on a
- * different class of CPU.
- */
- if (event->cpu != -1 &&
- !cpumask_test_cpu(event->cpu, &armpmu->supported_cpus))
- return -ENOENT;
-
- /* does not support taken branch sampling */
- if (has_branch_stack(event))
- return -EOPNOTSUPP;
-
- if (armpmu->map_event(event) == -ENOENT)
- return -ENOENT;
-
- event->destroy = hw_perf_event_destroy;
-
- if (!atomic_inc_not_zero(active_events)) {
- mutex_lock(&armpmu->reserve_mutex);
- if (atomic_read(active_events) == 0)
- err = armpmu_reserve_hardware(armpmu);
-
- if (!err)
- atomic_inc(active_events);
- mutex_unlock(&armpmu->reserve_mutex);
- }
-
- if (err)
- return err;
-
- err = __hw_perf_event_init(event);
- if (err)
- hw_perf_event_destroy(event);
-
- return err;
-}
-
-static void armpmu_enable(struct pmu *pmu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
- struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
- int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
-
- /* For task-bound events we may be called on other CPUs */
- if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
- return;
-
- if (enabled)
- armpmu->start(armpmu);
-}
-
-static void armpmu_disable(struct pmu *pmu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
-
- /* For task-bound events we may be called on other CPUs */
- if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
- return;
-
- armpmu->stop(armpmu);
-}
-
-/*
- * In heterogeneous systems, events are specific to a particular
- * microarchitecture, and aren't suitable for another. Thus, only match CPUs of
- * the same microarchitecture.
- */
-static int armpmu_filter_match(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- unsigned int cpu = smp_processor_id();
- return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
-}
-
-static void armpmu_init(struct arm_pmu *armpmu)
-{
- atomic_set(&armpmu->active_events, 0);
- mutex_init(&armpmu->reserve_mutex);
-
- armpmu->pmu = (struct pmu) {
- .pmu_enable = armpmu_enable,
- .pmu_disable = armpmu_disable,
- .event_init = armpmu_event_init,
- .add = armpmu_add,
- .del = armpmu_del,
- .start = armpmu_start,
- .stop = armpmu_stop,
- .read = armpmu_read,
- .filter_match = armpmu_filter_match,
- };
-}
-
-int armpmu_register(struct arm_pmu *armpmu, int type)
-{
- armpmu_init(armpmu);
- pr_info("enabled with %s PMU driver, %d counters available\n",
- armpmu->name, armpmu->num_events);
- return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
-}
-
-/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *__oprofile_cpu_pmu;
-
-/*
- * Despite the names, these two functions are CPU-specific and are used
- * by the OProfile/perf code.
- */
-const char *perf_pmu_name(void)
-{
- if (!__oprofile_cpu_pmu)
- return NULL;
-
- return __oprofile_cpu_pmu->name;
-}
-EXPORT_SYMBOL_GPL(perf_pmu_name);
-
-int perf_num_counters(void)
-{
- int max_events = 0;
-
- if (__oprofile_cpu_pmu != NULL)
- max_events = __oprofile_cpu_pmu->num_events;
-
- return max_events;
-}
-EXPORT_SYMBOL_GPL(perf_num_counters);
-
-static void cpu_pmu_enable_percpu_irq(void *data)
-{
- int irq = *(int *)data;
-
- enable_percpu_irq(irq, IRQ_TYPE_NONE);
-}
-
-static void cpu_pmu_disable_percpu_irq(void *data)
-{
- int irq = *(int *)data;
-
- disable_percpu_irq(irq);
-}
-
-static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
-{
- int i, irq, irqs;
- struct platform_device *pmu_device = cpu_pmu->plat_device;
- struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
-
- irqs = min(pmu_device->num_resources, num_possible_cpus());
-
- irq = platform_get_irq(pmu_device, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
- on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
- free_percpu_irq(irq, &hw_events->percpu_pmu);
- } else {
- for (i = 0; i < irqs; ++i) {
- int cpu = i;
-
- if (cpu_pmu->irq_affinity)
