Commit a43de489 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'ras-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull ras fixes from Thomas Gleixner:
 "A set of fixes for RAS/MCE:

   - Improve the error message when the kernel cannot recover from a MCE
     so the maximum amount of information gets provided.

   - Individually check MCE recovery features on SkyLake CPUs instead of
     assuming none when the CAPID0 register does not advertise the
     general ability for recovery.

   - Prevent MCE to output inconsistent messages which first show an
     error location and then claim that the source is unknown.

   - Prevent overwriting MCi_STATUS in the attempt to gather more
     information when a fatal MCE has alreay been detected. This leads
     to empty status values in the printout and failing to react
     promptly on the fatal event"

* 'ras-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Fix incorrect "Machine check from unknown source" message
  x86/mce: Do not overwrite MCi_STATUS in mce_no_way_out()
  x86/mce: Check for alternate indication of machine check recovery on Skylake
  x86/mce: Improve error message when kernel cannot recover
parents 6242258b 40c36e27

arch/x86/kernel/cpu/mcheck/mce-severity.c

+5 −0
Original line number Diff line number Diff line
@@ -160,6 +160,11 @@ static struct severity { 
		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),

		USER

		),

	MCESEV(

		PANIC, "Data load in unrecoverable area of kernel",

		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),

		KERNEL

		),

#endif

	MCESEV(

		PANIC, "Action required: unknown MCACOD",

arch/x86/kernel/cpu/mcheck/mce.c

+28 −16
Original line number Diff line number Diff line
@@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll); 
static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,

			  struct pt_regs *regs)

{

	int i, ret = 0;

	char *tmp;

	int i;



	for (i = 0; i < mca_cfg.banks; i++) {

		m->status = mce_rdmsrl(msr_ops.status(i));

		if (m->status & MCI_STATUS_VAL) {

		if (!(m->status & MCI_STATUS_VAL))

			continue;



		__set_bit(i, validp);

		if (quirk_no_way_out)

			quirk_no_way_out(i, m, regs);

		}



		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {

			mce_read_aux(m, i);

			*msg = tmp;

			ret = 1;

			return 1;

		}

	}

	return ret;

	return 0;

}



/*
@@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) 
		lmce = m.mcgstatus & MCG_STATUS_LMCES;



	/*

	 * Local machine check may already know that we have to panic.

	 * Broadcast machine check begins rendezvous in mce_start()

	 * Go through all banks in exclusion of the other CPUs. This way we

	 * don't report duplicated events on shared banks because the first one

	 * to see it will clear it. If this is a Local MCE, then no need to

	 * perform rendezvous.

	 * to see it will clear it.

	 */

	if (!lmce)

	if (lmce) {

		if (no_way_out)

			mce_panic("Fatal local machine check", &m, msg);

	} else {

		order = mce_start(&no_way_out);

	}



	for (i = 0; i < cfg->banks; i++) {

		__clear_bit(i, toclear);
@@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) 
			no_way_out = worst >= MCE_PANIC_SEVERITY;

	} else {

		/*

		 * Local MCE skipped calling mce_reign()

		 * If we found a fatal error, we need to panic here.

		 * If there was a fatal machine check we should have

		 * already called mce_panic earlier in this function.

		 * Since we re-read the banks, we might have found

		 * something new. Check again to see if we found a

		 * fatal error. We call "mce_severity()" again to

		 * make sure we have the right "msg".

		 */

		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)

			mce_panic("Machine check from unknown source",

				NULL, NULL);

		if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {

			mce_severity(&m, cfg->tolerant, &msg, true);

			mce_panic("Local fatal machine check!", &m, msg);

		}

	}



	/*

arch/x86/kernel/quirks.c

+9 −2
Original line number Diff line number Diff line
@@ -645,12 +645,19 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) 
/* Skylake */

static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)

{

	u32 capid0;

	u32 capid0, capid5;



	pci_read_config_dword(pdev, 0x84, &capid0);

	pci_read_config_dword(pdev, 0x98, &capid5);



	if ((capid0 & 0xc0) == 0xc0)

	/*

	 * CAPID0{7:6} indicate whether this is an advanced RAS SKU

	 * CAPID5{8:5} indicate that various NVDIMM usage modes are

	 * enabled, so memory machine check recovery is also enabled.

	 */

	if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))

		static_branch_inc(&mcsafe_key);



}

DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);

DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap);

CRA Git | Maintained and supported by SUSTech CRA and CCSE