From: Nadav Amit <namit@vmware.com>
To: Juergen Gross <jgross@suse.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
the arch/x86 maintainers <x86@kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Stefano Stabellini <sstabellini@kernel.org>,
Andy Lutomirski <luto@kernel.org>,
xen-devel <xen-devel@lists.xenproject.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>
Subject: Re: [Xen-devel] [RFC PATCH v2 1/3] x86/mm/tlb: Change __flush_tlb_one_user interface
Date: Mon, 26 Aug 2019 16:38:40 +0000 [thread overview]
Message-ID: <41C46D29-A0F3-48AA-BC28-2480F24D60FF@vmware.com> (raw)
In-Reply-To: <edb3a7e8-8fc6-7a55-37c1-3384a8413427@suse.com>
> On Aug 26, 2019, at 12:51 AM, Juergen Gross <jgross@suse.com> wrote:
>
> On 24.08.19 00:52, Nadav Amit wrote:
>> __flush_tlb_one_user() currently flushes a single entry, and flushes it
>> both in the kernel and user page-tables, when PTI is enabled.
>> Change __flush_tlb_one_user() and related interfaces into
>> __flush_tlb_range() that flushes a range and does not flush the user
>> page-table.
>> This refactoring is needed for the next patch, but regardless makes
>> sense and has several advantages. First, only Xen-PV, which does not
>> use PTI, implements the paravirtual interface of flush_tlb_one_user() so
>> nothing is broken by separating the user and kernel page-table flushes,
>> and the interface is more intuitive.
>> Second, INVLPG can flush unrelated mappings, and it is also a
>> serializing instruction. It is better to have a tight loop that flushes
>> the entries.
>> Third, currently __flush_tlb_one_kernel() also flushes the user
>> page-tables, which is not needed. This allows to avoid this redundant
>> flush.
>> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
>> Cc: Juergen Gross <jgross@suse.com>
>> Cc: Stefano Stabellini <sstabellini@kernel.org>
>> Cc: xen-devel@lists.xenproject.org
>> Signed-off-by: Nadav Amit <namit@vmware.com>
>> ---
>> arch/x86/include/asm/paravirt.h | 5 ++--
>> arch/x86/include/asm/paravirt_types.h | 3 ++-
>> arch/x86/include/asm/tlbflush.h | 24 +++++------------
>> arch/x86/kernel/paravirt.c | 7 ++---
>> arch/x86/mm/tlb.c | 39 ++++++++++++++++++++++-----
>> arch/x86/xen/mmu_pv.c | 21 +++++++++------
>> 6 files changed, 62 insertions(+), 37 deletions(-)
>
> ...
>
>> diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
>> index 48f7c7eb4dbc..ed68657f5e77 100644
>> --- a/arch/x86/xen/mmu_pv.c
>> +++ b/arch/x86/xen/mmu_pv.c
>> @@ -1325,22 +1325,27 @@ static noinline void xen_flush_tlb(void)
>> preempt_enable();
>> }
>> -static void xen_flush_tlb_one_user(unsigned long addr)
>> +static void xen_flush_tlb_range(unsigned long start, unsigned long end,
>> + u8 stride_shift)
>> {
>> struct mmuext_op *op;
>> struct multicall_space mcs;
>> -
>> - trace_xen_mmu_flush_tlb_one_user(addr);
>> + unsigned long addr;
>> preempt_disable();
>> mcs = xen_mc_entry(sizeof(*op));
>> op = mcs.args;
>> - op->cmd = MMUEXT_INVLPG_LOCAL;
>> - op->arg1.linear_addr = addr & PAGE_MASK;
>> - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
>> - xen_mc_issue(PARAVIRT_LAZY_MMU);
>> + for (addr = start; addr < end; addr += 1ul << stride_shift) {
>> + trace_xen_mmu_flush_tlb_one_user(addr);
>> +
>> + op->cmd = MMUEXT_INVLPG_LOCAL;
>> + op->arg1.linear_addr = addr & PAGE_MASK;
>> + MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
>> +
>> + xen_mc_issue(PARAVIRT_LAZY_MMU);
>> + }
>
> For this kind of usage (a loop) you should:
>
> - replace the call of xen_mc_entry() with xen_mc_batch()
> - use xen_extend_mmuext_op() for each loop iteration
> - call xen_mc_issue() after the loop
>
> Additionally I'd like you to replace trace_xen_mmu_flush_tlb_one_user()
> with trace_xen_mmu_flush_tlb_range() taking all three parameters and
> keep it where it was (out of the loop).
