Commit a9429089 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'ras-core-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Thomas Gleixner:
 "RAS updates from Borislav Petkov:

   - Unmap a whole guest page if an MCE is encountered in it to avoid
     follow-on MCEs leading to the guest crashing, by Tony Luck.

     This change collided with the entry changes and the merge
     resolution would have been rather unpleasant. To avoid that the
     entry branch was merged in before applying this. The resulting code
     did not change over the rebase.

   - AMD MCE error thresholding machinery cleanup and hotplug
     sanitization, by Thomas Gleixner.

   - Change the MCE notifiers to denote whether they have handled the
     error and not break the chain early by returning NOTIFY_STOP, thus
     giving the opportunity for the later handlers in the chain to see
     it. By Tony Luck.

   - Add AMD family 0x17, models 0x60-6f support, by Alexander Monakov.

   - Last but not least, the usual round of fixes and improvements"

* tag 'ras-core-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/mce/dev-mcelog: Fix -Wstringop-truncation warning about strncpy()
  x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned
  EDAC/amd64: Add AMD family 17h model 60h PCI IDs
  hwmon: (k10temp) Add AMD family 17h model 60h PCI match
  x86/amd_nb: Add AMD family 17h model 60h PCI IDs
  x86/mcelog: Add compat_ioctl for 32-bit mcelog support
  x86/mce: Drop bogus comment about mce.kflags
  x86/mce: Fixup exception only for the correct MCEs
  EDAC: Drop the EDAC report status checks
  x86/mce: Add mce=print_all option
  x86/mce: Change default MCE logger to check mce->kflags
  x86/mce: Fix all mce notifiers to update the mce->kflags bitmask
  x86/mce: Add a struct mce.kflags field
  x86/mce: Convert the CEC to use the MCE notifier
  x86/mce: Rename "first" function as "early"
  x86/mce/amd, edac: Remove report_gart_errors
  x86/mce/amd: Make threshold bank setting hotplug robust
  x86/mce/amd: Cleanup threshold device remove path
  x86/mce/amd: Straighten CPU hotplug path
  x86/mce/amd: Sanitize thresholding device creation hotplug path
  ...
parents 076f14be 7ccddc46
...@@ -57,6 +57,7 @@ struct threshold_bank { ...@@ -57,6 +57,7 @@ struct threshold_bank {
/* initialized to the number of CPUs on the node sharing this bank */ /* initialized to the number of CPUs on the node sharing this bank */
refcount_t cpus; refcount_t cpus;
unsigned int shared;
}; };
struct amd_northbridge { struct amd_northbridge {
......
...@@ -127,6 +127,17 @@ ...@@ -127,6 +127,17 @@
#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
#define XEC(x, mask) (((x) >> 16) & mask)
/* mce.kflags flag bits for logging etc. */
#define MCE_HANDLED_CEC BIT_ULL(0)
#define MCE_HANDLED_UC BIT_ULL(1)
#define MCE_HANDLED_EXTLOG BIT_ULL(2)
#define MCE_HANDLED_NFIT BIT_ULL(3)
#define MCE_HANDLED_EDAC BIT_ULL(4)
#define MCE_HANDLED_MCELOG BIT_ULL(5)
#define MCE_IN_KERNEL_RECOV BIT_ULL(6)
/* /*
* This structure contains all data related to the MCE log. Also * This structure contains all data related to the MCE log. Also
* carries a signature to make it easier to find from external * carries a signature to make it easier to find from external
...@@ -142,14 +153,16 @@ struct mce_log_buffer { ...@@ -142,14 +153,16 @@ struct mce_log_buffer {
struct mce entry[]; struct mce entry[];
}; };
/* Highest last */
enum mce_notifier_prios { enum mce_notifier_prios {
MCE_PRIO_FIRST = INT_MAX, MCE_PRIO_LOWEST,
MCE_PRIO_UC = INT_MAX - 1, MCE_PRIO_MCELOG,
MCE_PRIO_EXTLOG = INT_MAX - 2, MCE_PRIO_EDAC,
MCE_PRIO_NFIT = INT_MAX - 3, MCE_PRIO_NFIT,
MCE_PRIO_EDAC = INT_MAX - 4, MCE_PRIO_EXTLOG,
MCE_PRIO_MCELOG = 1, MCE_PRIO_UC,
MCE_PRIO_LOWEST = 0, MCE_PRIO_EARLY,
MCE_PRIO_CEC
}; };
struct notifier_block; struct notifier_block;
...@@ -347,5 +360,4 @@ umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return ...@@ -347,5 +360,4 @@ umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return
#endif #endif
static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
#endif /* _ASM_X86_MCE_H */ #endif /* _ASM_X86_MCE_H */
...@@ -86,27 +86,34 @@ int set_direct_map_default_noflush(struct page *page); ...@@ -86,27 +86,34 @@ int set_direct_map_default_noflush(struct page *page);
extern int kernel_set_to_readonly; extern int kernel_set_to_readonly;
#ifdef CONFIG_X86_64 #ifdef CONFIG_X86_64
static inline int set_mce_nospec(unsigned long pfn) /*
* Prevent speculative access to the page by either unmapping
* it (if we do not require access to any part of the page) or
* marking it uncacheable (if we want to try to retrieve data
* from non-poisoned lines in the page).