- cpu = cpu_pmu->irq_affinity[i];
-
- if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
- continue;
- irq = platform_get_irq(pmu_device, i);
- if (irq >= 0)
- free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
- }
- }
-}
-
-static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
-{
- int i, err, irq, irqs;
- struct platform_device *pmu_device = cpu_pmu->plat_device;
- struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
-
- if (!pmu_device)
- return -ENODEV;
-
- irqs = min(pmu_device->num_resources, num_possible_cpus());
- if (irqs < 1) {
- pr_warn_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
- return 0;
- }
-
- irq = platform_get_irq(pmu_device, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
- err = request_percpu_irq(irq, handler, "arm-pmu",
- &hw_events->percpu_pmu);
- if (err) {
- pr_err("unable to request IRQ%d for ARM PMU counters\n",
- irq);
- return err;
- }
- on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
- } else {
- for (i = 0; i < irqs; ++i) {
- int cpu = i;
-
- err = 0;
- irq = platform_get_irq(pmu_device, i);
- if (irq < 0)
- continue;
-
- if (cpu_pmu->irq_affinity)
- cpu = cpu_pmu->irq_affinity[i];
-
- /*
- * If we have a single PMU interrupt that we can't shift,
- * assume that we're running on a uniprocessor machine and
- * continue. Otherwise, continue without this interrupt.
- */
- if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
- pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
- irq, cpu);
- continue;
- }
-
- err = request_irq(irq, handler,
- IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
- per_cpu_ptr(&hw_events->percpu_pmu, cpu));
- if (err) {
- pr_err("unable to request IRQ%d for ARM PMU counters\n",
- irq);
- return err;
- }
-
- cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
- }
- }
-
- return 0;
-}
-
-/*
- * PMU hardware loses all context when a CPU goes offline.
- * When a CPU is hotplugged back in, since some hardware registers are
- * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
- * junk values out of them.
- */
-static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
- void *hcpu)
-{
- int cpu = (unsigned long)hcpu;
- struct arm_pmu *pmu = container_of(b, struct arm_pmu, hotplug_nb);
-
- if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
- return NOTIFY_DONE;
-
- if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
- return NOTIFY_DONE;
-
- if (pmu->reset)
- pmu->reset(pmu);
- else
- return NOTIFY_DONE;
-
- return NOTIFY_OK;
-}
-
-static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
-{
- int err;
- int cpu;
- struct pmu_hw_events __percpu *cpu_hw_events;
-
- cpu_hw_events = alloc_percpu(struct pmu_hw_events);
- if (!cpu_hw_events)
- return -ENOMEM;
-
- cpu_pmu->hotplug_nb.notifier_call = cpu_pmu_notify;
- err = register_cpu_notifier(&cpu_pmu->hotplug_nb);
- if (err)
- goto out_hw_events;
-
- for_each_possible_cpu(cpu) {
- struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
- raw_spin_lock_init(&events->pmu_lock);
- events->percpu_pmu = cpu_pmu;
- }
-
- cpu_pmu->hw_events = cpu_hw_events;
- cpu_pmu->request_irq = cpu_pmu_request_irq;
- cpu_pmu->free_irq = cpu_pmu_free_irq;
-
- /* Ensure the PMU has sane values out of reset. */
- if (cpu_pmu->reset)
- on_each_cpu_mask(&cpu_pmu->supported_cpus, cpu_pmu->reset,
- cpu_pmu, 1);
-
- /* If no interrupts available, set the corresponding capability flag */
- if (!platform_get_irq(cpu_pmu->plat_device, 0))
- cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
-
- return 0;
-
-out_hw_events:
- free_percpu(cpu_hw_events);
- return err;
-}
-
-static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
-{
- unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
- free_percpu(cpu_pmu->hw_events);
-}
-
-/*
- * CPU PMU identification and probing.
