rcu.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Valentin Schneider <vschneid@redhat.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	rcu@vger.kernel.org, x86@kernel.org,
	linux-arm-kernel@lists.infradead.org, loongarch@lists.linux.dev,
	linux-riscv@lists.infradead.org, linux-arch@vger.kernel.org,
	linux-trace-kernel@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Josh Poimboeuf <jpoimboe@kernel.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Frederic Weisbecker <frederic@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Jason Baron <jbaron@akamai.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ard Biesheuvel <ardb@kernel.org>,
	Sami Tolvanen <samitolvanen@google.com>,
	"David S. Miller" <davem@davemloft.net>,
	Neeraj Upadhyay <neeraj.upadhyay@kernel.org>,
	Joel Fernandes <joelagnelf@nvidia.com>,
	Josh Triplett <josh@joshtriplett.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	Uladzislau Rezki <urezki@gmail.com>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Mel Gorman <mgorman@suse.de>,
	Andrew Morton <akpm@linux-foundation.org>,
	Masahiro Yamada <masahiroy@kernel.org>,
	Han Shen <shenhan@google.com>, Rik van Riel <riel@surriel.com>,
	Jann Horn <jannh@google.com>,
	Dan Carpenter <dan.carpenter@linaro.org>,
	Oleg Nesterov <oleg@redhat.com>,
	Juri Lelli <juri.lelli@redhat.com>,
	Clark Williams <williams@redhat.com>,
	Yair Podemsky <ypodemsk@redhat.com>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Daniel Wagner <dwagner@suse.de>, Petr Tesarik <ptesarik@suse.com>,
	Shrikanth Hegde <sshegde@linux.ibm.com>
Subject: [RFC PATCH v7 28/31] x86/mm/pti: Introduce a kernel/user CR3 software signal
Date: Fri, 14 Nov 2025 16:14:25 +0100	[thread overview]
Message-ID: <20251114151428.1064524-8-vschneid@redhat.com> (raw)
In-Reply-To: <20251114150133.1056710-1-vschneid@redhat.com>

Later commits will rely on this information to defer kernel TLB flush
IPIs. Update it when switching to and from the kernel CR3.

This will only be really useful for NOHZ_FULL CPUs, but it should be
cheaper to unconditionally update a never-used per-CPU variable living in
its own cacheline than to check a shared cpumask such as
  housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)
at every entry.

Note that the COALESCE_TLBI config option is introduced in a later commit,
when the whole feature is implemented.

Signed-off-by: Valentin Schneider <vschneid@redhat.com>
---
Per the cover letter, I really hate this, but couldn't come up with
anything better.
---
 arch/x86/entry/calling.h        | 21 +++++++++++++++++++++
 arch/x86/entry/syscall_64.c     |  4 ++++
 arch/x86/include/asm/tlbflush.h |  3 +++
 3 files changed, 28 insertions(+)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 77e2d920a6407..0187c0ea2fddb 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -9,6 +9,7 @@
 #include <asm/ptrace-abi.h>
 #include <asm/msr.h>
 #include <asm/nospec-branch.h>
+#include <asm/jump_label.h>

 /*

@@ -170,11 +171,28 @@ For 32-bit we have the following conventions - kernel is built with
	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
 .endm

+.macro COALESCE_TLBI
+#ifdef CONFIG_COALESCE_TLBI
+	STATIC_BRANCH_FALSE_LIKELY housekeeping_overridden, .Lend_\@
+	movl     $1, PER_CPU_VAR(kernel_cr3_loaded)
+.Lend_\@:
+#endif // CONFIG_COALESCE_TLBI
+.endm
+
+.macro NOTE_SWITCH_TO_USER_CR3
+#ifdef CONFIG_COALESCE_TLBI
+	STATIC_BRANCH_FALSE_LIKELY housekeeping_overridden, .Lend_\@
+	movl     $0, PER_CPU_VAR(kernel_cr3_loaded)
+.Lend_\@:
+#endif // CONFIG_COALESCE_TLBI
+.endm
+
 .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
	mov	%cr3, \scratch_reg
	ADJUST_KERNEL_CR3 \scratch_reg
	mov	\scratch_reg, %cr3
+	COALESCE_TLBI
 .Lend_\@:
 .endm

@@ -182,6 +200,7 @@ For 32-bit we have the following conventions - kernel is built with
	PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask)

 .macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
+	NOTE_SWITCH_TO_USER_CR3
	mov	%cr3, \scratch_reg

	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
@@ -241,6 +260,7 @@ For 32-bit we have the following conventions - kernel is built with

	ADJUST_KERNEL_CR3 \scratch_reg
	movq	\scratch_reg, %cr3
+	COALESCE_TLBI

 .Ldone_\@:
 .endm
@@ -257,6 +277,7 @@ For 32-bit we have the following conventions - kernel is built with
	bt	$PTI_USER_PGTABLE_BIT, \save_reg
	jnc	.Lend_\@

+	NOTE_SWITCH_TO_USER_CR3
	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID

	/*
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index b6e68ea98b839..2589d232e0ba1 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -83,6 +83,10 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
	return false;
 }

+#ifdef CONFIG_COALESCE_TLBI
+DEFINE_PER_CPU(bool, kernel_cr3_loaded) = true;
+#endif
+
 /* Returns true to return using SYSRET, or false to use IRET */
 __visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
 {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 00daedfefc1b0..e39ae95b85072 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -17,6 +17,9 @@
 #include <asm/pgtable.h>