*/
static inline int set_mce_nospec(unsigned long pfn, bool unmap)
{ {
unsigned long decoy_addr; unsigned long decoy_addr;
int rc; int rc;
/* /*
* Mark the linear address as UC to make sure we don't log more
* errors because of speculative access to the page.
* We would like to just call: * We would like to just call:
* set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1); * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
* but doing that would radically increase the odds of a * but doing that would radically increase the odds of a
* speculative access to the poison page because we'd have * speculative access to the poison page because we'd have
* the virtual address of the kernel 1:1 mapping sitting * the virtual address of the kernel 1:1 mapping sitting
* around in registers. * around in registers.
* Instead we get tricky. We create a non-canonical address * Instead we get tricky. We create a non-canonical address
* that looks just like the one we want, but has bit 63 flipped. * that looks just like the one we want, but has bit 63 flipped.
* This relies on set_memory_uc() properly sanitizing any __pa() * This relies on set_memory_XX() properly sanitizing any __pa()
* results with __PHYSICAL_MASK or PTE_PFN_MASK. * results with __PHYSICAL_MASK or PTE_PFN_MASK.
*/ */
decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
if (unmap)
rc = set_memory_np(decoy_addr, 1);
else
rc = set_memory_uc(decoy_addr, 1); rc = set_memory_uc(decoy_addr, 1);
if (rc) if (rc)
pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
......
...@@ -35,6 +35,7 @@ struct mce { ...@@ -35,6 +35,7 @@ struct mce {
__u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */
__u64 ppin; /* Protected Processor Inventory Number */ __u64 ppin; /* Protected Processor Inventory Number */
__u32 microcode; /* Microcode revision */ __u32 microcode; /* Microcode revision */
__u64 kflags; /* Internal kernel use */
}; };
#define MCE_GET_RECORD_LEN _IOR('M', 1, int) #define MCE_GET_RECORD_LEN _IOR('M', 1, int)
......
...@@ -18,9 +18,11 @@ ...@@ -18,9 +18,11 @@
#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450
#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0
#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480
#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c
#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 #define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654
...@@ -33,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = { ...@@ -33,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) },
{} {}
}; };
...@@ -50,6 +53,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { ...@@ -50,6 +53,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) },
...@@ -65,6 +69,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { ...@@ -65,6 +69,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
......
This diff is collapsed.
...@@ -160,29 +160,17 @@ void mce_log(struct mce *m) ...@@ -160,29 +160,17 @@ void mce_log(struct mce *m)
} }
EXPORT_SYMBOL_GPL(mce_log); EXPORT_SYMBOL_GPL(mce_log);
/*
* We run the default notifier if we have only the UC, the first and the
* default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
* notifiers registered on the chain.
*/
#define NUM_DEFAULT_NOTIFIERS 3
static atomic_t num_notifiers;
void mce_register_decode_chain(struct notifier_block *nb) void mce_register_decode_chain(struct notifier_block *nb)
{ {
if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC)) if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
return; return;
atomic_inc(&num_notifiers);
blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
} }
EXPORT_SYMBOL_GPL(mce_register_decode_chain); EXPORT_SYMBOL_GPL(mce_register_decode_chain);
void mce_unregister_decode_chain(struct notifier_block *nb) void mce_unregister_decode_chain(struct notifier_block *nb)
{ {
atomic_dec(&num_notifiers);
blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
} }
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
...@@ -265,6 +253,7 @@ static void __print_mce(struct mce *m) ...@@ -265,6 +253,7 @@ static void __print_mce(struct mce *m)
} }
pr_cont("\n"); pr_cont("\n");
/* /*
* Note this output is parsed by external tools and old fields * Note this output is parsed by external tools and old fields
* should not be changed. * should not be changed.
...@@ -531,6 +520,14 @@ bool mce_is_memory_error(struct mce *m) ...@@ -531,6 +520,14 @@ bool mce_is_memory_error(struct mce *m)
} }
EXPORT_SYMBOL_GPL(mce_is_memory_error); EXPORT_SYMBOL_GPL(mce_is_memory_error);
static bool whole_page(struct mce *m)
{
if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV))
return true;
return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT;
}
bool mce_is_correctable(struct mce *m) bool mce_is_correctable(struct mce *m)
{ {
if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
...@@ -546,22 +543,7 @@ bool mce_is_correctable(struct mce *m) ...@@ -546,22 +543,7 @@ bool mce_is_correctable(struct mce *m)
} }
EXPORT_SYMBOL_GPL(mce_is_correctable); EXPORT_SYMBOL_GPL(mce_is_correctable);
static bool cec_add_mce(struct mce *m) static int mce_early_notifier(struct notifier_block *nb, unsigned long val,
{
if (!m)
return false;
/* We eat only correctable DRAM errors with usable addresses. */
if (mce_is_memory_error(m) &&
