linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Valentin Schneider <vschneid@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	kvm@vger.kernel.org, linux-mm@kvack.org, bpf@vger.kernel.org,
	x86@kernel.org, rcu@vger.kernel.org,
	linux-kselftest@vger.kernel.org,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Masami Hiramatsu" <mhiramat@kernel.org>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"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>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Wanpeng Li" <wanpengli@tencent.com>,
	"Vitaly Kuznetsov" <vkuznets@redhat.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Frederic Weisbecker" <frederic@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	"Neeraj Upadhyay" <quic_neeraju@quicinc.com>,
	"Joel Fernandes" <joel@joelfernandes.org>,
	"Josh Triplett" <josh@joshtriplett.org>,
	"Boqun Feng" <boqun.feng@gmail.com>,
	"Mathieu Desnoyers" <mathieu.desnoyers@efficios.com>,
	"Lai Jiangshan" <jiangshanlai@gmail.com>,
	Zqiang <qiang.zhang1211@gmail.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Uladzislau Rezki" <urezki@gmail.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Lorenzo Stoakes" <lstoakes@gmail.com>,
	"Josh Poimboeuf" <jpoimboe@kernel.org>,
	"Jason Baron" <jbaron@akamai.com>,
	"Kees Cook" <keescook@chromium.org>,
	"Sami Tolvanen" <samitolvanen@google.com>,
	"Ard Biesheuvel" <ardb@kernel.org>,
	"Nicholas Piggin" <npiggin@gmail.com>,
	"Juerg Haefliger" <juerg.haefliger@canonical.com>,
	"Nicolas Saenz Julienne" <nsaenz@kernel.org>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	"Nadav Amit" <namit@vmware.com>,
	"Dan Carpenter" <error27@gmail.com>,
	"Chuang Wang" <nashuiliang@gmail.com>,
	"Yang Jihong" <yangjihong1@huawei.com>,
	"Petr Mladek" <pmladek@suse.com>,
	"Jason A. Donenfeld" <Jason@zx2c4.com>,
	"Song Liu" <song@kernel.org>,
	"Julian Pidancet" <julian.pidancet@oracle.com>,
	"Tom Lendacky" <thomas.lendacky@amd.com>,
	"Dionna Glaze" <dionnaglaze@google.com>,
	"Thomas Weißschuh" <linux@weissschuh.net>,
	"Juri Lelli" <juri.lelli@redhat.com>,
	"Marcelo Tosatti" <mtosatti@redhat.com>,
	"Yair Podemsky" <ypodemsk@redhat.com>,
	"Daniel Wagner" <dwagner@suse.de>,
	"Petr Tesarik" <ptesarik@suse.com>
Subject: Re: [RFC PATCH v3 13/15] context_tracking,x86: Add infrastructure to defer kernel TLBI
Date: Thu, 21 Nov 2024 17:26:09 +0100	[thread overview]
Message-ID: <20241121162609.GM24774@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <20241119153502.41361-14-vschneid@redhat.com>

On Tue, Nov 19, 2024 at 04:35:00PM +0100, Valentin Schneider wrote:

> @@ -418,9 +419,20 @@ static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask)
>  #endif
>  #endif /* !MODULE */
>  
> +#define __NATIVE_TLB_FLUSH_GLOBAL(suffix, cr4)		\
> +	native_write_cr4##suffix(cr4 ^ X86_CR4_PGE);	\
> +	native_write_cr4##suffix(cr4)
> +#define NATIVE_TLB_FLUSH_GLOBAL(cr4)         __NATIVE_TLB_FLUSH_GLOBAL(, cr4)
> +#define NATIVE_TLB_FLUSH_GLOBAL_NOINSTR(cr4) __NATIVE_TLB_FLUSH_GLOBAL(_noinstr, cr4)
> +
>  static inline void __native_tlb_flush_global(unsigned long cr4)
>  {
> -	native_write_cr4(cr4 ^ X86_CR4_PGE);
> -	native_write_cr4(cr4);
> +	NATIVE_TLB_FLUSH_GLOBAL(cr4);
>  }
> +
> +static inline void __native_tlb_flush_global_noinstr(unsigned long cr4)
> +{
> +	NATIVE_TLB_FLUSH_GLOBAL_NOINSTR(cr4);
> +}

How about something like this instead? I've only compile tested the
tlb.c bit, but it should get __flush_tlb_global() to be noinstr I think,
including the Xen bit (unless I missed something but then objtool should
complain).