- */
-static int probe_current_pmu(struct arm_pmu *pmu,
- const struct pmu_probe_info *info)
-{
- int cpu = get_cpu();
- unsigned int cpuid = read_cpuid_id();
- int ret = -ENODEV;
-
- pr_info("probing PMU on CPU %d\n", cpu);
-
- for (; info->init != NULL; info++) {
- if ((cpuid & info->mask) != info->cpuid)
- continue;
- ret = info->init(pmu);
- break;
- }
-
- put_cpu();
- return ret;
-}
-
-static int of_pmu_irq_cfg(struct arm_pmu *pmu)
-{
- int i, irq, *irqs;
- struct platform_device *pdev = pmu->plat_device;
-
- /* Don't bother with PPIs; they're already affine */
- irq = platform_get_irq(pdev, 0);
- if (irq >= 0 && irq_is_percpu(irq))
- return 0;
-
- irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
- if (!irqs)
- return -ENOMEM;
-
- for (i = 0; i < pdev->num_resources; ++i) {
- struct device_node *dn;
- int cpu;
-
- dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity",
- i);
- if (!dn) {
- pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
- of_node_full_name(pdev->dev.of_node), i);
- break;
- }
-
- for_each_possible_cpu(cpu)
- if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
- break;
-
- if (cpu >= nr_cpu_ids) {
- pr_warn("Failed to find logical CPU for %s\n",
- dn->name);
- of_node_put(dn);
- break;
- }
- of_node_put(dn);
-
- irqs[i] = cpu;
- cpumask_set_cpu(cpu, &pmu->supported_cpus);
- }
-
- if (i == pdev->num_resources) {
- pmu->irq_affinity = irqs;
- } else {
- kfree(irqs);
- cpumask_setall(&pmu->supported_cpus);
- }
-
- return 0;
-}
-
-int arm_pmu_device_probe(struct platform_device *pdev,
- const struct of_device_id *of_table,
- const struct pmu_probe_info *probe_table)
-{
- const struct of_device_id *of_id;
- const int (*init_fn)(struct arm_pmu *);
- struct device_node *node = pdev->dev.of_node;
- struct arm_pmu *pmu;
- int ret = -ENODEV;
-
- pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
- if (!pmu) {
- pr_info("failed to allocate PMU device!\n");
- return -ENOMEM;
- }
-
- if (!__oprofile_cpu_pmu)
- __oprofile_cpu_pmu = pmu;
-
- pmu->plat_device = pdev;
-
- if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
- init_fn = of_id->data;
-
- ret = of_pmu_irq_cfg(pmu);
- if (!ret)
- ret = init_fn(pmu);
- } else {
- ret = probe_current_pmu(pmu, probe_table);
- cpumask_setall(&pmu->supported_cpus);
- }
-
- if (ret) {
- pr_info("failed to probe PMU!\n");
- goto out_free;
- }
-
- ret = cpu_pmu_init(pmu);
- if (ret)
- goto out_free;
-
- ret = armpmu_register(pmu, -1);
- if (ret)
- goto out_destroy;
-
- return 0;
-
-out_destroy:
- cpu_pmu_destroy(pmu);
-out_free:
- pr_info("failed to register PMU devices!\n");
- kfree(pmu);
- return ret;
-}
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 09f83e414a72..09413e7b49aa 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -34,9 +34,9 @@
#include <asm/cputype.h>
#include <asm/irq_regs.h>
-#include <asm/pmu.h>
#include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
enum armv6_perf_types {
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f9b37f876e20..126dc679b230 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -21,11 +21,11 @@
#include <asm/cp15.h>
#include <asm/cputype.h>
#include <asm/irq_regs.h>
-#include <asm/pmu.h>
#include <asm/vfp.h>
#include "../vfp/vfpinstr.h"
#include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
/*
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 304d056d5b25..aa0499e2eef7 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -16,9 +16,9 @@
#include <asm/cputype.h>
#include <asm/irq_regs.h>
-#include <asm/pmu.h>
#include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
enum xscale_perf_types {
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f192a2a41719..a3089bacb8d8 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -91,13 +91,6 @@ void arch_cpu_idle_exit(void)
ledtrig_cpu(CPU_LED_IDLE_END);
}
-#ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead(void)
-{
- cpu_die();
-}
-#endif
-
void __show_regs(struct pt_regs *regs)
{
unsigned long flags;
@@ -129,12 +122,36 @@ void __show_regs(struct pt_regs *regs)
buf[4] = '\0';
#ifndef CONFIG_CPU_V7M
- printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n",
- buf, interrupts_enabled(regs) ? "n" : "ff",
- fast_interrupts_enabled(regs) ? "n" : "ff",
- processor_modes[processor_mode(regs)],
- isa_modes[isa_mode(regs)],
- get_fs() == get_ds() ? "kernel" : "user");
+ {
+ unsigned int domain = get_domain();
+ const char *segment;
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+ /*
+ * Get the domain register for the parent context. In user
+ * mode, we don't save the DACR, so lets use what it should
+ * be. For other modes, we place it after the pt_regs struct.