mce_is_correctable(m) &&
mce_usable_address(m))
if (!cec_add_elem(m->addr >> PAGE_SHIFT))
return true;
return false;
}
static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
void *data) void *data)
{ {
struct mce *m = (struct mce *)data; struct mce *m = (struct mce *)data;
...@@ -569,9 +551,6 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val, ...@@ -569,9 +551,6 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
if (!m) if (!m)
return NOTIFY_DONE; return NOTIFY_DONE;
if (cec_add_mce(m))
return NOTIFY_STOP;
/* Emit the trace record: */ /* Emit the trace record: */
trace_mce_record(m); trace_mce_record(m);
...@@ -582,9 +561,9 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val, ...@@ -582,9 +561,9 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
return NOTIFY_DONE; return NOTIFY_DONE;
} }
static struct notifier_block first_nb = { static struct notifier_block early_nb = {
.notifier_call = mce_first_notifier, .notifier_call = mce_early_notifier,
.priority = MCE_PRIO_FIRST, .priority = MCE_PRIO_EARLY,
}; };
static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
...@@ -601,8 +580,10 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, ...@@ -601,8 +580,10 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
return NOTIFY_DONE; return NOTIFY_DONE;
pfn = mce->addr >> PAGE_SHIFT; pfn = mce->addr >> PAGE_SHIFT;
if (!memory_failure(pfn, 0)) if (!memory_failure(pfn, 0)) {
set_mce_nospec(pfn); set_mce_nospec(pfn, whole_page(mce));
mce->kflags |= MCE_HANDLED_UC;
}
return NOTIFY_OK; return NOTIFY_OK;
} }
...@@ -620,9 +601,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, ...@@ -620,9 +601,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
if (!m) if (!m)
return NOTIFY_DONE; return NOTIFY_DONE;
if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS) if (mca_cfg.print_all || !m->kflags)
return NOTIFY_DONE;
__print_mce(m); __print_mce(m);
return NOTIFY_DONE; return NOTIFY_DONE;
...@@ -1202,11 +1181,12 @@ static void kill_me_maybe(struct callback_head *cb) ...@@ -1202,11 +1181,12 @@ static void kill_me_maybe(struct callback_head *cb)
int flags = MF_ACTION_REQUIRED; int flags = MF_ACTION_REQUIRED;
pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
if (!(p->mce_status & MCG_STATUS_RIPV))
if (!p->mce_ripv)
flags |= MF_MUST_KILL; flags |= MF_MUST_KILL;
if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) { if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
set_mce_nospec(p->mce_addr >> PAGE_SHIFT); set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
return; return;
} }
...@@ -1360,15 +1340,27 @@ void noinstr do_machine_check(struct pt_regs *regs) ...@@ -1360,15 +1340,27 @@ void noinstr do_machine_check(struct pt_regs *regs)
BUG_ON(!on_thread_stack() || !user_mode(regs)); BUG_ON(!on_thread_stack() || !user_mode(regs));
current->mce_addr = m.addr; current->mce_addr = m.addr;
current->mce_status = m.mcgstatus; current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV);
current->mce_whole_page = whole_page(&m);
current->mce_kill_me.func = kill_me_maybe; current->mce_kill_me.func = kill_me_maybe;
if (kill_it) if (kill_it)
current->mce_kill_me.func = kill_me_now; current->mce_kill_me.func = kill_me_now;
task_work_add(current, &current->mce_kill_me, true); task_work_add(current, &current->mce_kill_me, true);
} else { } else {
/*
* Handle an MCE which has happened in kernel space but from
* which the kernel can recover: ex_has_fault_handler() has
* already verified that the rIP at which the error happened is
* a rIP from which the kernel can recover (by jumping to
* recovery code specified in _ASM_EXTABLE_FAULT()) and the
* corresponding exception handler which would do that is the
* proper one.
*/
if (m.kflags & MCE_IN_KERNEL_RECOV) {
if (!fixup_exception(regs, X86_TRAP_MC, 0, 0)) if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
mce_panic("Failed kernel mode recovery", &m, msg); mce_panic("Failed kernel mode recovery", &m, msg);
} }
}
} }
EXPORT_SYMBOL_GPL(do_machine_check); EXPORT_SYMBOL_GPL(do_machine_check);
...@@ -1758,6 +1750,7 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) ...@@ -1758,6 +1750,7 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR);
mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA);
mce_flags.amd_threshold = 1;
if (mce_flags.smca) { if (mce_flags.smca) {
msr_ops.ctl = smca_ctl_reg; msr_ops.ctl = smca_ctl_reg;
...@@ -2055,6 +2048,7 @@ void mce_disable_bank(int bank) ...@@ -2055,6 +2048,7 @@ void mce_disable_bank(int bank)
* mce=no_cmci Disables CMCI * mce=no_cmci Disables CMCI
* mce=no_lmce Disables LMCE * mce=no_lmce Disables LMCE
* mce=dont_log_ce Clears corrected events silently, no log created for CEs. * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
* mce=print_all Print all machine check logs to console
* mce=ignore_ce Disables polling and CMCI, corrected events are not cleared. * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
* mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
* monarchtimeout is how long to wait for other CPUs on machine * monarchtimeout is how long to wait for other CPUs on machine
...@@ -2083,6 +2077,8 @@ static int __init mcheck_enable(char *str) ...@@ -2083,6 +2077,8 @@ static int __init mcheck_enable(char *str)
cfg->lmce_disabled = 1; cfg->lmce_disabled = 1;