---
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
index 734482afbf81..ff26136fcd9c 100644
--- a/arch/x86/include/asm/invpcid.h
+++ b/arch/x86/include/asm/invpcid.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_INVPCID
 #define _ASM_X86_INVPCID
 
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
+static __always_inline void __invpcid(unsigned long pcid, unsigned long addr,
 			     unsigned long type)
 {
 	struct { u64 d[2]; } desc = { { pcid, addr } };
@@ -13,7 +13,7 @@ static inline void __invpcid(unsigned long pcid, unsigned long addr,
 	 * mappings, we don't want the compiler to reorder any subsequent
 	 * memory accesses before the TLB flush.
 	 */
-	asm volatile("invpcid %[desc], %[type]"
+	asm_inline volatile("invpcid %[desc], %[type]"
 		     :: [desc] "m" (desc), [type] "r" (type) : "memory");
 }
 
@@ -23,26 +23,25 @@ static inline void __invpcid(unsigned long pcid, unsigned long addr,
 #define INVPCID_TYPE_ALL_NON_GLOBAL	3
 
 /* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
-				     unsigned long addr)
+static __always_inline void invpcid_flush_one(unsigned long pcid, unsigned long addr)
 {
 	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
 }
 
 /* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+static __always_inline void invpcid_flush_single_context(unsigned long pcid)
 {
 	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
 }
 
 /* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+static __always_inline void invpcid_flush_all(void)
 {
 	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
 }
 
 /* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+static __always_inline void invpcid_flush_all_nonglobals(void)
 {
 	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
 }
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index d4eb9e1d61b8..b3daee3d4667 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -75,7 +75,7 @@ static inline void __flush_tlb_local(void)
 	PVOP_VCALL0(mmu.flush_tlb_user);
 }
 
-static inline void __flush_tlb_global(void)
+static __always_inline void __flush_tlb_global(void)
 {
 	PVOP_VCALL0(mmu.flush_tlb_kernel);
 }
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a2dd24947eb8..b4c635b20538 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -357,8 +357,8 @@ MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
 	trace_xen_mc_entry(mcl, 4);
 }
 
-static inline void
-MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
+static __always_inline void
+__MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
 		int *success_count, domid_t domid)
 {
 	mcl->op = __HYPERVISOR_mmuext_op;
@@ -366,6 +366,13 @@ MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
 	mcl->args[1] = count;
 	mcl->args[2] = (unsigned long)success_count;
 	mcl->args[3] = domid;
+}
+
+static inline void
+MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
+		int *success_count, domid_t domid)
+{
+	__MULTI_mmuext_op(mcl, op, count, success_count, domid);
 
 	trace_xen_mc_entry(mcl, 4);
 }
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index b0d5a644fc84..0cfc00a34b7e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1168,9 +1168,10 @@ void flush_tlb_one_user(unsigned long addr)
 /*
  * Flush everything
  */
-STATIC_NOPV void native_flush_tlb_global(void)
+STATIC_NOPV noinstr void native_flush_tlb_global(void)
 {
 	unsigned long flags;
+	unsigned long cr4;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
@@ -1189,9 +1190,15 @@ STATIC_NOPV void native_flush_tlb_global(void)
 	 * be called from deep inside debugging code.)
 	 */
 	raw_local_irq_save(flags);
-
-	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));
-
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	asm volatile("mov %0,%%cr4": : "r" (cr4 ^ X86_CR4_PGE) : "memory");
+	asm volatile("mov %0,%%cr4": : "r" (cr4) : "memory");
+	/*
+	 * In lieu of not having the pinning crap, hard fail if CR4 doesn't
+	 * match the expected value. This ensures that anybody doing dodgy gets
+	 * the fallthrough check.
+	 */
+	BUG_ON(cr4 != this_cpu_read(cpu_tlbstate.cr4));
 	raw_local_irq_restore(flags);
 }
 
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 55a4996d0c04..4eb265eb867a 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1231,22 +1231,22 @@ static noinstr void xen_write_cr2(unsigned long cr2)
 	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
 }
 