+ */
+ if (user_mode(regs))
+ domain = DACR_UACCESS_ENABLE;
+ else
+ domain = *(unsigned int *)(regs + 1);
+#endif
+
+ if ((domain & domain_mask(DOMAIN_USER)) ==
+ domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+ segment = "none";
+ else if (get_fs() == get_ds())
+ segment = "kernel";
+ else
+ segment = "user";
+
+ printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n",
+ buf, interrupts_enabled(regs) ? "n" : "ff",
+ fast_interrupts_enabled(regs) ? "n" : "ff",
+ processor_modes[processor_mode(regs)],
+ isa_modes[isa_mode(regs)], segment);
+ }
#else
printk("xPSR: %08lx\n", regs->ARM_cpsr);
#endif
@@ -146,10 +163,9 @@ void __show_regs(struct pt_regs *regs)
buf[0] = '\0';
#ifdef CONFIG_CPU_CP15_MMU
{
- unsigned int transbase, dac;
+ unsigned int transbase, dac = get_domain();
asm("mrc p15, 0, %0, c2, c0\n\t"
- "mrc p15, 0, %1, c3, c0\n"
- : "=r" (transbase), "=r" (dac));
+ : "=r" (transbase));
snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x",
transbase, dac);
}
@@ -210,6 +226,14 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
+ /*
+ * Copy the initial value of the domain access control register
+ * from the current thread: thread->addr_limit will have been
+ * copied from the current thread via setup_thread_stack() in
+ * kernel/fork.c
+ */
+ thread->cpu_domain = get_domain();
+
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->ARM_r0 = 0;
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
deleted file mode 100644
index 2e6024334790..000000000000
--- a/arch/arm/kernel/psci.c
+++ /dev/null
@@ -1,299 +0,0 @@
-/*
- * 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.
- *
- * Copyright (C) 2012 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#define pr_fmt(fmt) "psci: " fmt
-
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/reboot.h>
-#include <linux/pm.h>
-#include <uapi/linux/psci.h>
-
-#include <asm/compiler.h>
-#include <asm/errno.h>
-#include <asm/psci.h>
-#include <asm/system_misc.h>
-
-struct psci_operations psci_ops;
-
-static int (*invoke_psci_fn)(u32, u32, u32, u32);
-typedef int (*psci_initcall_t)(const struct device_node *);
-
-asmlinkage int __invoke_psci_fn_hvc(u32, u32, u32, u32);
-asmlinkage int __invoke_psci_fn_smc(u32, u32, u32, u32);
-
-enum psci_function {
- PSCI_FN_CPU_SUSPEND,
- PSCI_FN_CPU_ON,
- PSCI_FN_CPU_OFF,
- PSCI_FN_MIGRATE,
- PSCI_FN_AFFINITY_INFO,
- PSCI_FN_MIGRATE_INFO_TYPE,
- PSCI_FN_MAX,
-};
-
-static u32 psci_function_id[PSCI_FN_MAX];
-
-static int psci_to_linux_errno(int errno)
-{
- switch (errno) {
- case PSCI_RET_SUCCESS:
- return 0;
- case PSCI_RET_NOT_SUPPORTED:
- return -EOPNOTSUPP;
- case PSCI_RET_INVALID_PARAMS:
- return -EINVAL;
- case PSCI_RET_DENIED:
- return -EPERM;
- };
-
- return -EINVAL;
-}
-
-static u32 psci_power_state_pack(struct psci_power_state state)
-{
- return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
- & PSCI_0_2_POWER_STATE_ID_MASK) |
- ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
- & PSCI_0_2_POWER_STATE_TYPE_MASK) |
- ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
- & PSCI_0_2_POWER_STATE_AFFL_MASK);
-}
-
-static int psci_get_version(void)
-{
- int err;
-
- err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
- return err;
-}
-
-static int psci_cpu_suspend(struct psci_power_state state,
- unsigned long entry_point)
-{
- int err;
- u32 fn, power_state;
-
- fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
- power_state = psci_power_state_pack(state);
- err = invoke_psci_fn(fn, power_state, entry_point, 0);