else if (!strcmp(str, "dont_log_ce")) else if (!strcmp(str, "dont_log_ce"))
cfg->dont_log_ce = true; cfg->dont_log_ce = true;
else if (!strcmp(str, "print_all"))
cfg->print_all = true;
else if (!strcmp(str, "ignore_ce")) else if (!strcmp(str, "ignore_ce"))
cfg->ignore_ce = true; cfg->ignore_ce = true;
else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
...@@ -2105,7 +2101,7 @@ __setup("mce", mcheck_enable); ...@@ -2105,7 +2101,7 @@ __setup("mce", mcheck_enable);
int __init mcheck_init(void) int __init mcheck_init(void)
{ {
mcheck_intel_therm_init(); mcheck_intel_therm_init();
mce_register_decode_chain(&first_nb); mce_register_decode_chain(&early_nb);
mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_uc_nb);
mce_register_decode_chain(&mce_default_nb); mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity(); mcheck_vendor_init_severity();
...@@ -2349,6 +2345,7 @@ static ssize_t store_int_with_restart(struct device *s, ...@@ -2349,6 +2345,7 @@ static ssize_t store_int_with_restart(struct device *s,
static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all);
static struct dev_ext_attribute dev_attr_check_interval = { static struct dev_ext_attribute dev_attr_check_interval = {
__ATTR(check_interval, 0644, device_show_int, store_int_with_restart), __ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
...@@ -2373,6 +2370,7 @@ static struct device_attribute *mce_device_attrs[] = { ...@@ -2373,6 +2370,7 @@ static struct device_attribute *mce_device_attrs[] = {
#endif #endif
&dev_attr_monarch_timeout.attr, &dev_attr_monarch_timeout.attr,
&dev_attr_dont_log_ce.attr, &dev_attr_dont_log_ce.attr,
&dev_attr_print_all.attr,
&dev_attr_ignore_ce.attr, &dev_attr_ignore_ce.attr,
&dev_attr_cmci_disabled.attr, &dev_attr_cmci_disabled.attr,
NULL NULL
...@@ -2545,6 +2543,13 @@ static __init void mce_init_banks(void) ...@@ -2545,6 +2543,13 @@ static __init void mce_init_banks(void)
} }
} }
/*
* When running on XEN, this initcall is ordered against the XEN mcelog
* initcall:
*
* device_initcall(xen_late_init_mcelog);
* device_initcall_sync(mcheck_init_device);
*/
static __init int mcheck_init_device(void) static __init int mcheck_init_device(void)
{ {
int err; int err;
...@@ -2576,6 +2581,10 @@ static __init int mcheck_init_device(void) ...@@ -2576,6 +2581,10 @@ static __init int mcheck_init_device(void)
if (err) if (err)
goto err_out_mem; goto err_out_mem;
/*
* Invokes mce_cpu_online() on all CPUs which are online when
* the state is installed.
*/
err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online", err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
mce_cpu_online, mce_cpu_pre_down); mce_cpu_online, mce_cpu_pre_down);
if (err < 0) if (err < 0)
...@@ -2665,7 +2674,6 @@ static int __init mcheck_late_init(void) ...@@ -2665,7 +2674,6 @@ static int __init mcheck_late_init(void)
static_branch_inc(&mcsafe_key); static_branch_inc(&mcsafe_key);
mcheck_debugfs_init(); mcheck_debugfs_init();
cec_init();
/* /*
* Flush out everything that has been logged during early boot, now that * Flush out everything that has been logged during early boot, now that
......
...@@ -39,6 +39,9 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, ...@@ -39,6 +39,9 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
struct mce *mce = (struct mce *)data; struct mce *mce = (struct mce *)data;
unsigned int entry; unsigned int entry;
if (mce->kflags & MCE_HANDLED_CEC)
return NOTIFY_DONE;
mutex_lock(&mce_chrdev_read_mutex); mutex_lock(&mce_chrdev_read_mutex);
entry = mcelog->next; entry = mcelog->next;
...@@ -56,6 +59,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, ...@@ -56,6 +59,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
memcpy(mcelog->entry + entry, mce, sizeof(struct mce)); memcpy(mcelog->entry + entry, mce, sizeof(struct mce));
mcelog->entry[entry].finished = 1; mcelog->entry[entry].finished = 1;
mcelog->entry[entry].kflags = 0;
/* wake processes polling /dev/mcelog */ /* wake processes polling /dev/mcelog */
wake_up_interruptible(&mce_chrdev_wait); wake_up_interruptible(&mce_chrdev_wait);
...@@ -63,6 +67,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, ...@@ -63,6 +67,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
unlock: unlock:
mutex_unlock(&mce_chrdev_read_mutex); mutex_unlock(&mce_chrdev_read_mutex);
mce->kflags |= MCE_HANDLED_MCELOG;
return NOTIFY_OK; return NOTIFY_OK;
} }
...@@ -324,6 +329,7 @@ static const struct file_operations mce_chrdev_ops = { ...@@ -324,6 +329,7 @@ static const struct file_operations mce_chrdev_ops = {
.write = mce_chrdev_write, .write = mce_chrdev_write,
.poll = mce_chrdev_poll, .poll = mce_chrdev_poll,
.unlocked_ioctl = mce_chrdev_ioctl, .unlocked_ioctl = mce_chrdev_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.llseek = no_llseek, .llseek = no_llseek,
}; };
...@@ -343,7 +349,7 @@ static __init int dev_mcelog_init_device(void) ...@@ -343,7 +349,7 @@ static __init int dev_mcelog_init_device(void)
if (!mcelog) if (!mcelog)
return -ENOMEM; return -ENOMEM;
strncpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature)); memcpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature));
mcelog->len = mce_log_len; mcelog->len = mce_log_len;
mcelog->recordlen = sizeof(struct mce); mcelog->recordlen = sizeof(struct mce);
......
