summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arc/include/asm/delay.h9
-rw-r--r--arch/arc/include/asm/pgtable.h2
-rw-r--r--arch/arm64/boot/dts/arm/juno-r1.dts2
-rw-r--r--arch/arm64/boot/dts/arm/juno-r2.dts2
-rw-r--r--arch/arm64/boot/dts/arm/juno.dts2
-rw-r--r--arch/arm64/include/asm/cpufeature.h2
-rw-r--r--arch/arm64/include/asm/exec.h3
-rw-r--r--arch/arm64/include/asm/processor.h6
-rw-r--r--arch/arm64/kernel/cpufeature.c10
-rw-r--r--arch/arm64/kernel/process.c3
-rw-r--r--arch/arm64/kernel/suspend.c11
-rw-r--r--arch/arm64/kernel/traps.c3
-rw-r--r--arch/arm64/mm/fault.c15
-rw-r--r--arch/sparc/kernel/signal_32.c4
-rw-r--r--arch/sparc/mm/init_64.c71
-rw-r--r--arch/x86/events/core.c10
-rw-r--r--arch/x86/kernel/fpu/core.c16
17 files changed, 129 insertions, 42 deletions
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index 08e7e2a16..a36e86011 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -22,10 +22,11 @@
static inline void __delay(unsigned long loops)
{
__asm__ __volatile__(
- " lp 1f \n"
- " nop \n"
- "1: \n"
- : "+l"(loops));
+ " mov lp_count, %0 \n"
+ " lp 1f \n"
+ " nop \n"
+ "1: \n"
+ : : "r"(loops));
}
extern void __bad_udelay(void);
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 89eeb3720..e94ca72b9 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot)
-#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define pfn_pte(pfn, prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot))
/* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT)
diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts
index 123a58b29..f0b857d6d 100644
--- a/arch/arm64/boot/dts/arm/juno-r1.dts
+++ b/arch/arm64/boot/dts/arm/juno-r1.dts
@@ -76,7 +76,7 @@
compatible = "arm,idle-state";
arm,psci-suspend-param = <0x1010000>;
local-timer-stop;
- entry-latency-us = <300>;
+ entry-latency-us = <400>;
exit-latency-us = <1200>;
min-residency-us = <2500>;
};
diff --git a/arch/arm64/boot/dts/arm/juno-r2.dts b/arch/arm64/boot/dts/arm/juno-r2.dts
index 007be826e..26aaa6a76 100644
--- a/arch/arm64/boot/dts/arm/juno-r2.dts
+++ b/arch/arm64/boot/dts/arm/juno-r2.dts
@@ -76,7 +76,7 @@
compatible = "arm,idle-state";
arm,psci-suspend-param = <0x1010000>;
local-timer-stop;
- entry-latency-us = <300>;
+ entry-latency-us = <400>;
exit-latency-us = <1200>;
min-residency-us = <2500>;
};
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
index a7270eff6..6e154d948 100644
--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -76,7 +76,7 @@
compatible = "arm,idle-state";
arm,psci-suspend-param = <0x1010000>;
local-timer-stop;
- entry-latency-us = <300>;
+ entry-latency-us = <400>;
exit-latency-us = <1200>;
min-residency-us = <2500>;
};
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 7099f26e3..b96346b94 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -90,7 +90,7 @@ struct arm64_cpu_capabilities {
u16 capability;
int def_scope; /* default scope */
bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
- void (*enable)(void *); /* Called on all active CPUs */
+ int (*enable)(void *); /* Called on all active CPUs */
union {
struct { /* To be used for erratum handling only */
u32 midr_model;
diff --git a/arch/arm64/include/asm/exec.h b/arch/arm64/include/asm/exec.h
index db0563c23..f7865dd9d 100644
--- a/arch/arm64/include/asm/exec.h
+++ b/arch/arm64/include/asm/exec.h
@@ -18,6 +18,9 @@
#ifndef __ASM_EXEC_H
#define __ASM_EXEC_H
+#include <linux/sched.h>
+
extern unsigned long arch_align_stack(unsigned long sp);
+void uao_thread_switch(struct task_struct *next);
#endif /* __ASM_EXEC_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ace0a96e7..3be0ab013 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -190,8 +190,8 @@ static inline void spin_lock_prefetch(const void *ptr)
#endif
-void cpu_enable_pan(void *__unused);
-void cpu_enable_uao(void *__unused);
-void cpu_enable_cache_maint_trap(void *__unused);
+int cpu_enable_pan(void *__unused);
+int cpu_enable_uao(void *__unused);
+int cpu_enable_cache_maint_trap(void *__unused);
#endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 62272eac1..94a0330f7 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
#define pr_fmt(fmt) "CPU features: " fmt
#include <linux/bsearch.h>
+#include <linux/cpumask.h>
#include <linux/sort.h>
+#include <linux/stop_machine.h>
#include <linux/types.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
@@ -936,7 +938,13 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
{
for (; caps->matches; caps++)
if (caps->enable && cpus_have_cap(caps->capability))
- on_each_cpu(caps->enable, NULL, true);
+ /*
+ * Use stop_machine() as it schedules the work allowing
+ * us to modify PSTATE, instead of on_each_cpu() which
+ * uses an IPI, giving us a PSTATE that disappears when
+ * we return.