-static noinline void xen_flush_tlb(void)
+static noinline noinstr void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
-	preempt_disable();
+	preempt_disable_notrace();
 
 	mcs = xen_mc_entry(sizeof(*op));
 
 	op = mcs.args;
 	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
-	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+	__MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(XEN_LAZY_MMU);
+	__xen_mc_issue(XEN_LAZY_MMU);
 
-	preempt_enable();
+	preempt_enable_notrace();
 }
 
 static void xen_flush_tlb_one_user(unsigned long addr)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index e1b782e823e6..31eddca45c27 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -235,15 +235,19 @@ static inline struct multicall_space xen_mc_entry(size_t args)
 void xen_mc_flush(void);
 
 /* Issue a multicall if we're not in a lazy mode */
-static inline void xen_mc_issue(unsigned mode)
+static __always_inline void __xen_mc_issue(unsigned mode)
 {
-	trace_xen_mc_issue(mode);
-
 	if ((xen_get_lazy_mode() & mode) == 0)
 		xen_mc_flush();
 
 	/* restore flags saved in xen_mc_batch */
-	local_irq_restore(this_cpu_read(xen_mc_irq_flags));
+	raw_local_irq_restore(this_cpu_read(xen_mc_irq_flags));
+}
+
+static inline void xen_mc_issue(unsigned mode)
+{
+	trace_xen_mc_issue(mode);
+	__xen_mc_issue(mode);
 }
 
 /* Set up a callback to be called when the current batch is flushed */


  parent reply	other threads:[~2024-11-21 16:26 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-19 15:34 [RFC PATCH v3 00/15] context_tracking,x86: Defer some IPIs until a user->kernel transition Valentin Schneider
2024-11-19 15:34 ` [RFC PATCH v3 01/15] objtool: Make validate_call() recognize indirect calls to pv_ops[] Valentin Schneider
2024-11-19 20:38   ` Josh Poimboeuf
2024-11-19 15:34 ` [RFC PATCH v3 02/15] objtool: Flesh out warning related to pv_ops[] calls Valentin Schneider
2024-11-19 20:38   ` Josh Poimboeuf
2024-11-19 15:34 ` [RFC PATCH v3 03/15] sched/clock: Make sched_clock_running __ro_after_init Valentin Schneider
2024-11-19 15:34 ` [RFC PATCH v3 04/15] rcu: Add a small-width RCU watching counter debug option Valentin Schneider
2024-11-20 14:50   ` Peter Zijlstra
2024-11-20 16:15     ` Valentin Schneider
2024-11-22 12:53   ` Paul E. McKenney
2024-11-22 13:56     ` Valentin Schneider
2024-11-19 15:34 ` [RFC PATCH v3 05/15] rcutorture: Make TREE04 use CONFIG_RCU_DYNTICKS_TORTURE Valentin Schneider
2024-11-22 12:54   ` Paul E. McKenney
2024-11-19 15:34 ` [RFC PATCH v3 06/15] jump_label: Add forceful jump label type Valentin Schneider
2024-11-19 23:39   ` Josh Poimboeuf
2024-11-20 14:56     ` Peter Zijlstra
2024-11-20 14:57       ` Peter Zijlstra
2024-11-20 16:55         ` Josh Poimboeuf
2024-11-21 11:00           ` Peter Zijlstra
2024-11-21 15:38             ` Josh Poimboeuf
2024-11-21 15:51             ` Valentin Schneider
2024-11-21 20:21               ` Josh Poimboeuf
2024-11-22 10:17                 ` Valentin Schneider
2024-11-20 16:24     ` Valentin Schneider
2024-11-20  0:05   ` Josh Poimboeuf
2024-11-20 10:22     ` Peter Zijlstra
2024-11-19 15:34 ` [RFC PATCH v3 07/15] x86/speculation/mds: Make mds_idle_clear forceful Valentin Schneider
2024-11-19 15:34 ` [RFC PATCH v3 08/15] sched/clock, x86: Make __sched_clock_stable forceful Valentin Schneider
2024-11-20 14:59   ` Peter Zijlstra
2024-11-20 16:34     ` Valentin Schneider
2024-11-21 11:02       ` Peter Zijlstra
2024-11-19 15:34 ` [RFC PATCH v3 09/15] objtool: Warn about non __ro_after_init static key usage in .noinstr Valentin Schneider
2024-11-20 17:13   ` Josh Poimboeuf
2024-11-19 15:34 ` [RFC PATCH v3 10/15] x86/alternatives: Record text_poke's of JUMP_TYPE_FORCEFUL labels Valentin Schneider
2024-11-19 15:34 ` [RFC PATCH v3 11/15] context-tracking: Introduce work deferral infrastructure Valentin Schneider
2024-11-20 10:54   ` Frederic Weisbecker
2024-11-20 14:23     ` Frederic Weisbecker
2024-11-20 17:10       ` Valentin Schneider
2024-11-20 17:30         ` Frederic Weisbecker
2024-11-22 14:56           ` Valentin Schneider
2024-11-24 21:46             ` Frederic Weisbecker
2024-11-29 16:40               ` Valentin Schneider
2024-11-29 22:19                 ` Frederic Weisbecker
2024-11-19 15:34 ` [RFC PATCH v3 12/15] context_tracking,x86: Defer kernel text patching IPIs Valentin Schneider
2024-11-20 15:13   ` Peter Zijlstra
2024-11-19 15:35 ` [RFC PATCH v3 13/15] context_tracking,x86: Add infrastructure to defer kernel TLBI Valentin Schneider
2024-11-20 15:22   ` Peter Zijlstra
2024-11-20 15:32     ` Peter Zijlstra
2024-11-20 17:24       ` Valentin Schneider
2024-11-21 11:12         ` Peter Zijlstra
2024-11-21 15:07           ` Dave Hansen
2024-11-21 15:30             ` Peter Zijlstra
2024-12-05 17:31               ` Petr Tesarik
2024-12-09 12:04                 ` Valentin Schneider
2024-12-09 12:12                   ` Peter Zijlstra
2024-12-09 14:42                     ` Petr Tesarik
2024-12-10 13:53                       ` Valentin Schneider
2024-12-10 14:42                         ` Petr Tesarik
2024-12-09 12:33                   ` Petr Tesarik
2024-11-21 16:26   ` Peter Zijlstra [this message]
2024-11-19 15:35 ` [RFC PATCH v3 14/15] x86/mm, mm/vmalloc: Defer flush_tlb_kernel_range() targeting NOHZ_FULL CPUs Valentin Schneider
2024-11-19 15:35 ` [RFC PATCH v3 15/15] context-tracking: Add a Kconfig to enable IPI deferral for NO_HZ_IDLE Valentin Schneider
2024-11-19 16:45 ` [RFC PATCH v3 00/15] context_tracking,x86: Defer some IPIs until a user->kernel transition Steven Rostedt
2024-11-19 22:51   ` Valentin Schneider