>
> The paravirt parts seem to be okay.
Thanks for the quick response. I don’t think the preempt_disable/enable() is
needed in this case, but I kept them. Does the following match what you had
in mind?
---
arch/x86/xen/mmu_pv.c | 25 ++++++++++++++-----------
include/trace/events/xen.h | 18 ++++++++++++------
2 files changed, 26 insertions(+), 17 deletions(-)
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 48f7c7eb4dbc..faa01591df36 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1325,20 +1325,23 @@ static noinline void xen_flush_tlb(void)
preempt_enable();
}
-static void xen_flush_tlb_one_user(unsigned long addr)
+static void xen_flush_tlb_range(unsigned long start, unsigned long end,
+ u8 stride_shift)
{
- struct mmuext_op *op;
- struct multicall_space mcs;
-
- trace_xen_mmu_flush_tlb_one_user(addr);
+ struct mmuext_op op;
+ unsigned long addr;
preempt_disable();
- mcs = xen_mc_entry(sizeof(*op));
- op = mcs.args;
- op->cmd = MMUEXT_INVLPG_LOCAL;
- op->arg1.linear_addr = addr & PAGE_MASK;
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+ xen_mc_batch();
+ op.cmd = MMUEXT_INVLPG_LOCAL;
+
+ trace_xen_mmu_flush_tlb_range(start, end, stride_shift);
+
+ for (addr = start; addr < end; addr += 1ul << stride_shift) {
+ op.arg1.linear_addr = addr & PAGE_MASK;
+ xen_extend_mmuext_op(&op);
+ }
xen_mc_issue(PARAVIRT_LAZY_MMU);
@@ -2394,7 +2397,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
.flush_tlb_user = xen_flush_tlb,
.flush_tlb_kernel = xen_flush_tlb,
- .flush_tlb_one_user = xen_flush_tlb_one_user,
+ .flush_tlb_range = xen_flush_tlb_range,
.flush_tlb_multi = xen_flush_tlb_multi,
.tlb_remove_table = tlb_remove_table,
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 546022acf160..32bf0a94b4d8 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -352,14 +352,20 @@ DECLARE_EVENT_CLASS(xen_mmu_pgd,
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin);
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);
-TRACE_EVENT(xen_mmu_flush_tlb_one_user,
- TP_PROTO(unsigned long addr),
- TP_ARGS(addr),
+TRACE_EVENT(xen_mmu_flush_tlb_range,
+ TP_PROTO(unsigned long start, unsigned long end,
+ unsigned char stride_shift),
+ TP_ARGS(start, end, stride_shift),
TP_STRUCT__entry(
- __field(unsigned long, addr)
+ __field(unsigned long, start)
+ __field(unsigned long, end)
+ __field(unsigned char, stride_shift)
),
- TP_fast_assign(__entry->addr = addr),
- TP_printk("addr %lx", __entry->addr)
+ TP_fast_assign(__entry->start = start;
+ __entry->end = end;
+ __entry->stride_shift = stride_shift),
+ TP_printk("start %lx end %lx stride_shift %d", __entry->start,
+ __entry->end, __entry->stride_shift)
);
TRACE_EVENT(xen_mmu_flush_tlb_multi,
--
2.17.1
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2019-08-26 16:39 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20190823225248.15597-1-namit@vmware.com>
2019-08-23 22:52 ` [Xen-devel] [RFC PATCH v2 1/3] x86/mm/tlb: Change __flush_tlb_one_user interface Nadav Amit
2019-08-26 7:51 ` Juergen Gross
2019-08-26 16:38 ` Nadav Amit [this message]
2019-08-27 5:53 ` Juergen Gross
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=41C46D29-A0F3-48AA-BC28-2480F24D60FF@vmware.com \
--to=namit@vmware.com \
--cc=boris.ostrovsky@oracle.com \
--cc=dave.hansen@linux.intel.com \
--cc=jgross@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=sstabellini@kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=xen-devel@lists.xenproject.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).