From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org, Linus Torvalds <torvalds@linux-foundation.org>,
Andy Lutomirsky <luto@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Dave Hansen <dave.hansen@intel.com>,
Borislav Petkov <bpetkov@suse.de>,
Greg KH <gregkh@linuxfoundation.org>,
keescook@google.com, hughd@google.com,
Brian Gerst <brgerst@gmail.com>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Denys Vlasenko <dvlasenk@redhat.com>,
Rik van Riel <riel@redhat.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>,
Juergen Gross <jgross@suse.com>,
David Laight <David.Laight@aculab.com>,
Eduardo Valentin <eduval@amazon.com>,
aliguori@amazon.com, Will Deacon <will.deacon@arm.com>,
daniel.gruss@iaik.tugraz.at,
Dave Hansen <dave.hansen@linux.intel.com>
Subject: [patch 55/60] x86/mm: Use INVPCID for __native_flush_tlb_single()
Date: Mon, 04 Dec 2017 15:08:01 +0100 [thread overview]
Message-ID: <20171204150609.338279526@linutronix.de> (raw)
In-Reply-To: 20171204140706.296109558@linutronix.de
[-- Attachment #1: x86-mm--Use-INVPCID-for__native_flush_tlb_single.patch --]
[-- Type: text/plain, Size: 5047 bytes --]
From: Dave Hansen <dave.hansen@linux.intel.com>
This uses INVPCID to shoot down individual lines of the user mapping
instead of marking the entire user map as invalid. This
could/might/possibly be faster.
This for sure needs tlb_single_page_flush_ceiling to be redetermined;
esp. since INVPCID is _slow_.
[ Peterz: Split out from big combo patch ]
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/include/asm/cpufeatures.h | 1
arch/x86/include/asm/tlbflush.h | 23 ++++++++++++-
arch/x86/mm/init.c | 64 +++++++++++++++++++++----------------
3 files changed, 60 insertions(+), 28 deletions(-)
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -197,6 +197,7 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -138,6 +138,18 @@ static inline u16 kern_pcid(u16 asid)
return asid + 1;
}
+/*
+ * The user PCID is just the kernel one, plus the "switch bit".
+ */
+static inline u16 user_pcid(u16 asid)
+{
+ u16 ret = kern_pcid(asid);
+#ifdef CONFIG_KERNEL_PAGE_TABLE_ISOLATION
+ ret |= 1 << X86_CR3_KPTI_SWITCH_BIT;
+#endif
+ return ret;
+}
+
struct pgd_t;
static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
@@ -401,6 +413,8 @@ static inline void __native_flush_tlb_gl
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
invpcid_flush_all();
return;
@@ -427,7 +441,14 @@ static inline void __native_flush_tlb_si
if (!static_cpu_has_bug(X86_BUG_CPU_SECURE_MODE_KPTI))
return;
- invalidate_user_asid(loaded_mm_asid);
+ /*
+ * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+ * Just use invalidate_user_asid() in case we are called early.
+ */
+ if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+ invalidate_user_asid(loaded_mm_asid);
+ else
+ invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
}
static inline void __flush_tlb_all(void)
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -203,34 +203,44 @@ static void __init probe_page_size_mask(
static void setup_pcid(void)
{
-#ifdef CONFIG_X86_64
- if (boot_cpu_has(X86_FEATURE_PCID)) {
- if (boot_cpu_has(X86_FEATURE_PGE)) {
- /*
- * This can't be cr4_set_bits_and_update_boot() --
- * the trampoline code can't handle CR4.PCIDE and
- * it wouldn't do any good anyway. Despite the name,
- * cr4_set_bits_and_update_boot() doesn't actually
- * cause the bits in question to remain set all the
- * way through the secondary boot asm.
- *
- * Instead, we brute-force it and set CR4.PCIDE
- * manually in start_secondary().
- */
- cr4_set_bits(X86_CR4_PCIDE);
- } else {
- /*
- * flush_tlb_all(), as currently implemented, won't
- * work if PCID is on but PGE is not. Since that
- * combination doesn't exist on real hardware, there's
- * no reason to try to fully support it, but it's
- * polite to avoid corrupting data if we're on
- * an improperly configured VM.
- */
- setup_clear_cpu_cap(X86_FEATURE_PCID);
- }
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_PCID))
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
+ /*
+ * This can't be cr4_set_bits_and_update_boot() -- the
+ * trampoline code can't handle CR4.PCIDE and it wouldn't
+ * do any good anyway. Despite the name,
+ * cr4_set_bits_and_update_boot() doesn't actually cause
+ * the bits in question to remain set all the way through
+ * the secondary boot asm.