- return psci_to_linux_errno(err);
-}
-
-static int psci_cpu_off(struct psci_power_state state)
-{
- int err;
- u32 fn, power_state;
-
- fn = psci_function_id[PSCI_FN_CPU_OFF];
- power_state = psci_power_state_pack(state);
- err = invoke_psci_fn(fn, power_state, 0, 0);
- return psci_to_linux_errno(err);
-}
-
-static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
-{
- int err;
- u32 fn;
-
- fn = psci_function_id[PSCI_FN_CPU_ON];
- err = invoke_psci_fn(fn, cpuid, entry_point, 0);
- return psci_to_linux_errno(err);
-}
-
-static int psci_migrate(unsigned long cpuid)
-{
- int err;
- u32 fn;
-
- fn = psci_function_id[PSCI_FN_MIGRATE];
- err = invoke_psci_fn(fn, cpuid, 0, 0);
- return psci_to_linux_errno(err);
-}
-
-static int psci_affinity_info(unsigned long target_affinity,
- unsigned long lowest_affinity_level)
-{
- int err;
- u32 fn;
-
- fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
- err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
- return err;
-}
-
-static int psci_migrate_info_type(void)
-{
- int err;
- u32 fn;
-
- fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
- err = invoke_psci_fn(fn, 0, 0, 0);
- return err;
-}
-
-static int get_set_conduit_method(struct device_node *np)
-{
- const char *method;
-
- pr_info("probing for conduit method from DT.\n");
-
- if (of_property_read_string(np, "method", &method)) {
- pr_warn("missing \"method\" property\n");
- return -ENXIO;
- }
-
- if (!strcmp("hvc", method)) {
- invoke_psci_fn = __invoke_psci_fn_hvc;
- } else if (!strcmp("smc", method)) {
- invoke_psci_fn = __invoke_psci_fn_smc;
- } else {
- pr_warn("invalid \"method\" property: %s\n", method);
- return -EINVAL;
- }
- return 0;
-}
-
-static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
-{
- invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
-}
-
-static void psci_sys_poweroff(void)
-{
- invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
-}
-
-/*
- * PSCI Function IDs for v0.2+ are well defined so use
- * standard values.
- */
-static int psci_0_2_init(struct device_node *np)
-{
- int err, ver;
-
- err = get_set_conduit_method(np);
-
- if (err)
- goto out_put_node;
-
- ver = psci_get_version();
-
- if (ver == PSCI_RET_NOT_SUPPORTED) {
- /* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
- pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
- err = -EOPNOTSUPP;
- goto out_put_node;
- } else {
- pr_info("PSCIv%d.%d detected in firmware.\n",
- PSCI_VERSION_MAJOR(ver),
- PSCI_VERSION_MINOR(ver));
-
- if (PSCI_VERSION_MAJOR(ver) == 0 &&
- PSCI_VERSION_MINOR(ver) < 2) {
- err = -EINVAL;
- pr_err("Conflicting PSCI version detected.\n");
- goto out_put_node;
- }
- }
-
- pr_info("Using standard PSCI v0.2 function IDs\n");
- psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND;
- psci_ops.cpu_suspend = psci_cpu_suspend;
-
- psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
- psci_ops.cpu_off = psci_cpu_off;
-
- psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON;
- psci_ops.cpu_on = psci_cpu_on;
-
- psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE;
- psci_ops.migrate = psci_migrate;
-
- psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO;
- psci_ops.affinity_info = psci_affinity_info;
-
- psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
- PSCI_0_2_FN_MIGRATE_INFO_TYPE;
- psci_ops.migrate_info_type = psci_migrate_info_type;
-
- arm_pm_restart = psci_sys_reset;
-
- pm_power_off = psci_sys_poweroff;
-
-out_put_node:
- of_node_put(np);
- return err;
-}
-
-/*
- * PSCI < v0.2 get PSCI Function IDs via DT.
