On 12/30/24 11:53, Rik van Riel wrote:
> Use broadcast TLB invalidation for kernel addresses when available.
>
> This stops us from having to send IPIs for kernel TLB flushes.
>
> Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
> ---
> arch/x86/mm/tlb.c | 31 +++++++++++++++++++++++++++++++
> 1 file changed, 31 insertions(+)
>
> diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
> index 6cf881a942bb..29207dc5b807 100644
> --- a/arch/x86/mm/tlb.c
> +++ b/arch/x86/mm/tlb.c
> @@ -1077,6 +1077,32 @@ void flush_tlb_all(void)
> on_each_cpu(do_flush_tlb_all, NULL, 1);
> }
>
> +static void broadcast_kernel_range_flush(unsigned long start, unsigned long end)
> +{
> + unsigned long addr;
> + unsigned long maxnr = invlpgb_count_max;
> + unsigned long threshold = tlb_single_page_flush_ceiling * maxnr;
> +
> + /*
> + * TLBSYNC only waits for flushes originating on the same CPU.
> + * Disabling migration allows us to wait on all flushes.
> + */
> + guard(preempt)();
> +
> + if (end == TLB_FLUSH_ALL ||
> + (end - start) > threshold << PAGE_SHIFT) {
> + invlpgb_flush_all();
> + } else {
> + unsigned long nr;
> + for (addr = start; addr < end; addr += nr << PAGE_SHIFT) {
> + nr = min((end - addr) >> PAGE_SHIFT, maxnr);
> + invlpgb_flush_addr(addr, nr);
> + }
Would it be better to put this loop in the actual invlpgb_flush*
function(s)? Then callers don't have to worry about it, similar to what is
done in clflush_cache_range() / clflush_cache_range_opt().
Thanks,
Tom
> + }
> +
> + tlbsync();
> +}
> +
> static void do_kernel_range_flush(void *info)
> {
> struct flush_tlb_info *f = info;
> @@ -1089,6 +1115,11 @@ static void do_kernel_range_flush(void *info)
>
> void flush_tlb_kernel_range(unsigned long start, unsigned long end)
> {
> + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
> + broadcast_kernel_range_flush(start, end);
> + return;
> + }
> +
> /* Balance as user space task's flush, a bit conservative */
> if (end == TLB_FLUSH_ALL ||
> (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