+ *
+ * Instead, we brute-force it and set CR4.PCIDE manually in
+ * start_secondary().
+ */
+ cr4_set_bits(X86_CR4_PCIDE);
+
+ /*
+ * INVPCID's single-context modes (2/3) only work if we set
+ * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable
+ * on systems that have X86_CR4_PCIDE clear, or that have
+ * no INVPCID support at all.
+ */
+ if (boot_cpu_has(X86_FEATURE_INVPCID))
+ setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
+ } else {
+ /*
+ * flush_tlb_all(), as currently implemented, won't work if
+ * PCID is on but PGE is not. Since that combination
+ * doesn't exist on real hardware, there's no reason to try
+ * to fully support it, but it's polite to avoid corrupting
+ * data if we're on an improperly configured VM.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
}
-#endif
}
#ifdef CONFIG_X86_32
next prev parent reply other threads:[~2017-12-04 16:57 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-04 14:07 [patch 00/60] x86/kpti: Kernel Page Table Isolation (was KAISER) Thomas Gleixner
2017-12-04 14:07 ` [patch 01/60] x86/entry/64/paravirt: Use paravirt-safe macro to access eflags Thomas Gleixner
2017-12-05 12:17 ` Juergen Gross
2017-12-04 14:07 ` [patch 02/60] x86/unwinder/orc: Dont bail on stack overflow Thomas Gleixner
2017-12-04 20:31 ` Andy Lutomirski
2017-12-04 21:31 ` Thomas Gleixner
2017-12-04 14:07 ` [patch 03/60] x86/unwinder: Handle stack overflows more gracefully Thomas Gleixner
2017-12-04 14:07 ` [patch 04/60] x86/irq: Remove an old outdated comment about context tracking races Thomas Gleixner
2017-12-04 14:07 ` [patch 05/60] x86/irq/64: Print the offending IP in the stack overflow warning Thomas Gleixner
2017-12-04 14:07 ` [patch 06/60] x86/entry/64: Allocate and enable the SYSENTER stack Thomas Gleixner
2017-12-04 14:07 ` [patch 07/60] x86/dumpstack: Add get_stack_info() support for " Thomas Gleixner
2017-12-04 14:07 ` [patch 08/60] x86/entry/gdt: Put per-CPU GDT remaps in ascending order Thomas Gleixner
2017-12-04 14:07 ` [patch 09/60] x86/mm/fixmap: Generalize the GDT fixmap mechanism, introduce struct cpu_entry_area Thomas Gleixner
2017-12-04 14:07 ` [patch 10/60] x86/kasan/64: Teach KASAN about the cpu_entry_area Thomas Gleixner
2017-12-04 14:07 ` [patch 11/60] x86/entry: Fix assumptions that the HW TSS is at the beginning of cpu_tss Thomas Gleixner
2017-12-04 14:07 ` [patch 12/60] x86/dumpstack: Handle stack overflow on all stacks Thomas Gleixner
2017-12-04 14:07 ` [patch 13/60] x86/entry: Move SYSENTER_stack to the beginning of struct tss_struct Thomas Gleixner
2017-12-04 14:07 ` [patch 14/60] x86/entry: Remap the TSS into the CPU entry area Thomas Gleixner
2017-12-04 18:20 ` Borislav Petkov
2017-12-04 14:07 ` [patch 15/60] x86/entry/64: Separate cpu_current_top_of_stack from TSS.sp0 Thomas Gleixner
2017-12-04 14:07 ` [patch 16/60] x86/espfix/64: Stop assuming that pt_regs is on the entry stack Thomas Gleixner
2017-12-04 14:07 ` [patch 17/60] x86/entry/64: Use a per-CPU trampoline stack for IDT entries Thomas Gleixner
2017-12-04 14:07 ` [patch 18/60] x86/entry/64: Return to userspace from the trampoline stack Thomas Gleixner
2017-12-04 14:07 ` [patch 19/60] x86/entry/64: Create a per-CPU SYSCALL entry trampoline Thomas Gleixner
