Commit f0915781 authored by Will Deacon's avatar Will Deacon

ARM: tlb: don't perform inner-shareable invalidation for local TLB ops

Inner-shareable TLB invalidation is typically more expensive than local
(non-shareable) invalidation, so performing the broadcasting for
local_flush_tlb_* operations is a waste of cycles and needlessly
clobbers entries in the TLBs of other CPUs.

This patch introduces __flush_tlb_* versions for many of the TLB
invalidation functions, which only respect inner-shareable variants of
the invalidation instructions when presented with the TLB_V7_UIS_FULL
flag. The local version is also inlined to prevent SMP_ON_UP kernels
from missing flushes, where the __flush variant would be called with
the UP flags.

This gains us around 0.5% in hackbench scores for a dual-core A15, but I
would expect this to improve as more cores (and clusters) are added to
the equation.
Reviewed-by: default avatarCatalin Marinas <catalin.marinas@arm.com>
Reported-by: default avatarAlbin Tonnerre <Albin.Tonnerre@arm.com>
Signed-off-by: default avatarWill Deacon <will.deacon@arm.com>
parent 792a843a
......@@ -319,6 +319,16 @@ extern struct cpu_tlb_fns cpu_tlb;
#define tlb_op(f, regs, arg) __tlb_op(f, "p15, 0, %0, " regs, arg)
#define tlb_l2_op(f, regs, arg) __tlb_op(f, "p15, 1, %0, " regs, arg)
static inline void __local_flush_tlb_all(void)
{
const int zero = 0;
const unsigned int __tlb_flag = __cpu_tlb_flags;
tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
}
static inline void local_flush_tlb_all(void)
{
const int zero = 0;
......@@ -327,10 +337,8 @@ static inline void local_flush_tlb_all(void)
if (tlb_flag(TLB_WB))
dsb();
tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
__local_flush_tlb_all();
tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero);
if (tlb_flag(TLB_BARRIER)) {
dsb();
......@@ -338,31 +346,69 @@ static inline void local_flush_tlb_all(void)
}
}
static inline void local_flush_tlb_mm(struct mm_struct *mm)
static inline void __flush_tlb_all(void)
{
const int zero = 0;
const int asid = ASID(mm);
const unsigned int __tlb_flag = __cpu_tlb_flags;
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_all();
tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
if (tlb_flag(TLB_BARRIER)) {
dsb();
isb();
}
}
static inline void __local_flush_tlb_mm(struct mm_struct *mm)
{
const int zero = 0;
const int asid = ASID(mm);
const unsigned int __tlb_flag = __cpu_tlb_flags;
if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
}
put_cpu();
}
tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
}
static inline void local_flush_tlb_mm(struct mm_struct *mm)
{
const int asid = ASID(mm);
const unsigned int __tlb_flag = __cpu_tlb_flags;
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_mm(mm);
tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid);
if (tlb_flag(TLB_BARRIER))
dsb();
}
static inline void __flush_tlb_mm(struct mm_struct *mm)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_mm(mm);
#ifdef CONFIG_ARM_ERRATA_720789
tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0);
#else
tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm));
#endif
if (tlb_flag(TLB_BARRIER))
......@@ -370,16 +416,13 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
}
static inline void
local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
{
const int zero = 0;
const unsigned int __tlb_flag = __cpu_tlb_flags;
uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
if (tlb_flag(TLB_WB))
dsb();
if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
......@@ -392,6 +435,36 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
}
static inline void
local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_page(vma, uaddr);
tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr);
if (tlb_flag(TLB_BARRIER))
dsb();
}
static inline void
__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_page(vma, uaddr);
#ifdef CONFIG_ARM_ERRATA_720789
tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
#else
......@@ -402,16 +475,11 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
dsb();
}
static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
static inline void __local_flush_tlb_kernel_page(unsigned long kaddr)
{
const int zero = 0;
const unsigned int __tlb_flag = __cpu_tlb_flags;
kaddr &= PAGE_MASK;
if (tlb_flag(TLB_WB))
dsb();
tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
......@@ -421,6 +489,36 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
}
static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
kaddr &= PAGE_MASK;
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_kernel_page(kaddr);
tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr);
if (tlb_flag(TLB_BARRIER)) {
dsb();
isb();
}
}
static inline void __flush_tlb_kernel_page(unsigned long kaddr)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
kaddr &= PAGE_MASK;
if (tlb_flag(TLB_WB))
dsb();
__local_flush_tlb_kernel_page(kaddr);
tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
if (tlb_flag(TLB_BARRIER)) {
......
......@@ -104,7 +104,7 @@ void flush_tlb_all(void)
if (tlb_ops_need_broadcast())
on_each_cpu(ipi_flush_tlb_all, NULL, 1);
else
local_flush_tlb_all();
__flush_tlb_all();
broadcast_tlb_a15_erratum();
}
......@@ -113,7 +113,7 @@ void flush_tlb_mm(struct mm_struct *mm)
if (tlb_ops_need_broadcast())
on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
else
local_flush_tlb_mm(mm);
__flush_tlb_mm(mm);
broadcast_tlb_mm_a15_erratum(mm);
}
......@@ -126,7 +126,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
&ta, 1);
} else
local_flush_tlb_page(vma, uaddr);
__flush_tlb_page(vma, uaddr);
broadcast_tlb_mm_a15_erratum(vma->vm_mm);
}
......@@ -137,7 +137,7 @@ void flush_tlb_kernel_page(unsigned long kaddr)
ta.ta_start = kaddr;
on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
} else
local_flush_tlb_kernel_page(kaddr);
__flush_tlb_kernel_page(kaddr);
broadcast_tlb_a15_erratum();
}
......
......@@ -162,10 +162,7 @@ static void flush_context(unsigned int cpu)
}
/* Queue a TLB invalidate and flush the I-cache if necessary. */
if (!tlb_ops_need_broadcast())
cpumask_set_cpu(cpu, &tlb_flush_pending);
else
cpumask_setall(&tlb_flush_pending);
cpumask_setall(&tlb_flush_pending);
if (icache_is_vivt_asid_tagged())
__flush_icache_all();
......@@ -245,8 +242,6 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
local_flush_bp_all();
local_flush_tlb_all();
if (erratum_a15_798181())
dummy_flush_tlb_a15_erratum();
}
atomic64_set(&per_cpu(active_asids, cpu), asid);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment