linux-alpha.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: peterz@infradead.org
Cc: juri.lelli@redhat.com,
	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
	rafael@kernel.org, catalin.marinas@arm.com,
	linus.walleij@linaro.org, nsekhar@ti.com, bsegall@google.com,
	guoren@kernel.org, pavel@ucw.cz, agordeev@linux.ibm.com,
	linux-arch@vger.kernel.org, linux-samsung-soc@vger.kernel.org,
	vincent.guittot@linaro.org, mpe@ellerman.id.au,
	chenhuacai@kernel.org, christophe.leroy@csgroup.eu,
	linux-acpi@vger.kernel.org, agross@kernel.org,
	geert@linux-m68k.org, linux-imx@nxp.com, vgupta@kernel.org,
	mattst88@gmail.com, mturquette@baylibre.com, sammy@sammy.net,
	pmladek@suse.com, linux-pm@vger.kernel.org,
	Sascha Hauer <s.hauer@pengutronix.de>,
	linux-um@lists.infradead.org, npiggin@gmail.com,
	tglx@linutronix.de, linux-omap@vger.kernel.org,
	dietmar.eggemann@arm.com, andreyknvl@gmail.com,
	gregkh@linuxfoundation.org, linux-kernel@vger.kernel.org,
	linux-perf-users@vger.kernel.
Subject: [PATCH v3 22/51] x86/tdx: Remove TDX_HCALL_ISSUE_STI
Date: Thu, 12 Jan 2023 20:43:36 +0100	[thread overview]
Message-ID: <20230112195540.682137572@infradead.org> (raw)
In-Reply-To: 20230112194314.845371875@infradead.org

Now that arch_cpu_idle() is expected to return with IRQs disabled,
avoid the useless STI/CLI dance.

Per the specs this is supposed to work, but nobody has yet relied up
this behaviour so broken implementations are possible.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 arch/x86/coco/tdx/tdcall.S        |   13 -------------
 arch/x86/coco/tdx/tdx.c           |   23 ++++-------------------
 arch/x86/include/asm/shared/tdx.h |    1 -
 3 files changed, 4 insertions(+), 33 deletions(-)

--- a/arch/x86/coco/tdx/tdcall.S
+++ b/arch/x86/coco/tdx/tdcall.S
@@ -139,19 +139,6 @@ SYM_FUNC_START(__tdx_hypercall)
 
 	movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx
 
-	/*
-	 * For the idle loop STI needs to be called directly before the TDCALL
-	 * that enters idle (EXIT_REASON_HLT case). STI instruction enables
-	 * interrupts only one instruction later. If there is a window between
-	 * STI and the instruction that emulates the HALT state, there is a
-	 * chance for interrupts to happen in this window, which can delay the
-	 * HLT operation indefinitely. Since this is the not the desired
-	 * result, conditionally call STI before TDCALL.
-	 */
-	testq $TDX_HCALL_ISSUE_STI, %rsi
-	jz .Lskip_sti
-	sti
-.Lskip_sti:
 	tdcall
 
 	/*
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -169,7 +169,7 @@ static int ve_instr_len(struct ve_info *
 	}
 }
 
-static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
+static u64 __cpuidle __halt(const bool irq_disabled)
 {
 	struct tdx_hypercall_args args = {
 		.r10 = TDX_HYPERCALL_STANDARD,
@@ -189,20 +189,14 @@ static u64 __cpuidle __halt(const bool i
 	 * can keep the vCPU in virtual HLT, even if an IRQ is
 	 * pending, without hanging/breaking the guest.
 	 */
-	return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0);
+	return __tdx_hypercall(&args, 0);
 }
 
 static int handle_halt(struct ve_info *ve)
 {
-	/*
-	 * Since non safe halt is mainly used in CPU offlining
-	 * and the guest will always stay in the halt state, don't
-	 * call the STI instruction (set do_sti as false).
-	 */
 	const bool irq_disabled = irqs_disabled();
-	const bool do_sti = false;
 
