x86/ioapic: Add register level checks to detect bogus io-apic entries

With the recent changes to clear_IO_APIC_pin() which tries to
clear remoteIRR bit explicitly, some of the users started to see
"Unable to reset IRR for apic .." messages.

Close look shows that these are related to bogus IO-APIC entries
which return's all 1's for their io-apic registers. And the
above mentioned error messages are benign. But kernel should
have ignored such io-apic's in the first place.

Check if register 0, 1, 2 of the listed io-apic are all 1's and
ignore such io-apic.

Reported-by: Álvaro Castillo <midgoon@gmail.com>
Tested-by: Jon Dufresne <jon@jondufresne.org>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: yinghai@kernel.org
Cc: kernel-team@fedoraproject.org
Cc: Josh Boyer <jwboyer@redhat.com>
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/1331577393.31585.94.camel@sbsiddha-desk.sc.intel.com
[ Performed minor cleanup of affected code. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fb072754bc1d7a30c0eb2e0249a267182dda22aa..6d10a66fc5a9195772be6f6622fb09cd2aadc0a3 100644 (file)
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3967,18 +3967,36 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 static __init int bad_ioapic(unsigned long address)
 {
        if (nr_ioapics >= MAX_IO_APICS) {
-               printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded "
-                      "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics);
+               pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
+                       MAX_IO_APICS, nr_ioapics);
                return 1;
        }
        if (!address) {
-               printk(KERN_WARNING "WARNING: Bogus (zero) I/O APIC address"
-                      " found in table, skipping!\n");
+               pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n");
                return 1;
        }
        return 0;
 }
 
+static __init int bad_ioapic_register(int idx)
+{
+       union IO_APIC_reg_00 reg_00;
+       union IO_APIC_reg_01 reg_01;
+       union IO_APIC_reg_02 reg_02;
+
+       reg_00.raw = io_apic_read(idx, 0);
+       reg_01.raw = io_apic_read(idx, 1);
+       reg_02.raw = io_apic_read(idx, 2);
+
+       if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) {
+               pr_warn("I/O APIC 0x%x registers return all ones, skipping!\n",
+                       mpc_ioapic_addr(idx));
+               return 1;
+       }
+
+       return 0;
+}
+
 void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 {
        int idx = 0;
@@ -3995,6 +4013,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
        ioapics[idx].mp_config.apicaddr = address;
 
        set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+
+       if (bad_ioapic_register(idx)) {
+               clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+               return;
+       }
+
        ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
        ioapics[idx].mp_config.apicver = io_apic_get_version(idx);
 
@@ -4015,10 +4039,10 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
        if (gsi_cfg->gsi_end >= gsi_top)
                gsi_top = gsi_cfg->gsi_end + 1;
 
-       printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
-              "GSI %d-%d\n", idx, mpc_ioapic_id(idx),
-              mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
-              gsi_cfg->gsi_base, gsi_cfg->gsi_end);
+       pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n",
+               idx, mpc_ioapic_id(idx),
+               mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
+               gsi_cfg->gsi_base, gsi_cfg->gsi_end);
 
        nr_ioapics++;
 }