[tip: x86/microcode] x86/microcode: Sanitize __wait_for_cpus()

[tip-bot2 for Thomas Gleixner]

The following commit has been merged into the x86/microcode branch of tip:

Commit-ID:     7f21c0ed2cfefcbc6e2b383a6001c0c48a135ffe
Gitweb:        https://git.kernel.org/tip/7f21c0ed2cfefcbc6e2b383a6001c0c48a135ffe
Author:        Thomas Gleixner <tglx@xxxxxxxxxxxxx>
AuthorDate:    Mon, 02 Oct 2023 13:59:59 +02:00
Committer:     Borislav Petkov (AMD) <bp@xxxxxxxxx>
CommitterDate: Thu, 19 Oct 2023 15:56:17 +02:00

x86/microcode: Sanitize __wait_for_cpus()

The code is too complicated for no reason:

 - The return value is pointless as this is a strict boolean.

 - It's way simpler to count down from num_online_cpus() and check for
   zero.

  - The timeout argument is pointless as this is always one second.

  - Touching the NMI watchdog every 100ns does not make any sense, neither
    does checking every 100ns. This is really not a hotpath operation.

Preload the atomic counter with the number of online CPUs and simplify the
whole timeout logic. Delay for one microsecond and touch the NMI watchdog
once per millisecond.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Borislav Petkov (AMD) <bp@xxxxxxxxx>
Link: https://lore.kernel.org/r/20231002115903.204251527@xxxxxxxxxxxxx
---
 arch/x86/kernel/cpu/microcode/core.c | 39 +++++++++++----------------
 1 file changed, 17 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 63c4e12..9fd5a96 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -252,31 +252,26 @@ static struct platform_device	*microcode_pdev;
  *   requirement can be relaxed in the future. Right now, this is conservative
  *   and good.
  */
-#define SPINUNIT 100 /* 100 nsec */
+static atomic_t late_cpus_in, late_cpus_out;
 
-
-static atomic_t late_cpus_in;
-static atomic_t late_cpus_out;
-
-static int __wait_for_cpus(atomic_t *t, long long timeout)
+static bool wait_for_cpus(atomic_t *cnt)
 {
-	int all_cpus = num_online_cpus();
+	unsigned int timeout;
 
-	atomic_inc(t);
+	WARN_ON_ONCE(atomic_dec_return(cnt) < 0);
 
-	while (atomic_read(t) < all_cpus) {
-		if (timeout < SPINUNIT) {
-			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
-				all_cpus - atomic_read(t));
-			return 1;
-		}
+	for (timeout = 0; timeout < USEC_PER_SEC; timeout++) {
+		if (!atomic_read(cnt))
+			return true;
 
-		ndelay(SPINUNIT);
-		timeout -= SPINUNIT;
+		udelay(1);
 
-		touch_nmi_watchdog();
+		if (!(timeout % USEC_PER_MSEC))
+			touch_nmi_watchdog();
 	}
-	return 0;
+	/* Prevent the late comers from making progress and let them time out */
+	atomic_inc(cnt);
+	return false;
 }
 
 /*
@@ -294,7 +289,7 @@ static int __reload_late(void *info)
 	 * Wait for all CPUs to arrive. A load will not be attempted unless all
 	 * CPUs show up.
 	 * */
-	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
+	if (!wait_for_cpus(&late_cpus_in))
 		return -1;
 
 	/*
@@ -317,7 +312,7 @@ static int __reload_late(void *info)
 	}
 
 wait_for_siblings:
-	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC))
+	if (!wait_for_cpus(&late_cpus_out))
 		panic("Timeout during microcode update!\n");
 
 	/*
@@ -344,8 +339,8 @@ static int microcode_reload_late(void)
 	pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
 	pr_err("You should switch to early loading, if possible.\n");
 
-	atomic_set(&late_cpus_in,  0);
-	atomic_set(&late_cpus_out, 0);
+	atomic_set(&late_cpus_in, num_online_cpus());
+	atomic_set(&late_cpus_out, num_online_cpus());
 
 	/*
 	 * Take a snapshot before the microcode update in order to compare and