All of lore.kernel.org
 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 4.4 30/37] kaiser: asm/tlbflush.h handle noPGE at lower level
Date: Wed,  3 Jan 2018 21:11:36 +0100	[thread overview]
Message-ID: <20180103195058.379455686@linuxfoundation.org> (raw)
In-Reply-To: <20180103195056.837404126@linuxfoundation.org>

4.4-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
@@ -151,14 +151,6 @@ 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
@@ -182,11 +174,8 @@ 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();
 	}
 }
 
@@ -194,12 +183,6 @@ 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
@@ -255,11 +238,7 @@ static inline void __native_flush_tlb_si
 
 static inline void __flush_tlb_all(void)
 {
-	if (cpu_has_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 20:13 UTC|newest]

Thread overview: 156+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-03 20:11 [PATCH 4.4 00/37] 4.4.110-stable review Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 01/37] x86/boot: Add early cmdline parsing for options with arguments Greg Kroah-Hartman
2018-01-03 20:11   ` Greg Kroah-Hartman
2018-01-03 20:11   ` Greg Kroah-Hartman
2018-01-03 20:11   ` Greg Kroah-Hartman
2018-01-03 20:11 ` [kernel-hardening] [PATCH 4.4 02/37] KAISER: Kernel Address Isolation Greg Kroah-Hartman
2018-01-03 20:11   ` Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 03/37] kaiser: merged update Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 04/37] kaiser: do not set _PAGE_NX on pgd_none Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 05/37] kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 06/37] kaiser: fix build and FIXME in alloc_ldt_struct() Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 07/37] kaiser: KAISER depends on SMP Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 08/37] kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 09/37] kaiser: fix perf crashes Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 10/37] kaiser: ENOMEM if kaiser_pagetable_walk() NULL Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 11/37] kaiser: tidied up asm/kaiser.h somewhat Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 12/37] kaiser: tidied up kaiser_add/remove_mapping slightly Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 13/37] kaiser: kaiser_remove_mapping() move along the pgd Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 14/37] kaiser: cleanups while trying for gold link Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 15/37] kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 16/37] kaiser: delete KAISER_REAL_SWITCH option Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 17/37] kaiser: vmstat show NR_KAISERTABLE as nr_overhead Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 18/37] kaiser: enhanced by kernel and user PCIDs Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 19/37] kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 20/37] kaiser: PCID 0 for kernel and 128 for user Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 21/37] kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 22/37] kaiser: paranoid_entry pass cr3 need to paranoid_exit Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 23/37] kaiser: _pgd_alloc() without __GFP_REPEAT to avoid stalls Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 24/37] kaiser: fix unlikely error in alloc_ldt_struct() Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 25/37] kaiser: add "nokaiser" boot option, using ALTERNATIVE Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 26/37] x86/kaiser: Rename and simplify X86_FEATURE_KAISER handling Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 27/37] x86/kaiser: Check boottime cmdline params Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 28/37] kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 29/37] 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 4.4 31/37] kaiser: kaiser_flush_tlb_on_return_to_user() check PCID Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 32/37] x86/paravirt: Dont patch flush_tlb_single Greg Kroah-Hartman
2018-01-03 20:11   ` Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 33/37] x86/kaiser: Reenable PARAVIRT Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 34/37] kaiser: disabled on Xen PV Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 35/37] x86/kaiser: Move feature detection up Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 36/37] KPTI: Rename to PAGE_TABLE_ISOLATION Greg Kroah-Hartman
2018-01-03 20:11 ` [PATCH 4.4 37/37] KPTI: Report when enabled Greg Kroah-Hartman
2018-01-03 22:08 ` [PATCH 4.4 00/37] 4.4.110-stable review Nathan Chancellor
2018-01-04  8:10   ` Greg Kroah-Hartman
2018-01-04  6:50 ` Naresh Kamboju
2018-01-04  9:27 ` kernelci.org bot
2018-01-05  0:06   ` Kevin Hilman
2018-01-08 15:06     ` Guillaume Tucker
2018-01-04 16:38 ` Pavel Tatashin
2018-01-04 16:53   ` Greg Kroah-Hartman
2018-01-04 17:01     ` Guenter Roeck
2018-01-04 17:09       ` Greg Kroah-Hartman
2018-01-04 17:02     ` Pavel Tatashin
2018-01-04 17:03     ` Willy Tarreau
2018-01-04 17:11       ` Greg Kroah-Hartman
2018-01-04 17:13         ` Willy Tarreau
2018-01-04 17:14         ` Greg Kroah-Hartman
2018-01-04 17:16           ` Greg Kroah-Hartman
2018-01-04 17:56             ` Guenter Roeck
2018-01-05 15:00               ` Greg Kroah-Hartman
2018-01-05 18:12                 ` Guenter Roeck
2018-01-05 20:53                   ` Greg Kroah-Hartman
2018-01-04 20:11   ` Linus Torvalds
2018-01-04 17:03 ` Guenter Roeck
2018-01-04 19:38 ` Thomas Voegtle
2018-01-04 19:50   ` Greg Kroah-Hartman
2018-01-04 20:16     ` Thomas Voegtle
2018-01-04 20:29       ` Linus Torvalds