...@@ -119,6 +119,7 @@ struct mca_config { ...@@ -119,6 +119,7 @@ struct mca_config {
bool dont_log_ce; bool dont_log_ce;
bool cmci_disabled; bool cmci_disabled;
bool ignore_ce; bool ignore_ce;
bool print_all;
__u64 lmce_disabled : 1, __u64 lmce_disabled : 1,
disabled : 1, disabled : 1,
...@@ -158,7 +159,10 @@ struct mce_vendor_flags { ...@@ -158,7 +159,10 @@ struct mce_vendor_flags {
*/ */
smca : 1, smca : 1,
__reserved_0 : 61; /* AMD-style error thresholding banks present. */
amd_threshold : 1,
__reserved_0 : 60;
}; };
extern struct mce_vendor_flags mce_flags; extern struct mce_vendor_flags mce_flags;
......
...@@ -213,8 +213,12 @@ static int error_context(struct mce *m) ...@@ -213,8 +213,12 @@ static int error_context(struct mce *m)
{ {
if ((m->cs & 3) == 3) if ((m->cs & 3) == 3)
return IN_USER; return IN_USER;
if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip))
if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) {
m->kflags |= MCE_IN_KERNEL_RECOV;
return IN_KERNEL_RECOV; return IN_KERNEL_RECOV;
}
return IN_KERNEL; return IN_KERNEL;
} }
......
...@@ -42,8 +42,6 @@ struct extlog_l1_head { ...@@ -42,8 +42,6 @@ struct extlog_l1_head {
u8 rev1[12]; u8 rev1[12];
}; };
static int old_edac_report_status;
static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295"; static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";
/* L1 table related physical address */ /* L1 table related physical address */
...@@ -146,7 +144,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, ...@@ -146,7 +144,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
static u32 err_seq; static u32 err_seq;
estatus = extlog_elog_entry_check(cpu, bank); estatus = extlog_elog_entry_check(cpu, bank);
if (estatus == NULL) if (estatus == NULL || (mce->kflags & MCE_HANDLED_CEC))
return NOTIFY_DONE; return NOTIFY_DONE;
memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN); memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
...@@ -176,7 +174,8 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, ...@@ -176,7 +174,8 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
} }
out: out:
return NOTIFY_STOP; mce->kflags |= MCE_HANDLED_EXTLOG;
return NOTIFY_OK;
} }
static bool __init extlog_get_l1addr(void) static bool __init extlog_get_l1addr(void)
...@@ -228,11 +227,6 @@ static int __init extlog_init(void) ...@@ -228,11 +227,6 @@ static int __init extlog_init(void)
if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr()) if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr())
return -ENODEV; return -ENODEV;
if (edac_get_report_status() == EDAC_REPORTING_FORCE) {
pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
return -EPERM;
}
rc = -EINVAL; rc = -EINVAL;
/* get L1 header to fetch necessary information */ /* get L1 header to fetch necessary information */
l1_hdr_size = sizeof(struct extlog_l1_head); l1_hdr_size = sizeof(struct extlog_l1_head);
...@@ -280,12 +274,6 @@ static int __init extlog_init(void) ...@@ -280,12 +274,6 @@ static int __init extlog_init(void)
if (elog_buf == NULL) if (elog_buf == NULL)
goto err_release_elog; goto err_release_elog;
/*
* eMCA event report method has higher priority than EDAC method,
* unless EDAC event report method is mandatory.
*/
old_edac_report_status = edac_get_report_status();
edac_set_report_status(EDAC_REPORTING_DISABLED);
mce_register_decode_chain(&extlog_mce_dec); mce_register_decode_chain(&extlog_mce_dec);
/* enable OS to be involved to take over management from BIOS */ /* enable OS to be involved to take over management from BIOS */
((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN; ((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
...@@ -307,7 +295,6 @@ static int __init extlog_init(void) ...@@ -307,7 +295,6 @@ static int __init extlog_init(void)
static void __exit extlog_exit(void) static void __exit extlog_exit(void)
{ {
edac_set_report_status(old_edac_report_status);
mce_unregister_decode_chain(&extlog_mce_dec); mce_unregister_decode_chain(&extlog_mce_dec);
((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
if (extlog_l1_addr) if (extlog_l1_addr)
......
...@@ -76,6 +76,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, ...@@ -76,6 +76,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
*/ */
acpi_nfit_ars_rescan(acpi_desc, 0); acpi_nfit_ars_rescan(acpi_desc, 0);
} }
mce->kflags |= MCE_HANDLED_NFIT;
break; break;
} }
......
...@@ -4,9 +4,6 @@ ...@@ -4,9 +4,6 @@
static struct edac_pci_ctl_info *pci_ctl; static struct edac_pci_ctl_info *pci_ctl;
static int report_gart_errors;
module_param(report_gart_errors, int, 0644);
/* /*
* Set by command line parameter. If BIOS has enabled the ECC, this override is * Set by command line parameter. If BIOS has enabled the ECC, this override is
* cleared to prevent re-enabling the hardware by this driver. * cleared to prevent re-enabling the hardware by this driver.