- */
-static int psci_0_1_init(struct device_node *np)
-{
- u32 id;
- int err;
-
- err = get_set_conduit_method(np);
-
- if (err)
- goto out_put_node;
-
- pr_info("Using PSCI v0.1 Function IDs from DT\n");
-
- if (!of_property_read_u32(np, "cpu_suspend", &id)) {
- psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
- psci_ops.cpu_suspend = psci_cpu_suspend;
- }
-
- if (!of_property_read_u32(np, "cpu_off", &id)) {
- psci_function_id[PSCI_FN_CPU_OFF] = id;
- psci_ops.cpu_off = psci_cpu_off;
- }
-
- if (!of_property_read_u32(np, "cpu_on", &id)) {
- psci_function_id[PSCI_FN_CPU_ON] = id;
- psci_ops.cpu_on = psci_cpu_on;
- }
-
- if (!of_property_read_u32(np, "migrate", &id)) {
- psci_function_id[PSCI_FN_MIGRATE] = id;
- psci_ops.migrate = psci_migrate;
- }
-
-out_put_node:
- of_node_put(np);
- return err;
-}
-
-static const struct of_device_id const psci_of_match[] __initconst = {
- { .compatible = "arm,psci", .data = psci_0_1_init},
- { .compatible = "arm,psci-0.2", .data = psci_0_2_init},
- {},
-};
-
-int __init psci_init(void)
-{
- struct device_node *np;
- const struct of_device_id *matched_np;
- psci_initcall_t init_fn;
-
- np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
- if (!np)
- return -ENODEV;
-
- init_fn = (psci_initcall_t)matched_np->data;
- return init_fn(np);
-}
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
index 28a1db4da704..61c04b02faeb 100644
--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@@ -17,6 +17,8 @@
#include <linux/smp.h>
#include <linux/of.h>
#include <linux/delay.h>
+#include <linux/psci.h>
+
#include <uapi/linux/psci.h>
#include <asm/psci.h>
@@ -51,22 +53,34 @@ static int psci_boot_secondary(unsigned int cpu, struct task_struct *idle)
{
if (psci_ops.cpu_on)
return psci_ops.cpu_on(cpu_logical_map(cpu),
- __pa(secondary_startup));
+ virt_to_idmap(&secondary_startup));
return -ENODEV;
}
#ifdef CONFIG_HOTPLUG_CPU
+int psci_cpu_disable(unsigned int cpu)
+{
+ /* Fail early if we don't have CPU_OFF support */
+ if (!psci_ops.cpu_off)
+ return -EOPNOTSUPP;
+
+ /* Trusted OS will deny CPU_OFF */
+ if (psci_tos_resident_on(cpu))
+ return -EPERM;
+
+ return 0;
+}
+
void __ref psci_cpu_die(unsigned int cpu)
{
- const struct psci_power_state ps = {
- .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
- };
+ u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
+ PSCI_0_2_POWER_STATE_TYPE_SHIFT;
- if (psci_ops.cpu_off)
- psci_ops.cpu_off(ps);
+ if (psci_ops.cpu_off)
+ psci_ops.cpu_off(state);
- /* We should never return */
- panic("psci: cpu %d failed to shutdown\n", cpu);
+ /* We should never return */
+ panic("psci: cpu %d failed to shutdown\n", cpu);
}
int __ref psci_cpu_kill(unsigned int cpu)
@@ -109,6 +123,7 @@ bool __init psci_smp_available(void)
struct smp_operations __initdata psci_smp_ops = {
.smp_boot_secondary = psci_boot_secondary,
#ifdef CONFIG_HOTPLUG_CPU
+ .cpu_disable = psci_cpu_disable,
.cpu_die = psci_cpu_die,
.cpu_kill = psci_cpu_kill,
#endif
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 36c18b73c1f4..20edd349d379 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -31,12 +31,14 @@
#include <linux/bug.h>
#include <linux/compiler.h>
#include <linux/sort.h>
+#include <linux/psci.h>
#include <asm/unified.h>
#include <asm/cp15.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/elf.h>
+#include <asm/fixmap.h>
#include <asm/procinfo.h>