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=20241121162609.GM24774@noisy.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=Jason@zx2c4.com \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=boqun.feng@gmail.com \
    --cc=bp@alien8.de \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=dionnaglaze@google.com \
    --cc=dwagner@suse.de \
    --cc=error27@gmail.com \
    --cc=frederic@kernel.org \
    --cc=hch@infradead.org \
    --cc=hpa@zytor.com \
    --cc=jbaron@akamai.com \
    --cc=jiangshanlai@gmail.com \
    --cc=joel@joelfernandes.org \
    --cc=josh@joshtriplett.org \
    --cc=jpoimboe@kernel.org \
    --cc=juerg.haefliger@canonical.com \
    --cc=julian.pidancet@oracle.com \
    --cc=juri.lelli@redhat.com \
    --cc=keescook@chromium.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@weissschuh.net \
    --cc=lstoakes@gmail.com \
    --cc=luto@kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=namit@vmware.com \
    --cc=nashuiliang@gmail.com \
    --cc=npiggin@gmail.com \
    --cc=nsaenz@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=pmladek@suse.com \
    --cc=ptesarik@suse.com \
    --cc=qiang.zhang1211@gmail.com \
    --cc=quic_neeraju@quicinc.com \
    --cc=rcu@vger.kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=samitolvanen@google.com \
    --cc=song@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=urezki@gmail.com \
    --cc=vkuznets@redhat.com \
    --cc=vschneid@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=x86@kernel.org \
    --cc=yangjihong1@huawei.com \
    --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