...@@ -2319,6 +2316,16 @@ static struct amd64_family_type family_types[] = { ...@@ -2319,6 +2316,16 @@ static struct amd64_family_type family_types[] = {
.dbam_to_cs = f17_addr_mask_to_cs_size, .dbam_to_cs = f17_addr_mask_to_cs_size,
} }
}, },
[F17_M60H_CPUS] = {
.ctl_name = "F17h_M60h",
.f0_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F0,
.f6_id = PCI_DEVICE_ID_AMD_17H_M60H_DF_F6,
.max_mcs = 2,
.ops = {
.early_channel_count = f17_early_channel_count,
.dbam_to_cs = f17_addr_mask_to_cs_size,
}
},
[F17_M70H_CPUS] = { [F17_M70H_CPUS] = {
.ctl_name = "F17h_M70h", .ctl_name = "F17h_M70h",
.f0_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F0, .f0_id = PCI_DEVICE_ID_AMD_17H_M70H_DF_F0,
...@@ -3357,6 +3364,10 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) ...@@ -3357,6 +3364,10 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
fam_type = &family_types[F17_M30H_CPUS]; fam_type = &family_types[F17_M30H_CPUS];
pvt->ops = &family_types[F17_M30H_CPUS].ops; pvt->ops = &family_types[F17_M30H_CPUS].ops;
break; break;
} else if (pvt->model >= 0x60 && pvt->model <= 0x6f) {
fam_type = &family_types[F17_M60H_CPUS];
pvt->ops = &family_types[F17_M60H_CPUS].ops;
break;
} else if (pvt->model >= 0x70 && pvt->model <= 0x7f) { } else if (pvt->model >= 0x70 && pvt->model <= 0x7f) {
fam_type = &family_types[F17_M70H_CPUS]; fam_type = &family_types[F17_M70H_CPUS];
pvt->ops = &family_types[F17_M70H_CPUS].ops; pvt->ops = &family_types[F17_M70H_CPUS].ops;
...@@ -3681,9 +3692,6 @@ static int __init amd64_edac_init(void) ...@@ -3681,9 +3692,6 @@ static int __init amd64_edac_init(void)
} }
/* register stuff with EDAC MCE */ /* register stuff with EDAC MCE */
if (report_gart_errors)
amd_report_gart_errors(true);
if (boot_cpu_data.x86 >= 0x17) if (boot_cpu_data.x86 >= 0x17)
amd_register_ecc_decoder(decode_umc_error); amd_register_ecc_decoder(decode_umc_error);
else else
...@@ -3718,8 +3726,6 @@ static void __exit amd64_edac_exit(void) ...@@ -3718,8 +3726,6 @@ static void __exit amd64_edac_exit(void)
edac_pci_release_generic_ctl(pci_ctl); edac_pci_release_generic_ctl(pci_ctl);
/* unregister from EDAC MCE */ /* unregister from EDAC MCE */
amd_report_gart_errors(false);
if (boot_cpu_data.x86 >= 0x17) if (boot_cpu_data.x86 >= 0x17)
amd_unregister_ecc_decoder(decode_umc_error); amd_unregister_ecc_decoder(decode_umc_error);
else else
......
...@@ -120,6 +120,8 @@ ...@@ -120,6 +120,8 @@
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F0 0x1490 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F0 0x1490
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F0 0x1448
#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F6 0x144e
#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F0 0x1440 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F0 0x1440
#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F6 0x1446 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F6 0x1446
#define PCI_DEVICE_ID_AMD_19H_DF_F0 0x1650 #define PCI_DEVICE_ID_AMD_19H_DF_F0 0x1650
...@@ -293,6 +295,7 @@ enum amd_families { ...@@ -293,6 +295,7 @@ enum amd_families {
F17_CPUS, F17_CPUS,
F17_M10H_CPUS, F17_M10H_CPUS,
F17_M30H_CPUS, F17_M30H_CPUS,
F17_M60H_CPUS,
F17_M70H_CPUS, F17_M70H_CPUS,
F19_CPUS, F19_CPUS,
NUM_FAMILIES, NUM_FAMILIES,
......
...@@ -43,8 +43,6 @@ ...@@ -43,8 +43,6 @@
int edac_op_state = EDAC_OPSTATE_INVAL; int edac_op_state = EDAC_OPSTATE_INVAL;
EXPORT_SYMBOL_GPL(edac_op_state); EXPORT_SYMBOL_GPL(edac_op_state);
static int edac_report = EDAC_REPORTING_ENABLED;
/* lock to memory controller's control array */ /* lock to memory controller's control array */
static DEFINE_MUTEX(mem_ctls_mutex); static DEFINE_MUTEX(mem_ctls_mutex);
static LIST_HEAD(mc_devices); static LIST_HEAD(mc_devices);
...@@ -60,65 +58,6 @@ static struct mem_ctl_info *error_desc_to_mci(struct edac_raw_error_desc *e) ...@@ -60,65 +58,6 @@ static struct mem_ctl_info *error_desc_to_mci(struct edac_raw_error_desc *e)
return container_of(e, struct mem_ctl_info, error_desc); return container_of(e, struct mem_ctl_info, error_desc);
} }
int edac_get_report_status(void)
{
return edac_report;
}
EXPORT_SYMBOL_GPL(edac_get_report_status);
void edac_set_report_status(int new)
{
if (new == EDAC_REPORTING_ENABLED ||
new == EDAC_REPORTING_DISABLED ||
new == EDAC_REPORTING_FORCE)
edac_report = new;
}
EXPORT_SYMBOL_GPL(edac_set_report_status);
static int edac_report_set(const char *str, const struct kernel_param *kp)
{
if (!str)
return -EINVAL;
if (!strncmp(str, "on", 2))
edac_report = EDAC_REPORTING_ENABLED;
else if (!strncmp(str, "off", 3))
edac_report = EDAC_REPORTING_DISABLED;
else if (!strncmp(str, "force", 5))
edac_report = EDAC_REPORTING_FORCE;
return 0;
}
static int edac_report_get(char *buffer, const struct kernel_param *kp)
{
int ret = 0;
switch (edac_report) {
case EDAC_REPORTING_ENABLED:
ret = sprintf(buffer, "on");
break;
case EDAC_REPORTING_DISABLED:
ret = sprintf(buffer, "off");
break;
case EDAC_REPORTING_FORCE:
ret = sprintf(buffer, "force");
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
static const struct kernel_param_ops edac_report_ops = {
.set = edac_report_set,
.get = edac_report_get,
};
module_param_cb(edac_report, &edac_report_ops, &edac_report, 0644);
unsigned int edac_dimm_info_location(struct dimm_info *dimm, char *buf, unsigned int edac_dimm_info_location(struct dimm_info *dimm, char *buf,
unsigned int len) unsigned int len)
{ {
......