#include <asm/psci.h>
#include <asm/sections.h>
@@ -954,6 +956,9 @@ void __init setup_arch(char **cmdline_p)
strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = cmd_line;
+ if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM))
+ early_fixmap_init();
+
parse_early_param();
#ifdef CONFIG_MMU
@@ -972,7 +977,7 @@ void __init setup_arch(char **cmdline_p)
unflatten_device_tree();
arm_dt_init_cpu_maps();
- psci_init();
+ psci_dt_init();
xen_early_init();
#ifdef CONFIG_SMP
if (is_smp()) {
@@ -1015,7 +1020,7 @@ static int __init topology_init(void)
for_each_possible_cpu(cpu) {
struct cpuinfo_arm *cpuinfo = &per_cpu(cpu_data, cpu);
- cpuinfo->cpu.hotpluggable = 1;
+ cpuinfo->cpu.hotpluggable = platform_can_hotplug_cpu(cpu);
register_cpu(&cpuinfo->cpu, cpu);
}
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 423663e23791..b6cda06b455f 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -562,6 +562,12 @@ static int do_signal(struct pt_regs *regs, int syscall)
asmlinkage int
do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
{
+ /*
+ * The assembly code enters us with IRQs off, but it hasn't
+ * informed the tracing code of that for efficiency reasons.
+ * Update the trace code with the current status.
+ */
+ trace_hardirqs_off();
do {
if (likely(thread_flags & _TIF_NEED_RESCHED)) {
schedule();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 3d6b7821cff8..ba0063c539c3 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -175,13 +175,26 @@ static int platform_cpu_disable(unsigned int cpu)
if (smp_ops.cpu_disable)
return smp_ops.cpu_disable(cpu);
+ return 0;
+}
+
+int platform_can_hotplug_cpu(unsigned int cpu)
+{
+ /* cpu_die must be specified to support hotplug */
+ if (!smp_ops.cpu_die)
+ return 0;
+
+ if (smp_ops.cpu_can_disable)
+ return smp_ops.cpu_can_disable(cpu);
+
/*
* By default, allow disabling all CPUs except the first one,
* since this is special on a lot of platforms, e.g. because
* of clock tick interrupts.
*/
- return cpu == 0 ? -EPERM : 0;
+ return cpu != 0;
}
+
/*
* __cpu_disable runs on the processor to be shutdown.
*/
@@ -253,7 +266,7 @@ void __cpu_die(unsigned int cpu)
* of the other hotplug-cpu capable cores, so presumably coming
* out of idle fixes this.
*/
-void __ref cpu_die(void)
+void arch_cpu_idle_dead(void)
{
unsigned int cpu = smp_processor_id();
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 1361756782c7..5b26e7efa9ea 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -141,11 +141,14 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
while (1) {
unsigned long temp;
+ unsigned int __ua_flags;
+ __ua_flags = uaccess_save_and_enable();
if (type == TYPE_SWPB)
__user_swpb_asm(*data, address, res, temp);
else
__user_swp_asm(*data, address, res, temp);
+ uaccess_restore(__ua_flags);
if (likely(res != -EAGAIN) || signal_pending(current))
break;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d358226236f2..969f9d9e665f 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -870,7 +870,6 @@ void __init early_trap_init(void *vectors_base)
kuser_init(vectors_base);
flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
- modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
#else /* ifndef CONFIG_CPU_V7M */
/*
* on V7-M there is no need to copy the vector table to a dedicated
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-16 17:42:07 +0100