2018-01-04 20:43         ` Andy Lutomirski
2018-01-04 20:57           ` Hugh Dickins
2018-01-04 21:16             ` Andy Lutomirski
2018-01-04 21:23             ` Pavel Tatashin
2018-01-04 21:37               ` Hugh Dickins
2018-01-04 21:48                 ` Pavel Tatashin
2018-01-04 22:33                   ` Linus Torvalds
2018-01-05 14:59                   ` Greg Kroah-Hartman
2018-01-05 15:32                     ` Pavel Tatashin
2018-01-05 15:51                       ` Greg Kroah-Hartman
2018-01-05 15:57                         ` Willy Tarreau
2018-01-05 18:01                           ` Greg Kroah-Hartman
2018-01-05 16:26                         ` Pavel Tatashin
2018-01-05 16:57                       ` Andy Lutomirski
2018-01-05 17:14                         ` Pavel Tatashin
2018-01-05 17:43                           ` Andy Lutomirski
2018-01-05 17:48                             ` Pavel Tatashin
2018-01-05 17:52                               ` Greg Kroah-Hartman
2018-01-05 18:15                                 ` Andy Lutomirski
2018-01-05 18:21                                   ` Pavel Tatashin
2018-01-05 19:14                                     ` Pavel Tatashin
2018-01-05 19:18                                       ` Pavel Tatashin
2018-01-05 20:45                                         ` Greg Kroah-Hartman
2018-01-05 21:03                                           ` Pavel Tatashin
2018-01-05 23:15                                             ` Hugh Dickins
2018-01-06  1:16                                               ` Pavel Tatashin
2018-01-07 10:45                                             ` Greg Kroah-Hartman
2018-01-07 14:17                                               ` Pavel Tatashin
2018-01-07 15:06                                                 ` Pavel Tatashin
2018-01-08  7:46                                                   ` Greg Kroah-Hartman
2018-01-08 20:38                                                     ` Pavel Tatashin
2018-01-08 21:24                                                       ` Pavel Tatashin
2018-01-11 18:36                                                         ` Pavel Tatashin
2018-01-11 18:40                                                           ` Pavel Tatashin
2018-01-11 19:09                                                             ` Linus Torvalds
2018-01-11 20:37                                                               ` Thomas Gleixner
2018-01-11 20:46                                                                 ` Linus Torvalds
2018-01-11 21:32                                                                   ` Thomas Gleixner
2018-01-11 22:30                                                                     ` Thomas Gleixner
2018-01-11 22:42                                                                       ` Steven Sistare
2018-01-11 22:47                                                                         ` Thomas Gleixner
2018-01-12  1:15                                                                           ` Guenter Roeck
2018-01-11 22:59                                                                         ` Linus Torvalds
2018-01-11 23:03                                                                       ` Thomas Gleixner
2018-01-12  7:19                                                                         ` Greg Kroah-Hartman
2018-01-12  8:03                                                                           ` Thomas Gleixner
2018-01-11 21:35                                                                   ` Steven Sistare
2018-01-11 21:44                                                                     ` Thomas Gleixner
2018-01-11 21:49                                                                       ` Linus Torvalds
2018-01-11 20:10                                                           ` Greg Kroah-Hartman
2018-01-11 20:17                                                             ` Linus Torvalds
2018-01-11 20:18                                                             ` Pavel Tatashin
2018-01-05 20:48                                   ` Greg Kroah-Hartman
2018-01-05  5:33           ` Andy Lutomirski
2018-01-05 10:12             ` Kees Cook
2018-01-05 12:14               ` Greg Kroah-Hartman
2018-01-05 13:08               ` Greg Kroah-Hartman
2018-01-04 20:10   ` Guenter Roeck
2018-01-05 14:58   ` Greg Kroah-Hartman
2018-01-05 15:25     ` Thomas Voegtle
2018-01-05 15:48       ` Greg Kroah-Hartman
2018-01-04 22:00 ` Shuah Khan
2018-01-05  7:55   ` Greg Kroah-Hartman
2018-01-04 23:45 ` Guenter Roeck
2018-01-04 23:58   ` Linus Torvalds
2018-01-05  4:37   ` Mike Galbraith
2018-01-05  4:37     ` Mike Galbraith
2018-01-05 12:17     ` Greg Kroah-Hartman
2018-01-05 12:17       ` Greg Kroah-Hartman
2018-01-05 13:03       ` Mike Galbraith
2018-01-05 13:03         ` Mike Galbraith
2018-01-05 13:34         ` Greg Kroah-Hartman
2018-01-05 13:34           ` Greg Kroah-Hartman
2018-01-05 14:03           ` Mike Galbraith
2018-01-05 23:28             ` Hugh Dickins
2018-01-06  2:58               ` Mike Galbraith
2018-01-05 13:41   ` Greg Kroah-Hartman
2018-01-05 17:51     ` Guenter Roeck
2018-01-05 17:20 ` Alice Ferrazzi
2018-01-05 18:01   ` Greg Kroah-Hartman
2018-01-09 19:49     ` Serge E. Hallyn
2018-01-10  8:48       ` Greg Kroah-Hartman
2018-01-10 16:45         ` Serge E. Hallyn
2018-01-05 17:56 ` Guenter Roeck
2018-01-05 20:54   ` Greg Kroah-Hartman
2018-01-05 21:21     ` Guenter Roeck
2018-01-06  1:35     ` Guenter Roeck

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=20180103195058.379455686@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.