...@@ -1815,7 +1815,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, ...@@ -1815,7 +1815,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
struct mem_ctl_info *mci; struct mem_ctl_info *mci;
i7_dev = get_i7core_dev(mce->socketid); i7_dev = get_i7core_dev(mce->socketid);
if (!i7_dev) if (!i7_dev || (mce->kflags & MCE_HANDLED_CEC))
return NOTIFY_DONE; return NOTIFY_DONE;
mci = i7_dev->mci; mci = i7_dev->mci;
...@@ -1834,7 +1834,8 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, ...@@ -1834,7 +1834,8 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
i7core_check_error(mci, mce); i7core_check_error(mci, mce);
/* Advise mcelog that the errors were handled */ /* Advise mcelog that the errors were handled */
return NOTIFY_STOP; mce->kflags |= MCE_HANDLED_EDAC;
return NOTIFY_OK;
} }
static struct notifier_block i7_mce_dec = { static struct notifier_block i7_mce_dec = {
......
...@@ -10,15 +10,8 @@ static struct amd_decoder_ops fam_ops; ...@@ -10,15 +10,8 @@ static struct amd_decoder_ops fam_ops;
static u8 xec_mask = 0xf; static u8 xec_mask = 0xf;
static bool report_gart_errors;
static void (*decode_dram_ecc)(int node_id, struct mce *m); static void (*decode_dram_ecc)(int node_id, struct mce *m);
void amd_report_gart_errors(bool v)
{
report_gart_errors = v;
}
EXPORT_SYMBOL_GPL(amd_report_gart_errors);
void amd_register_ecc_decoder(void (*f)(int, struct mce *)) void amd_register_ecc_decoder(void (*f)(int, struct mce *))
{ {
decode_dram_ecc = f; decode_dram_ecc = f;
...@@ -1030,20 +1023,6 @@ static inline void amd_decode_err_code(u16 ec) ...@@ -1030,20 +1023,6 @@ static inline void amd_decode_err_code(u16 ec)
pr_cont("\n"); pr_cont("\n");
} }
/*
* Filter out unwanted MCE signatures here.
*/
static bool ignore_mce(struct mce *m)
{
/*
* NB GART TLB error reporting is disabled by default.
*/
if (m->bank == 4 && XEC(m->status, 0x1f) == 0x5 && !report_gart_errors)
return true;
return false;
}
static const char *decode_error_status(struct mce *m) static const char *decode_error_status(struct mce *m)
{ {
if (m->status & MCI_STATUS_UC) { if (m->status & MCI_STATUS_UC) {
...@@ -1067,8 +1046,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ...@@ -1067,8 +1046,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
unsigned int fam = x86_family(m->cpuid); unsigned int fam = x86_family(m->cpuid);
int ecc; int ecc;
if (ignore_mce(m)) if (m->kflags & MCE_HANDLED_CEC)
return NOTIFY_STOP; return NOTIFY_DONE;
pr_emerg(HW_ERR "%s\n", decode_error_status(m)); pr_emerg(HW_ERR "%s\n", decode_error_status(m));
...@@ -1170,7 +1149,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ...@@ -1170,7 +1149,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
err_code: err_code:
amd_decode_err_code(m->status & 0xffff); amd_decode_err_code(m->status & 0xffff);
return NOTIFY_STOP; m->kflags |= MCE_HANDLED_EDAC;
return NOTIFY_OK;
} }
static struct notifier_block amd_mce_dec_nb = { static struct notifier_block amd_mce_dec_nb = {
......
...@@ -7,7 +7,6 @@ ...@@ -7,7 +7,6 @@
#include <asm/mce.h> #include <asm/mce.h>
#define EC(x) ((x) & 0xffff) #define EC(x) ((x) & 0xffff)
#define XEC(x, mask) (((x) >> 16) & mask)
#define LOW_SYNDROME(x) (((x) >> 15) & 0xff) #define LOW_SYNDROME(x) (((x) >> 15) & 0xff)
#define HIGH_SYNDROME(x) (((x) >> 24) & 0xff) #define HIGH_SYNDROME(x) (((x) >> 24) & 0xff)
...@@ -77,7 +76,6 @@ struct amd_decoder_ops { ...@@ -77,7 +76,6 @@ struct amd_decoder_ops {
bool (*mc2_mce)(u16, u8); bool (*mc2_mce)(u16, u8);
}; };
void amd_report_gart_errors(bool);
void amd_register_ecc_decoder(void (*f)(int, struct mce *)); void amd_register_ecc_decoder(void (*f)(int, struct mce *));
void amd_unregister_ecc_decoder(void (*f)(int, struct mce *)); void amd_unregister_ecc_decoder(void (*f)(int, struct mce *));
......
