[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251024150333.GSaPuVRQYxH92zyrmO@fat_crate.local>
Date: Fri, 24 Oct 2025 17:03:33 +0200
From: Borislav Petkov <bp@...en8.de>
To: Yazen Ghannam <yazen.ghannam@....com>
Cc: x86@...nel.org, Tony Luck <tony.luck@...el.com>,
"Rafael J. Wysocki" <rafael@...nel.org>,
Len Brown <lenb@...nel.org>, linux-kernel@...r.kernel.org,
linux-edac@...r.kernel.org, Smita.KoralahalliChannabasappa@....com,
Qiuxu Zhuo <qiuxu.zhuo@...el.com>,
Nikolay Borisov <nik.borisov@...e.com>,
Bert Karwatzki <spasswolf@....de>, linux-acpi@...r.kernel.org
Subject: Re: [PATCH v7 2/8] x86/mce: Unify AMD DFR handler with MCA Polling
On Thu, Oct 16, 2025 at 04:37:47PM +0000, Yazen Ghannam wrote:
> @@ -1878,6 +1924,9 @@ static void __mcheck_cpu_init_prepare_banks(void)
>
> bitmap_fill(all_banks, MAX_NR_BANKS);
> machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
> +
> + if (mce_flags.smca)
> + machine_check_poll(MCP_DFR | MCP_QUEUE_LOG, &all_banks);
So you're going to run the poll again just for DFR errors?!
What for?
I think this is enough:
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 1482648c8508..7d6588195d56 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -299,7 +299,6 @@ enum mcp_flags {
MCP_TIMESTAMP = BIT(0), /* log time stamp */
MCP_UC = BIT(1), /* log uncorrected errors */
MCP_QUEUE_LOG = BIT(2), /* only queue to genpool */
- MCP_DFR = BIT(3), /* log deferred errors */
};
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 64aa7ecfd332..d9f9ee7db5c8 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -807,7 +807,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error)
/* APIC interrupt handler for deferred errors */
static void amd_deferred_error_interrupt(void)
{
- machine_check_poll(MCP_TIMESTAMP | MCP_DFR, &this_cpu_ptr(&mce_amd_data)->dfr_intr_banks);
+ machine_check_poll(MCP_TIMESTAMP, &this_cpu_ptr(&mce_amd_data)->dfr_intr_banks);
}
static void reset_block(struct threshold_block *block)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 39725df7d35c..7be062429ce3 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -779,17 +779,13 @@ static bool should_log_poll_error(enum mcp_flags flags, struct mce_hw_err *err)
{
struct mce *m = &err->m;
- if (flags & MCP_DFR)
+ if (mce_flags.smca)
return smca_should_log_poll_error(flags, err);
/* If this entry is not valid, ignore it. */
if (!(m->status & MCI_STATUS_VAL))
return false;
- /* Ignore deferred errors if not looking for them (MCP_DFR not set). */
- if (m->status & MCI_STATUS_DEFERRED)
- return false;
-
/*
* If we are logging everything (at CPU online) or this
* is a corrected error, then we must log it.
@@ -1924,9 +1920,6 @@ static void __mcheck_cpu_init_prepare_banks(void)
bitmap_fill(all_banks, MAX_NR_BANKS);
machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
-
- if (mce_flags.smca)
- machine_check_poll(MCP_DFR | MCP_QUEUE_LOG, &all_banks);
}
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
Powered by blists - more mailing lists