+ */
+ stop_machine(caps->enable, NULL, cpu_online_mask);
}
/*
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6cd261223..9cc866721 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -49,6 +49,7 @@
#include <asm/alternative.h>
#include <asm/compat.h>
#include <asm/cacheflush.h>
+#include <asm/exec.h>
#include <asm/fpsimd.h>
#include <asm/mmu_context.h>
#include <asm/processor.h>
@@ -303,7 +304,7 @@ static void tls_thread_switch(struct task_struct *next)
}
/* Restore the UAO state depending on next's addr_limit */
-static void uao_thread_switch(struct task_struct *next)
+void uao_thread_switch(struct task_struct *next)
{
if (IS_ENABLED(CONFIG_ARM64_UAO)) {
if (task_thread_info(next)->addr_limit == KERNEL_DS)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index b616e365c..23ddf5500 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,8 +1,11 @@
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/slab.h>
+#include <asm/alternative.h>
#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
+#include <asm/exec.h>
#include <asm/pgtable.h>
#include <asm/memory.h>
#include <asm/mmu_context.h>
@@ -48,6 +51,14 @@ void notrace __cpu_suspend_exit(void)
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
/*
+ * PSTATE was not saved over suspend/resume, re-enable any detected
+ * features that might not have been set correctly.
+ */
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+ CONFIG_ARM64_PAN));
+ uao_thread_switch(current);
+
+ /*
* Restore HW breakpoint registers to sane values
* before debug exceptions are possibly reenabled
* through local_dbg_restore.
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 771a01a7f..9595d3d9c 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -428,9 +428,10 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
}
-void cpu_enable_cache_maint_trap(void *__unused)
+int cpu_enable_cache_maint_trap(void *__unused)
{
config_sctlr_el1(SCTLR_EL1_UCI, 0);
+ return 0;
}
#define __user_cache_maint(insn, address, res) \
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 05d2bd776..67506c3c5 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -29,7 +29,9 @@
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
+#include <linux/preempt.h>
+#include <asm/bug.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
@@ -671,9 +673,17 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
NOKPROBE_SYMBOL(do_debug_exception);
#ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
{
+ /*
+ * We modify PSTATE. This won't work from irq context as the PSTATE
+ * is discarded once we return from the exception.
