linux-kernel - [PATCH 11/20] x86/mce/amd: Simplify DFR handler setup

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sat, 18 Nov 2023 13:32:39 -0600
From:   Yazen Ghannam <yazen.ghannam@....com>
To:     <linux-edac@...r.kernel.org>
CC:     <linux-kernel@...r.kernel.org>, <tony.luck@...el.com>,
        <x86@...nel.org>, <Avadhut.Naik@....com>,
        <Smita.KoralahalliChannabasappa@....com>,
        <amd-gfx@...ts.freedesktop.org>,
        <linux-trace-kernel@...r.kernel.org>,
        "Yazen Ghannam" <yazen.ghannam@....com>
Subject: [PATCH 11/20] x86/mce/amd: Simplify DFR handler setup

AMD systems with the SUCCOR feature can send an APIC LVT interrupt for
deferred errors. The LVT offset is 0x2 by convention, i.e. this is the
default as listed in hardware documentation.

However, the MCA registers may list a different LVT offset for this
interrupt. The kernel should honor the value from the hardware.

Simplify the enable flow by using the hardware-provided value. Any
conflicts will be caught by setup_APIC_eilvt(). Conflicts on production
systems can be handled as quirks, if needed.

Also, rename the function using a "verb-first" style.

Signed-off-by: Yazen Ghannam <yazen.ghannam@....com>
---
 arch/x86/kernel/cpu/mce/amd.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 4fddc5c8ae0e..9197badd9929 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -48,7 +48,6 @@
 #define MSR_CU_DEF_ERR		0xC0000410
 #define MASK_DEF_LVTOFF		0x000000F0
 #define MASK_DEF_INT_TYPE	0x00000006
-#define DEF_LVT_OFF		0x2
 #define DEF_INT_TYPE_APIC	0x2
 #define INTR_TYPE_APIC			0x1
 
@@ -581,19 +580,9 @@ static int setup_APIC_mce_threshold(int reserved, int new)
 	return reserved;
 }
 
-static int setup_APIC_deferred_error(int reserved, int new)
+static void enable_deferred_error_interrupt(void)
 {
-	if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
-					      APIC_EILVT_MSG_FIX, 0))
-		return new;
-
-	return reserved;
-}
-
-static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
-{
-	u32 low = 0, high = 0;
-	int def_offset = -1, def_new;
+	u32 low = 0, high = 0, def_new;
 
 	if (!mce_flags.succor)
 		return;
@@ -601,17 +590,15 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
 		return;
 
+	/*
+	 * Trust the value from hardware.
+	 * If there's a conflict, then setup_APIC_eilvt() will throw an error.
+	 */
 	def_new = (low & MASK_DEF_LVTOFF) >> 4;
-	if (!(low & MASK_DEF_LVTOFF)) {
-		pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
-		def_new = DEF_LVT_OFF;
-		low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
-	}
+	if (setup_APIC_eilvt(def_new, DEFERRED_ERROR_VECTOR, APIC_EILVT_MSG_FIX, 0))
+		return;
 
-	def_offset = setup_APIC_deferred_error(def_offset, def_new);
-	if ((def_offset == def_new) &&
-	    (deferred_error_int_vector != amd_deferred_error_interrupt))
-		deferred_error_int_vector = amd_deferred_error_interrupt;
+	deferred_error_int_vector = amd_deferred_error_interrupt;
 
 	if (!mce_flags.smca)
 		low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
@@ -777,7 +764,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 	u32 low = 0, high = 0, address = 0;
 	int offset = -1;
 
-	deferred_error_interrupt_enable(c);
+	enable_deferred_error_interrupt();
 
 	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
 		if (mce_flags.smca)
-- 
2.34.1