 DECLARE_PER_CPU(u64, tlbstate_untag_mask);
+#ifdef CONFIG_COALESCE_TLBI
+DECLARE_PER_CPU(bool, kernel_cr3_loaded);
+#endif

 void __flush_tlb_all(void);

--
2.51.0


  parent reply	other threads:[~2025-11-14 15:16 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-14 15:01 [PATCH v7 00/31] context_tracking,x86: Defer some IPIs until a user->kernel transition Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 01/31] objtool: Make validate_call() recognize indirect calls to pv_ops[] Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 02/31] objtool: Flesh out warning related to pv_ops[] calls Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 03/31] rcu: Add a small-width RCU watching counter debug option Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 04/31] rcutorture: Make TREE04 use CONFIG_RCU_DYNTICKS_TORTURE Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 05/31] jump_label: Add annotations for validating noinstr usage Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 06/31] static_call: Add read-only-after-init static calls Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 07/31] x86/paravirt: Mark pv_sched_clock static call as __ro_after_init Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 08/31] x86/idle: Mark x86_idle " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 09/31] x86/paravirt: Mark pv_steal_clock " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 10/31] riscv/paravirt: " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 11/31] loongarch/paravirt: " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 12/31] arm64/paravirt: " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 13/31] arm/paravirt: " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 14/31] perf/x86/amd: Mark perf_lopwr_cb " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 15/31] sched/clock: Mark sched_clock_running key " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 16/31] KVM: VMX: Mark __kvm_is_using_evmcs static " Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 17/31] x86/bugs: Mark cpu_buf_vm_clear key as allowed in .noinstr Valentin Schneider
2025-11-14 15:01 ` [PATCH v7 18/31] x86/speculation/mds: Mark cpu_buf_idle_clear " Valentin Schneider
2025-11-14 15:10 ` [PATCH v7 19/31] sched/clock, x86: Mark __sched_clock_stable " Valentin Schneider
2025-11-14 15:10 ` [PATCH v7 20/31] KVM: VMX: Mark vmx_l1d_should flush and vmx_l1d_flush_cond keys " Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 21/31] stackleack: Mark stack_erasing_bypass key " Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 22/31] objtool: Add noinstr validation for static branches/calls Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 23/31] module: Add MOD_NOINSTR_TEXT mem_type Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 24/31] context-tracking: Introduce work deferral infrastructure Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 25/31] context_tracking,x86: Defer kernel text patching IPIs Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 26/31] x86/jump_label: Add ASM support for static_branch_likely() Valentin Schneider
2025-11-14 15:14 ` [PATCH v7 27/31] x86/mm: Make INVPCID type macros available to assembly Valentin Schneider
2025-11-14 15:14 ` Valentin Schneider [this message]
2025-11-14 15:14 ` [RFC PATCH v7 29/31] x86/mm/pti: Implement a TLB flush immediately after a switch to kernel CR3 Valentin Schneider
2025-11-19 14:31   ` Andy Lutomirski
2025-11-19 15:44     ` Valentin Schneider
2025-11-19 17:31       ` Andy Lutomirski
2025-11-21 10:12         ` Valentin Schneider
2025-11-14 15:14 ` [RFC PATCH v7 30/31] x86/mm, mm/vmalloc: Defer kernel TLB flush IPIs under CONFIG_COALESCE_TLBI=y Valentin Schneider
2025-11-19 18:31   ` Dave Hansen
2025-11-19 18:33     ` Andy Lutomirski
2025-11-21 17:37     ` Valentin Schneider
2025-11-21 17:50       ` Dave Hansen
2025-11-14 15:14 ` [RFC PATCH v7 31/31] x86/entry: Add an option to coalesce TLB flushes Valentin Schneider
2025-11-14 16:20 ` [PATCH v7 00/31] context_tracking,x86: Defer some IPIs until a user->kernel transition Andy Lutomirski
2025-11-14 17:22   ` Andy Lutomirski
2025-11-14 18:14     ` Paul E. McKenney
2025-11-14 18:45       ` Andy Lutomirski
2025-11-14 20:03         ` Paul E. McKenney
2025-11-15  0:29           ` Andy Lutomirski
2025-11-15  2:30             ` Paul E. McKenney
2025-11-14 20:06         ` 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=20251114151428.1064524-8-vschneid@redhat.com \
    --to=vschneid@redhat.com \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=arnd@arndb.de \
    --cc=boqun.feng@gmail.com \
    --cc=bp@alien8.de \
    --cc=dan.carpenter@linaro.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=davem@davemloft.net \
    --cc=dwagner@suse.de \
    --cc=frederic@kernel.org \
    --cc=hpa@zytor.com \
    --cc=jannh@google.com \
    --cc=jbaron@akamai.com \
    --cc=joelagnelf@nvidia.com \
    --cc=josh@joshtriplett.org \
    --cc=jpoimboe@kernel.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=loongarch@lists.linux.dev \
    --cc=luto@kernel.org \
    --cc=masahiroy@kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=neeraj.upadhyay@kernel.org \
    --cc=oleg@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ptesarik@suse.com \
    --cc=rcu@vger.kernel.org \
    --cc=riel@surriel.com \
    --cc=rostedt@goodmis.org \
    --cc=samitolvanen@google.com \
    --cc=shenhan@google.com \
    --cc=sshegde@linux.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=urezki@gmail.com \
    --cc=williams@redhat.com \
    --cc=x86@kernel.org \
    --cc=ypodemsk@redhat.com \
    /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).