2017-12-04 22:30 ` Andy Lutomirski
2017-12-04 14:07 ` [patch 20/60] x86/entry/64: Move the IST stacks into struct cpu_entry_area Thomas Gleixner
2017-12-04 14:07 ` [patch 21/60] x86/entry/64: Remove the SYSENTER stack canary Thomas Gleixner
2017-12-04 14:07 ` [patch 22/60] x86/entry: Clean up the SYSENTER_stack code Thomas Gleixner
2017-12-04 19:41 ` Borislav Petkov
2017-12-04 14:07 ` [patch 23/60] x86/entry/64: Make cpu_entry_area.tss read-only Thomas Gleixner
2017-12-04 20:25 ` Borislav Petkov
2017-12-04 14:07 ` [patch 24/60] x86/paravirt: Dont patch flush_tlb_single Thomas Gleixner
2017-12-05 12:18 ` Juergen Gross
2017-12-04 14:07 ` [patch 25/60] x86/paravirt: Provide a way to check for hypervisors Thomas Gleixner
2017-12-05 12:19 ` Juergen Gross
2017-12-04 14:07 ` [patch 26/60] x86/cpufeature: Make cpu bugs sticky Thomas Gleixner
2017-12-04 22:39 ` Borislav Petkov
2017-12-04 14:07 ` [patch 27/60] x86/cpufeatures: Add X86_BUG_CPU_INSECURE Thomas Gleixner
2017-12-04 23:18 ` Borislav Petkov
2017-12-04 14:07 ` [patch 28/60] x86/mm/kpti: Disable global pages if KERNEL_PAGE_TABLE_ISOLATION=y Thomas Gleixner
2017-12-05 14:34 ` Borislav Petkov
2017-12-04 14:07 ` [patch 29/60] x86/mm/kpti: Prepare the x86/entry assembly code for entry/exit CR3 switching Thomas Gleixner
2017-12-04 14:07 ` [patch 30/60] x86/mm/kpti: Add infrastructure for page table isolation Thomas Gleixner
2017-12-05 15:20 ` Borislav Petkov
2017-12-04 14:07 ` [patch 31/60] x86/mm/kpti: Add mapping helper functions Thomas Gleixner
2017-12-04 22:27 ` Andy Lutomirski
2017-12-05 16:01 ` Borislav Petkov
2017-12-07 8:33 ` Borislav Petkov
2017-12-04 14:07 ` [patch 32/60] x86/mm/kpti: Allow NX poison to be set in p4d/pgd Thomas Gleixner
2017-12-05 17:09 ` Borislav Petkov
2017-12-04 14:07 ` [patch 33/60] x86/mm/kpti: Allocate a separate user PGD Thomas Gleixner
2017-12-05 18:33 ` Borislav Petkov
2017-12-06 20:56 ` Ingo Molnar
2017-12-04 14:07 ` [patch 34/60] x86/mm/kpti: Populate " Thomas Gleixner
2017-12-05 19:17 ` Borislav Petkov
2017-12-04 14:07 ` [patch 35/60] x86/espfix: Ensure that ESPFIX is visible in " Thomas Gleixner
2017-12-04 22:28 ` Andy Lutomirski
2017-12-04 14:07 ` [patch 36/60] x86/mm/kpti: Add functions to clone kernel PMDs Thomas Gleixner
2017-12-06 15:39 ` Borislav Petkov
2017-12-04 14:07 ` [patch 37/60] x86mm//kpti: Force entry through trampoline when KPTI active Thomas Gleixner
2017-12-06 16:01 ` Borislav Petkov
2017-12-04 14:07 ` [patch 38/60] x86/fixmap: Move cpu entry area into a separate PMD Thomas Gleixner
2017-12-06 18:57 ` Borislav Petkov
2017-12-04 14:07 ` [patch 39/60] x86/mm/kpti: Share cpu_entry_area PMDs Thomas Gleixner
2017-12-06 21:18 ` Borislav Petkov
2017-12-04 14:07 ` [patch 40/60] x86: PMD align entry text Thomas Gleixner
2017-12-07 8:07 ` Borislav Petkov
2017-12-04 14:07 ` [patch 41/60] x86/mm/kpti: Share entry text PMD Thomas Gleixner
2017-12-07 8:24 ` Borislav Petkov
2017-12-04 14:07 ` [patch 42/60] x86/fixmap: Move IDT fixmap into the cpu_entry_area range Thomas Gleixner
2017-12-04 14:07 ` [patch 43/60] x86/fixmap: Add debugstore entries to cpu_entry_area Thomas Gleixner
2017-12-07 9:55 ` Borislav Petkov
2017-12-04 14:07 ` [patch 44/60] x86/events/intel/ds: Map debug buffers in fixmap Thomas Gleixner
