linux/arch/riscv/mm/tlbflush.c
Linus Torvalds 0bfbc914d9 RISC-V Patches for the 6.10 Merge Window, Part 1
* Support for byte/half-word compare-and-exchange, emulated via LR/SC
   loops.
 * Support for Rust.
 * Support for Zihintpause in hwprobe.
 * Support for the PR_RISCV_SET_ICACHE_FLUSH_CTX prctl().
 * Support for lockless lockrefs.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmZN/hcTHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYiVrGEACUT3gsbTx1q7fa11iQNxOjVkpl66Qn
 7+kI+V9xt5+GuH2EjJk6AsSNHPKeQ8totbSTA8AZjINFvgVjXslN+DPpcjCFKvnh
 NN5/Lyd64X0PZMsxGWlN9SHTFWf2b7lalCnY51BlX/IpBbHWc/no9XUsPSVixx6u
 9q+JoS3D1DDV92nGcA/UK9ICCsDcf4omWgZW7KbjnVWnuY9jt4ctTy11jtF2RM9R
 Z9KAWh0RqPzjz0vNbBBf9Iw7E4jt/Px6HDYPfZAiE2dVsCTHjdsC7TcGRYXzKt6F
 4q9zg8kzwvUG5GaBl7/XprXO1vaeOUmPcTVoE7qlRkSdkknRH/iBz1P4hk+r0fze
 f+h5ZUV/oJP7vDb+vHm/BExtGufgLuJ2oMA2Bp9qI17EMcMsGiRMt7DsBMEafWDk
 bNrFcJdqqYBz6HxfTwzNH5ErxfS/59PuwYl913BTSOH//raCZCFXOfyrSICH7qXd
 UFOLLmBpMuApLa8ayFeI9Mp3flWfbdQHR52zLRLiUvlpWNEDKrNQN417juVwTXF0
 DYkjJDhFPLfFOr/sJBboftOMOUdA9c/CJepY9o4kPvBXUvPtRHN1jdXDNSCVDZRb
 nErnsJ9rv0PzfxQU7Xjhd2QmCMeMlbCQDpXAKKETyyimpTbgF33rovN0i5ixX3m4
 KG6RvKDubOzZdA==
 =YLoD
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-6.10-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Add byte/half-word compare-and-exchange, emulated via LR/SC loops

 - Support for Rust

 - Support for Zihintpause in hwprobe

 - Add PR_RISCV_SET_ICACHE_FLUSH_CTX prctl()

 - Support lockless lockrefs

* tag 'riscv-for-linus-6.10-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (42 commits)
  riscv: defconfig: Enable CONFIG_CLK_SOPHGO_CV1800
  riscv: select ARCH_HAS_FAST_MULTIPLIER
  riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required
  riscv: Annotate pgtable_l{4,5}_enabled with __ro_after_init
  riscv: Remove redundant CONFIG_64BIT from pgtable_l{4,5}_enabled
  riscv: mm: Always use an ASID to flush mm contexts
  riscv: mm: Preserve global TLB entries when switching contexts
  riscv: mm: Make asid_bits a local variable
  riscv: mm: Use a fixed layout for the MM context ID
  riscv: mm: Introduce cntx2asid/cntx2version helper macros
  riscv: Avoid TLB flush loops when affected by SiFive CIP-1200
  riscv: Apply SiFive CIP-1200 workaround to single-ASID sfence.vma
  riscv: mm: Combine the SMP and UP TLB flush code
  riscv: Only send remote fences when some other CPU is online
  riscv: mm: Broadcast kernel TLB flushes only when needed
  riscv: Use IPIs for remote cache/TLB flushes by default
  riscv: Factor out page table TLB synchronization
  riscv: Flush the instruction cache during SMP bringup
  riscv: hwprobe: export Zihintpause ISA extension
  riscv: misaligned: remove CONFIG_RISCV_M_MODE specific code
  ...
2024-05-22 09:56:00 -07:00

