From: Nadav Amit <namit@vmware.com>
To: Andy Lutomirski <luto@kernel.org>,
Dave Hansen <dave.hansen@linux.intel.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
Peter Zijlstra <peterz@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Nadav Amit <namit@vmware.com>,
Rik van Riel <riel@surriel.com>,
Josh Poimboeuf <jpoimboe@redhat.com>
Subject: [PATCH v2 3/9] x86/mm/tlb: Open-code on_each_cpu_cond_mask() for tlb_is_not_lazy()
Date: Tue, 2 Jul 2019 16:51:45 -0700 [thread overview]
Message-ID: <20190702235151.4377-4-namit@vmware.com> (raw)
In-Reply-To: <20190702235151.4377-1-namit@vmware.com>
Open-code on_each_cpu_cond_mask() in native_flush_tlb_others() to
optimize the code. Open-coding eliminates the need for the indirect branch
that is used to call is_lazy(), and in CPUs that are vulnerable to
Spectre v2, it eliminates the retpoline. In addition, it allows to use a
preallocated cpumask to compute the CPUs that should be.
This would later allow us not to adapt on_each_cpu_cond_mask() to
support local and remote functions.
Note that calling tlb_is_not_lazy() for every CPU that needs to be
flushed, as done in native_flush_tlb_multi() might look ugly, but it is
equivalent to what is currently done in on_each_cpu_cond_mask().
Actually, native_flush_tlb_multi() does it more efficiently since it
avoids using an indirect branch for the matter.
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
---
arch/x86/mm/tlb.c | 40 ++++++++++++++++++++++++++++++++++------
1 file changed, 34 insertions(+), 6 deletions(-)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 8a957b58525f..5c9b1607191d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -658,11 +658,13 @@ static void flush_tlb_func_remote(void *info)
flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
}
-static bool tlb_is_not_lazy(int cpu, void *data)
+static bool tlb_is_not_lazy(int cpu)
{
return !per_cpu(cpu_tlbstate.is_lazy, cpu);
}
+static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
@@ -706,12 +708,38 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
* up on the new contents of what used to be page tables, while
* doing a speculative memory access.
*/
- if (info->freed_tables)
+ if (info->freed_tables) {
smp_call_function_many(cpumask, flush_tlb_func_remote,
(void *)info, 1);
- else
- on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote,
- (void *)info, 1, GFP_ATOMIC, cpumask);
+ } else {
+ /*
+ * Although we could have used on_each_cpu_cond_mask(),
+ * open-coding it has performance advantages, as it eliminates
+ * the need for indirect calls or retpolines. In addition, it
+ * allows to use a designated cpumask for evaluating the
+ * condition, instead of allocating one.
+ *
+ * This code works under the assumption that there are no nested
+ * TLB flushes, an assumption that is already made in
+ * flush_tlb_mm_range().
+ *
+ * cond_cpumask is logically a stack-local variable, but it is
+ * more efficient to have it off the stack and not to allocate
+ * it on demand. Preemption is disabled and this code is
+ * non-reentrant.
+ */
+ struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
+ int cpu;
+
+ cpumask_clear(cond_cpumask);
+
+ for_each_cpu(cpu, cpumask) {
+ if (tlb_is_not_lazy(cpu))
+ __cpumask_set_cpu(cpu, cond_cpumask);
+ }
+ smp_call_function_many(cond_cpumask, flush_tlb_func_remote,
+ (void *)info, 1);
+ }
}
/*
@@ -865,7 +893,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
if (cpumask_test_cpu(cpu, &batch->cpumask)) {
lockdep_assert_irqs_enabled();
local_irq_disable();
- flush_tlb_func_local(&full_flush_tlb_info);
+ flush_tlb_func_local((void *)&full_flush_tlb_info);
local_irq_enable();
}
--
2.17.1
next prev parent reply other threads:[~2019-07-03 7:14 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-02 23:51 [PATCH v2 0/9] x86: Concurrent TLB flushes Nadav Amit
2019-07-02 23:51 ` [PATCH v2 1/9] smp: Run functions concurrently in smp_call_function_many() Nadav Amit
2019-07-02 23:51 ` [PATCH v2 2/9] x86/mm/tlb: Remove reason as argument for flush_tlb_func_local() Nadav Amit
2019-07-02 23:51 ` Nadav Amit [this message]
2019-07-02 23:51 ` [PATCH v2 4/9] x86/mm/tlb: Flush remote and local TLBs concurrently Nadav Amit
2019-07-03 14:04 ` Juergen Gross
2019-07-03 17:02 ` Nadav Amit
2019-07-03 17:43 ` [Xen-devel] " Andrew Cooper
2019-07-03 18:09 ` Nadav Amit
2019-07-02 23:51 ` [PATCH v2 5/9] x86/mm/tlb: Privatize cpu_tlbstate Nadav Amit
2019-07-02 23:51 ` [PATCH v2 6/9] x86/mm/tlb: Do not make is_lazy dirty for no reason Nadav Amit
2019-07-02 23:51 ` [PATCH v2 7/9] cpumask: Mark functions as pure Nadav Amit
2019-07-02 23:51 ` [PATCH v2 8/9] x86/mm/tlb: Remove UV special case Nadav Amit
2019-07-09 19:50 ` Thomas Gleixner
2019-07-09 20:09 ` Russ Anderson
2019-07-09 20:29 ` Mike Travis
2019-07-09 21:09 ` Nadav Amit
2019-07-09 21:17 ` Mike Travis
2019-07-02 23:51 ` [PATCH v2 9/9] x86/mm/tlb: Remove unnecessary uses of the inline keyword Nadav Amit
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190702235151.4377-4-namit@vmware.com \
--to=namit@vmware.com \
--cc=dave.hansen@linux.intel.com \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).