mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Hugh Dickins <hughd@google.com>,
	Jiri Kosina <jkosina@suse.cz>
Subject: [PATCH 4.9 32/39] kaiser: asm/tlbflush.h handle noPGE at lower level
Date: Wed,  3 Jan 2018 21:11:46 +0100	[thread overview]
Message-ID: <20180103195105.433550394@linuxfoundation.org> (raw)
In-Reply-To: <20180103195104.066528044@linuxfoundation.org>

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hugh Dickins <hughd@google.com>


I found asm/tlbflush.h too twisty, and think it safer not to avoid
__native_flush_tlb_global_irq_disabled() in the kaiser_enabled case,
but instead let it handle kaiser_enabled along with cr3: it can just
use __native_flush_tlb() for that, no harm in re-disabling preemption.

(This is not the same change as Kirill and Dave have suggested for
upstream, flipping PGE in cr4: that's neat, but needs a cpu_has_pge
check; cr3 is enough for kaiser, and thought to be cheaper than cr4.)

Also delete the X86_FEATURE_INVPCID invpcid_flush_all_nonglobals()
preference from __native_flush_tlb(): unlike the invpcid_flush_all()
preference in __native_flush_tlb_global(), it's not seen in upstream
4.14, and was recently reported to be surprisingly slow.

Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/include/asm/tlbflush.h |   27 +++------------------------
 1 file changed, 3 insertions(+), 24 deletions(-)

--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -152,14 +152,6 @@ static inline void kaiser_flush_tlb_on_r
 
 static inline void __native_flush_tlb(void)
 {
-	if (this_cpu_has(X86_FEATURE_INVPCID)) {
-		/*
-		 * Note, this works with CR4.PCIDE=0 or 1.
-		 */
-		invpcid_flush_all_nonglobals();
-		return;
-	}
-
 	/*
 	 * If current->mm == NULL then we borrow a mm which may change during a
 	 * task switch and therefore we must not be preempted while we write CR3
@@ -183,11 +175,8 @@ static inline void __native_flush_tlb_gl
 		/* restore PGE as it was before */
 		native_write_cr4(cr4);
 	} else {
-		/*
-		 * x86_64 microcode update comes this way when CR4.PGE is not
-		 * enabled, and it's safer for all callers to allow this case.
-		 */
-		native_write_cr3(native_read_cr3());
+		/* do it with cr3, letting kaiser flush user PCID */
+		__native_flush_tlb();
 	}
 }
 
@@ -195,12 +184,6 @@ static inline void __native_flush_tlb_gl
 {
 	unsigned long flags;
 
-	if (kaiser_enabled) {
-		/* Globals are not used at all */
-		__native_flush_tlb();
-		return;
-	}
-
 	if (this_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
 		 * Using INVPCID is considerably faster than a pair of writes
@@ -256,11 +239,7 @@ static inline void __native_flush_tlb_si
 
 static inline void __flush_tlb_all(void)
 {
-	if (boot_cpu_has(X86_FEATURE_PGE))
-		__flush_tlb_global();
-	else
-		__flush_tlb();
-
+	__flush_tlb_global();
 	/*
 	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
 	 * we'd end up flushing kernel translations for the current ASID but

  parent reply	other threads:[~2018-01-03 20:14 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-03 20:11 [PATCH 4.9 00/39] 4.9.75-stable review Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 01/39] tcp_bbr: reset full pipe detection on loss recovery undo Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 02/39] tcp_bbr: reset long-term bandwidth sampling " Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 03/39] x86/boot: Add early cmdline parsing for options with arguments Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 04/39] KAISER: Kernel Address Isolation Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 05/39] kaiser: merged update Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 06/39] kaiser: do not set _PAGE_NX on pgd_none Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 07/39] kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 08/39] kaiser: fix build and FIXME in alloc_ldt_struct() Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 09/39] kaiser: KAISER depends on SMP Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 10/39] kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 11/39] kaiser: fix perf crashes Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 12/39] kaiser: ENOMEM if kaiser_pagetable_walk() NULL Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 13/39] kaiser: tidied up asm/kaiser.h somewhat Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 14/39] kaiser: tidied up kaiser_add/remove_mapping slightly Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 15/39] kaiser: align addition to x86/mm/Makefile Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 16/39] kaiser: cleanups while trying for gold link Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 17/39] kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 18/39] kaiser: delete KAISER_REAL_SWITCH option Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 19/39] kaiser: vmstat show NR_KAISERTABLE as nr_overhead Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 20/39] kaiser: enhanced by kernel and user PCIDs Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 21/39] kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 22/39] kaiser: PCID 0 for kernel and 128 for user Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 23/39] kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 24/39] kaiser: paranoid_entry pass cr3 need to paranoid_exit Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 25/39] kaiser: kaiser_remove_mapping() move along the pgd Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 26/39] kaiser: fix unlikely error in alloc_ldt_struct() Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 27/39] kaiser: add "nokaiser" boot option, using ALTERNATIVE Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 28/39] x86/kaiser: Rename and simplify X86_FEATURE_KAISER handling Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 29/39] x86/kaiser: Check boottime cmdline params Greg Kroah-Hartman
2018-01-04  0:16   ` Ben Hutchings
2018-01-04  7:05     ` Borislav Petkov
2018-01-04  7:38       ` Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 30/39] kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 31/39] kaiser: drop is_atomic arg to kaiser_pagetable_walk() Greg Kroah-Hartman
2018-01-03 20:11 ` Greg Kroah-Hartman [this message]
2018-01-03 20:11 ` [PATCH 4.9 33/39] kaiser: kaiser_flush_tlb_on_return_to_user() check PCID Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 34/39] x86/paravirt: Dont patch flush_tlb_single Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 35/39] x86/kaiser: Reenable PARAVIRT Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 36/39] kaiser: disabled on Xen PV Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 37/39] x86/kaiser: Move feature detection up Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 38/39] KPTI: Rename to PAGE_TABLE_ISOLATION Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.9 39/39] KPTI: Report when enabled Greg Kroah-Hartman
2018-01-04  1:24 ` [PATCH 4.9 00/39] 4.9.75-stable review Ben Hutchings
2018-01-04  4:07   ` Hugh Dickins
2018-01-04  4:18     ` Andy Lutomirski
2018-01-04  7:39   ` Greg Kroah-Hartman
2018-01-04  7:41     ` Greg Kroah-Hartman
2018-01-04  7:01 ` Naresh Kamboju
2018-01-04  8:10   ` Greg Kroah-Hartman
2018-01-04 10:07 ` kernelci.org bot
2018-01-05  0:10   ` Kevin Hilman
2018-01-04 17:04 ` Guenter Roeck
2018-01-04 22:01 ` Shuah Khan
2018-01-05 10:23 ` Alice Ferrazzi
2018-01-05 12:12   ` Greg Kroah-Hartman

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=20180103195105.433550394@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=hughd@google.com \
    --cc=jkosina@suse.cz \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.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

Powered by JetHome