-	if (__halt(irq_disabled, do_sti))
+	if (__halt(irq_disabled))
 		return -EIO;
 
 	return ve_instr_len(ve);
@@ -210,22 +204,13 @@ static int handle_halt(struct ve_info *v
 
 void __cpuidle tdx_safe_halt(void)
 {
-	 /*
-	  * For do_sti=true case, __tdx_hypercall() function enables
-	  * interrupts using the STI instruction before the TDCALL. So
-	  * set irq_disabled as false.
-	  */
 	const bool irq_disabled = false;
-	const bool do_sti = true;
 
 	/*
 	 * Use WARN_ONCE() to report the failure.
 	 */
-	if (__halt(irq_disabled, do_sti))
+	if (__halt(irq_disabled))
 		WARN_ONCE(1, "HLT instruction emulation failed\n");
-
-	/* XXX I can't make sense of what @do_sti actually does */
-	raw_local_irq_disable();
 }
 
 static int read_msr(struct pt_regs *regs, struct ve_info *ve)
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -8,7 +8,6 @@
 #define TDX_HYPERCALL_STANDARD  0
 
 #define TDX_HCALL_HAS_OUTPUT	BIT(0)
-#define TDX_HCALL_ISSUE_STI	BIT(1)
 
 #define TDX_CPUID_LEAF_ID	0x21
 #define TDX_IDENT		"IntelTDX    "