+ */
+ WARN_ON_ONCE(in_interrupt());
+
config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+ asm(SET_PSTATE_PAN(1));
+ return 0;
}
#endif /* CONFIG_ARM64_PAN */
@@ -684,8 +694,9 @@ void cpu_enable_pan(void *__unused)
* We need to enable the feature at runtime (instead of adding it to
* PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
*/
-void cpu_enable_uao(void *__unused)
+int cpu_enable_uao(void *__unused)
{
asm(SET_PSTATE_UAO(1));
+ return 0;
}
#endif /* CONFIG_ARM64_UAO */
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index c3c12efe0..9c0c8fd0b 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
- if (!invalid_frame_pointer(sf, sizeof(*sf)))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
goto segv_and_exit;
if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
@@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
synchronize_user_stack();
sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
- if (!invalid_frame_pointer(sf, sizeof(*sf)))
+ if (invalid_frame_pointer(sf, sizeof(*sf)))
goto segv;
if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 7ac6b62fb..05c770825 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -802,8 +802,10 @@ struct mdesc_mblock {
};
static struct mdesc_mblock *mblocks;
static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+ struct node_mem_mask *pnode_mask);
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
{
int i;
@@ -819,8 +821,11 @@ static unsigned long ra_to_pa(unsigned long addr)
return addr;
}
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
{
+ static bool search_mdesc = true;
+ static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+ static int last_index;
int i;
addr = ra_to_pa(addr);
@@ -830,13 +835,30 @@ static int find_node(unsigned long addr)
if ((addr & p->mask) == p->val)
return i;
}
- /* The following condition has been observed on LDOM guests.*/
- WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
- " rule. Some physical memory will be owned by node 0.");
- return 0;
+ /* The following condition has been observed on LDOM guests because
+ * node_masks only contains the best latency mask and value.
+ * LDOM guest's mdesc can contain a single latency group to
+ * cover multiple address range. Print warning message only if the
+ * address cannot be found in node_masks nor mdesc.
+ */
+ if ((search_mdesc) &&
+ ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+ /* find the available node in the mdesc */
+ last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+ numadbg("find_node: latency group for address 0x%lx is %d\n",
+ addr, last_index);
+ if ((last_index < 0) || (last_index >= num_node_masks)) {
+ /* WARN_ONCE() and use default group 0 */
+ WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+ search_mdesc = false;
+ last_index = 0;
+ }
+ }
+
+ return last_index;
}
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
{
*nid = find_node(start);
start += PAGE_SIZE;
@@ -1160,6 +1182,41 @@ int __node_distance(int from, int to)
return numa_latency[from][to];
}
+static int find_numa_node_for_addr(unsigned long pa,
+ struct node_mem_mask *pnode_mask)
+{
+ struct mdesc_handle *md = mdesc_grab();
+ u64 node, arc;
+ int i = 0;
+
+ node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+ if (node == MDESC_NODE_NULL)
+ goto out;
+
+ mdesc_for_each_node_by_name(md, node, "group") {
+ mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+ u64 target = mdesc_arc_target(md, arc);
+ struct mdesc_mlgroup *m = find_mlgroup(target);
+
+ if (!m)
+ continue;
+ if ((pa & m->mask) == m->match) {
+ if (pnode_mask) {
+ pnode_mask->mask = m->mask;
+ pnode_mask->val = m->match;
+ }
+ mdesc_release(md);
+ return i;
+ }
+ }
+ i++;
+ }
+
+out:
+ mdesc_release(md);
+ return -1;
+}
+
static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
{
int i;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d0efb5cb1..a4e070a51 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2344,7 +2344,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
frame.next_frame = 0;
frame.return_address = 0;
- if (!access_ok(VERIFY_READ, fp, 8))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
@@ -2354,9 +2354,6 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
if (bytes != 0)
break;
- if (!valid_user_frame(fp, sizeof(frame)))
- break;
-
perf_callchain_store(entry, cs_base + frame.return_address);
fp = compat_ptr(ss_base + frame.next_frame);
}
@@ -2405,7 +2402,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
frame.next_frame = NULL;
frame.return_address = 0;
- if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
@@ -2415,9 +2412,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
if (bytes != 0)
break;
- if (!valid_user_frame(fp, sizeof(frame)))
- break;
-
perf_callchain_store(entry, frame.return_address);
fp = (void __user *)frame.next_frame;
}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index c289e2f4a..3fc03a09a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -517,14 +517,14 @@ void fpu__clear(struct fpu *fpu)
{
WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
- fpu__drop(fpu);
-
- /*
- * Make sure fpstate is cleared and initialized.
- */
- if (static_cpu_has(X86_FEATURE_FPU)) {
- fpu__activate_curr(fpu);
- user_fpu_begin();
+ if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
+ /* FPU state will be reallocated lazily at the first use. */
+ fpu__drop(fpu);
+ } else {
+ if (!fpu->fpstate_active) {
+ fpu__activate_curr(fpu);
+ user_fpu_begin();
+ }
copy_init_fpstate_to_fpregs();
}
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-17 01:56:25 +0000