2017-12-04 14:07 ` [patch 45/60] x86/fixmap: Add ldt entries to user shared fixmap Thomas Gleixner
2017-12-04 14:07 ` [patch 46/60] x86/ldt: Rename ldt_struct->entries member Thomas Gleixner
2017-12-04 14:07 ` [patch 47/60] x86/ldt: Map LDT entries into fixmap Thomas Gleixner
2017-12-04 22:33 ` Andy Lutomirski
2017-12-04 22:51 ` Thomas Gleixner
2017-12-04 14:07 ` [patch 48/60] x86/mm: Move the CR3 construction functions to tlbflush.h Thomas Gleixner
2017-12-04 14:07 ` [patch 49/60] x86/mm: Remove hard-coded ASID limit checks Thomas Gleixner
2017-12-04 14:07 ` [patch 50/60] x86/mm: Put MMU to hardware ASID translation in one place Thomas Gleixner
2017-12-04 14:07 ` [patch 51/60] x86/mm: Allow flushing for future ASID switches Thomas Gleixner
2017-12-04 22:22 ` Andy Lutomirski
2017-12-04 22:34 ` Dave Hansen
2017-12-04 22:36 ` Andy Lutomirski
2017-12-04 22:47 ` Peter Zijlstra
2017-12-04 22:54 ` Andy Lutomirski
2017-12-04 23:06 ` Peter Zijlstra
2017-12-04 14:07 ` [patch 52/60] x86/mm: Abstract switching CR3 Thomas Gleixner
2017-12-04 14:07 ` [patch 53/60] x86/mm: Use/Fix PCID to optimize user/kernel switches Thomas Gleixner
2017-12-05 21:46 ` Andy Lutomirski
2017-12-05 22:05 ` Peter Zijlstra
2017-12-05 22:08 ` Dave Hansen
2017-12-04 14:08 ` [patch 54/60] x86/mm: Optimize RESTORE_CR3 Thomas Gleixner
2017-12-04 14:08 ` Thomas Gleixner [this message]
2017-12-04 22:25 ` [patch 55/60] x86/mm: Use INVPCID for __native_flush_tlb_single() Andy Lutomirski
2017-12-04 22:51 ` Peter Zijlstra
2017-12-05 13:51 ` Dave Hansen
2017-12-05 14:08 ` Peter Zijlstra
2017-12-04 14:08 ` [patch 56/60] x86/mm/kpti: Disable native VSYSCALL Thomas Gleixner
2017-12-04 22:33 ` Andy Lutomirski
2017-12-04 14:08 ` [patch 57/60] x86/mm/kpti: Add Kconfig Thomas Gleixner
2017-12-04 16:54 ` Andy Lutomirski
2017-12-04 16:57 ` Thomas Gleixner
2017-12-05 9:34 ` Thomas Gleixner
2017-12-04 14:08 ` [patch 58/60] x86/mm/debug_pagetables: Add page table directory Thomas Gleixner
2017-12-04 14:08 ` [patch 59/60] x86/mm/dump_pagetables: Check user space page table for WX pages Thomas Gleixner
2017-12-04 14:08 ` [patch 60/60] x86/mm/debug_pagetables: Allow dumping current pagetables Thomas Gleixner
2017-12-04 18:02 ` [patch 00/60] x86/kpti: Kernel Page Table Isolation (was KAISER) Linus Torvalds
2017-12-04 18:18 ` Thomas Gleixner
2017-12-04 18:21 ` Boris Ostrovsky
2017-12-04 18:28 ` Linus Torvalds
2017-12-05 21:49 ` Andy Lutomirski
2017-12-05 21:57 ` Dave Hansen
2017-12-05 23:19 ` Andy Lutomirski
2018-01-19 20:56 ` Andrew Morton
2018-01-19 21:06 ` Dave Hansen
2018-01-20 19:59 ` Thomas Gleixner
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=20171204150609.338279526@linutronix.de \
--to=tglx@linutronix.de \
--cc=David.Laight@aculab.com \
--cc=aliguori@amazon.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bpetkov@suse.de \
--cc=brgerst@gmail.com \
--cc=daniel.gruss@iaik.tugraz.at \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=dvlasenk@redhat.com \
--cc=eduval@amazon.com \
--cc=gregkh@linuxfoundation.org \
--cc=hughd@google.com \
--cc=jgross@suse.com \
--cc=jpoimboe@redhat.com \
--cc=keescook@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=torvalds@linux-foundation.org \
--cc=will.deacon@arm.com \
--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).