  parent reply	other threads:[~2023-01-12 19:43 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-12 19:43 [PATCH v3 00/51] cpuidle,rcu: Clean up the mess Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 01/51] x86/perf/amd: Remove tracing from perf_lopwr_cb() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 02/51] x86/idle: Replace x86_idle with a static_call Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 03/51] cpuidle/poll: Ensure IRQ state is invariant Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 04/51] cpuidle: Move IRQ state validation Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 05/51] cpuidle,riscv: Push RCU-idle into driver Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 06/51] cpuidle,tegra: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 07/51] cpuidle,psci: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 08/51] cpuidle,imx6: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 09/51] cpuidle,omap3: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 10/51] cpuidle,armada: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 11/51] cpuidle,omap4: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 12/51] cpuidle,dt: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 13/51] cpuidle: Fix ct_idle_*() usage Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 14/51] cpuidle, cpu_pm: Remove RCU fiddling from cpu_pm_{enter, exit}() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 15/51] acpi_idle: Remove tracing Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 16/51] cpuidle: Annotate poll_idle() Peter Zijlstra
2023-01-20  9:56   ` Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 17/51] objtool/idle: Validate __cpuidle code as noinstr Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 18/51] cpuidle, intel_idle: Fix CPUIDLE_FLAG_IRQ_ENABLE *again* Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 19/51] cpuidle,intel_idle: Fix CPUIDLE_FLAG_INIT_XSTATE Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 20/51] cpuidle,intel_idle: Fix CPUIDLE_FLAG_IBRS Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 21/51] arch/idle: Change arch_cpu_idle() IRQ behaviour Peter Zijlstra
2023-01-12 19:43 ` Peter Zijlstra [this message]
2023-01-12 19:43 ` [PATCH v3 23/51] arm,smp: Remove trace_.*_rcuidle() usage Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 24/51] arm64,smp: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 25/51] printk: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 26/51] time/tick-broadcast: Remove RCU_NONIDLE usage Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 27/51] cpuidle, sched: Remove annotations from TIF_{POLLING_NRFLAG, NEED_RESCHED} Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 28/51] cpuidle,mwait: Make noinstr clean Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 29/51] cpuidle,tdx: Make tdx " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 30/51] cpuidle,xenpv: Make more PARAVIRT_XXL " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 31/51] cpuidle,nospec: Make " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 32/51] cpuidle,acpi: " Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 33/51] trace: Remove trace_hardirqs_{on,off}_caller() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 34/51] trace: WARN on rcuidle Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 35/51] trace,hardirq: No moar _rcuidle() tracing Peter Zijlstra
2023-01-17  4:24   ` Masami Hiramatsu
2023-01-17  8:53     ` Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 36/51] cpuidle,omap3: Use WFI for omap3_pm_idle() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 37/51] cpuidle,omap3: Push RCU-idle into omap_sram_idle() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 38/51] cpuidle,omap4: Push RCU-idle into omap4_enter_lowpower() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 39/51] arm,omap2: Use WFI for omap2_pm_idle() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 40/51] cpuidle,powerdomain: Remove trace_.*_rcuidle() Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 41/51] cpuidle,clk: " Peter Zijlstra
2023-01-12 20:28   ` Stephen Boyd
2023-01-12 19:43 ` [PATCH v3 42/51] ubsan: Fix objtool UACCESS warns Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 43/51] intel_idle: Add force_irq_on module param Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 44/51] entry, kasan, x86: Disallow overriding mem*() functions Peter Zijlstra
2023-01-12 19:43 ` [PATCH v3 45/51] sched: Always inline __this_cpu_preempt_check() Peter Zijlstra
2023-01-12 19:44 ` [PATCH v3 46/51] arm64,riscv,perf: Remove RCU_NONIDLE() usage Peter Zijlstra
2023-01-12 19:44 ` [PATCH v3 47/51] cpuidle: Ensure ct_cpuidle_enter() is always called from noinstr/__cpuidle Peter Zijlstra
2023-01-12 19:44 ` [PATCH v3 48/51] cpuidle, arch: Mark all ct_cpuidle_enter() callers __cpuidle Peter Zijlstra
2023-01-12 19:44 ` [PATCH v3 49/51] cpuidle, arch: Mark all regular cpuidle_state::enter methods __cpuidle Peter Zijlstra
2023-01-12 19:44 ` [PATCH v3 50/51] cpuidle: Comments about noinstr/__cpuidle Peter Zijlstra
2023-01-12 19:44 ` [PATCH v3 51/51] context_tracking: Fix noinstr vs KASAN Peter Zijlstra
2023-01-13 18:06 ` [PATCH v3 00/51] cpuidle,rcu: Clean up the mess Paul E. McKenney
2023-01-16 16:59 ` Mark Rutland
2023-01-17 10:26   ` Peter Zijlstra
2023-01-17 12:39     ` Sudeep Holla
2023-01-17 13:16     ` Mark Rutland
2023-01-17 14:21       ` Sudeep Holla
2023-01-17 15:35         ` Mark Rutland

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=20230112195540.682137572@infradead.org \
    --to=peterz@infradead.org \
    --cc=agordeev@linux.ibm.com \
    --cc=agross@kernel.org \
    --cc=andreyknvl@gmail.com \
    --cc=bsegall@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=chenhuacai@kernel.org \
    --cc=christophe.leroy@csgroup.eu \
    --cc=dietmar.eggemann@arm.com \
    --cc=geert@linux-m68k.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=guoren@kernel.org \
    --cc=juri.lelli@redhat.com \
    --cc=linus.walleij@linaro.org \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-imx@nxp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-omap@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel. \
    --cc=linux-pm@vger.kernel.org \
    --cc=linux-samsung-soc@vger.kernel.org \
    --cc=linux-um@lists.infradead.org \
    --cc=mattst88@gmail.com \
    --cc=mpe@ellerman.id.au \
    --cc=mturquette@baylibre.com \
    --cc=npiggin@gmail.com \
    --cc=nsekhar@ti.com \
    --cc=pavel@ucw.cz \
    --cc=pmladek@suse.com \
    --cc=rafael.j.wysocki@intel.com \
    --cc=rafael@kernel.org \
    --cc=s.hauer@pengutronix.de \
    --cc=sammy@sammy.net \
    --cc=tglx@linutronix.de \
    --cc=vgupta@kernel.org \
    --cc=vincent.guittot@linaro.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).