206 lines
5.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>
#include <asm/sbi.h>
#include <asm/mmu_context.h>
/*
* Flush entire TLB if number of entries to be flushed is greater
* than the threshold below.
*/
unsigned long tlb_flush_all_threshold __read_mostly = 64;
static void local_flush_tlb_range_threshold_asid(unsigned long start,
unsigned long size,
unsigned long stride,
unsigned long asid)
{
unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride);
int i;
if (nr_ptes_in_range > tlb_flush_all_threshold) {
local_flush_tlb_all_asid(asid);
return;
}
for (i = 0; i < nr_ptes_in_range; ++i) {
local_flush_tlb_page_asid(start, asid);
start += stride;
}
}
static inline void local_flush_tlb_range_asid(unsigned long start,
unsigned long size, unsigned long stride, unsigned long asid)
{
if (size <= stride)
local_flush_tlb_page_asid(start, asid);
else if (size == FLUSH_TLB_MAX_SIZE)
local_flush_tlb_all_asid(asid);
else
local_flush_tlb_range_threshold_asid(start, size, stride, asid);
}
/* Flush a range of kernel pages without broadcasting */
void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
}
static void __ipi_flush_tlb_all(void *info)
{
local_flush_tlb_all();
}
void flush_tlb_all(void)
{
if (num_online_cpus() < 2)
local_flush_tlb_all();
else if (riscv_use_sbi_for_rfence())
sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
else
on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
}
struct flush_tlb_range_data {
unsigned long asid;
unsigned long start;
unsigned long size;
unsigned long stride;
};
static void __ipi_flush_tlb_range_asid(void *info)
{
struct flush_tlb_range_data *d = info;
local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
}
static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
unsigned long start, unsigned long size,
unsigned long stride)
{
unsigned int cpu;
if (cpumask_empty(cmask))
return;
cpu = get_cpu();
/* Check if the TLB flush needs to be sent to other CPUs. */
if (cpumask_any_but(cmask, cpu) >= nr_cpu_ids) {
local_flush_tlb_range_asid(start, size, stride, asid);
} else if (riscv_use_sbi_for_rfence()) {
sbi_remote_sfence_vma_asid(cmask, start, size, asid);
} else {
struct flush_tlb_range_data ftd;
ftd.asid = asid;
ftd.start = start;
ftd.size = size;
ftd.stride = stride;
on_each_cpu_mask(cmask, __ipi_flush_tlb_range_asid, &ftd, 1);
}
put_cpu();
}
static inline unsigned long get_mm_asid(struct mm_struct *mm)
{
return cntx2asid(atomic_long_read(&mm->context.id));
}
void flush_tlb_mm(struct mm_struct *mm)
{
__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
}
void flush_tlb_mm_range(struct mm_struct *mm,
unsigned long start, unsigned long end,
unsigned int page_size)
{
__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
start, end - start, page_size);
}
void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
{
__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
addr, PAGE_SIZE, PAGE_SIZE);
}
void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
unsigned long stride_size;
if (!is_vm_hugetlb_page(vma)) {
stride_size = PAGE_SIZE;
} else {
stride_size = huge_page_size(hstate_vma(vma));
/*
* As stated in the privileged specification, every PTE in a
* NAPOT region must be invalidated, so reset the stride in that
* case.
*/
if (has_svnapot()) {
if (stride_size >= PGDIR_SIZE)
stride_size = PGDIR_SIZE;
else if (stride_size >= P4D_SIZE)
stride_size = P4D_SIZE;
else if (stride_size >= PUD_SIZE)
stride_size = PUD_SIZE;
else if (stride_size >= PMD_SIZE)
stride_size = PMD_SIZE;
else
stride_size = PAGE_SIZE;
}
}
__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
start, end - start, stride_size);
}
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
__flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID,
start, end - start, PAGE_SIZE);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
start, end - start, PMD_SIZE);
}
#endif
bool arch_tlbbatch_should_defer(struct mm_struct *mm)
{
return true;
}
void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
struct mm_struct *mm,
unsigned long uaddr)
{
cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
}
void arch_flush_tlb_batched_pending(struct mm_struct *mm)
{
flush_tlb_mm(mm);
}
void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
cpumask_clear(&batch->cpumask);
}