...@@ -1396,11 +1396,8 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo ...@@ -1396,11 +1396,8 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
struct dram_addr daddr; struct dram_addr daddr;
char *type; char *type;
if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
return NOTIFY_DONE;
mci = pnd2_mci; mci = pnd2_mci;
if (!mci) if (!mci || (mce->kflags & MCE_HANDLED_CEC))
return NOTIFY_DONE; return NOTIFY_DONE;
/* /*
...@@ -1429,7 +1426,8 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo ...@@ -1429,7 +1426,8 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
pnd2_mce_output_error(mci, mce, &daddr); pnd2_mce_output_error(mci, mce, &daddr);
/* Advice mcelog that the error were handled */ /* Advice mcelog that the error were handled */
return NOTIFY_STOP; mce->kflags |= MCE_HANDLED_EDAC;
return NOTIFY_OK;
} }
static struct notifier_block pnd2_mce_dec = { static struct notifier_block pnd2_mce_dec = {
......
...@@ -3134,7 +3134,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, ...@@ -3134,7 +3134,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
struct mem_ctl_info *mci; struct mem_ctl_info *mci;
char *type; char *type;
if (edac_get_report_status() == EDAC_REPORTING_DISABLED) if (mce->kflags & MCE_HANDLED_CEC)
return NOTIFY_DONE; return NOTIFY_DONE;
/* /*
...@@ -3183,7 +3183,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, ...@@ -3183,7 +3183,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
sbridge_mce_output_error(mci, mce); sbridge_mce_output_error(mci, mce);
/* Advice mcelog that the error were handled */ /* Advice mcelog that the error were handled */
return NOTIFY_STOP; mce->kflags |= MCE_HANDLED_EDAC;
return NOTIFY_OK;
} }
static struct notifier_block sbridge_mce_dec = { static struct notifier_block sbridge_mce_dec = {
...@@ -3523,8 +3524,6 @@ static int __init sbridge_init(void) ...@@ -3523,8 +3524,6 @@ static int __init sbridge_init(void)
if (rc >= 0) { if (rc >= 0) {
mce_register_decode_chain(&sbridge_mce_dec); mce_register_decode_chain(&sbridge_mce_dec);
if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
return 0; return 0;
} }
......
...@@ -573,7 +573,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, ...@@ -573,7 +573,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
struct mem_ctl_info *mci; struct mem_ctl_info *mci;
char *type; char *type;
if (edac_get_report_status() == EDAC_REPORTING_DISABLED) if (mce->kflags & MCE_HANDLED_CEC)
return NOTIFY_DONE; return NOTIFY_DONE;
/* ignore unless this is memory related with an address */ /* ignore unless this is memory related with an address */
...@@ -615,6 +615,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, ...@@ -615,6 +615,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
skx_mce_output_error(mci, mce, &res); skx_mce_output_error(mci, mce, &res);
mce->kflags |= MCE_HANDLED_EDAC;
return NOTIFY_DONE; return NOTIFY_DONE;
} }
......
...@@ -632,6 +632,7 @@ static const struct pci_device_id k10temp_id_table[] = { ...@@ -632,6 +632,7 @@ static const struct pci_device_id k10temp_id_table[] = {
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
{ PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) },
{} {}
......
...@@ -309,7 +309,7 @@ static bool sanity_check(struct ce_array *ca) ...@@ -309,7 +309,7 @@ static bool sanity_check(struct ce_array *ca)
return ret; return ret;
} }
int cec_add_elem(u64 pfn) static int cec_add_elem(u64 pfn)
{ {
struct ce_array *ca = &ce_arr; struct ce_array *ca = &ce_arr;
unsigned int to = 0; unsigned int to = 0;
...@@ -527,7 +527,33 @@ static int __init create_debugfs_nodes(void) ...@@ -527,7 +527,33 @@ static int __init create_debugfs_nodes(void)
return 1; return 1;
} }
void __init cec_init(void) static int cec_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
struct mce *m = (struct mce *)data;
if (!m)
return NOTIFY_DONE;
/* We eat only correctable DRAM errors with usable addresses. */
if (mce_is_memory_error(m) &&
mce_is_correctable(m) &&
mce_usable_address(m)) {
if (!cec_add_elem(m->addr >> PAGE_SHIFT)) {
m->kflags |= MCE_HANDLED_CEC;
return NOTIFY_OK;
}
}
return NOTIFY_DONE;
}
static struct notifier_block cec_nb = {
.notifier_call = cec_notifier,
.priority = MCE_PRIO_CEC,
};
static void __init cec_init(void)
{ {
if (ce_arr.disabled) if (ce_arr.disabled)
return; return;
...@@ -546,8 +572,11 @@ void __init cec_init(void) ...@@ -546,8 +572,11 @@ void __init cec_init(void)
INIT_DELAYED_WORK(&cec_work, cec_work_fn); INIT_DELAYED_WORK(&cec_work, cec_work_fn);
schedule_delayed_work(&cec_work, CEC_DECAY_DEFAULT_INTERVAL); schedule_delayed_work(&cec_work, CEC_DECAY_DEFAULT_INTERVAL);
mce_register_decode_chain(&cec_nb);
pr_info("Correctable Errors collector initialized.\n"); pr_info("Correctable Errors collector initialized.\n");
} }
late_initcall(cec_init);
int __init parse_cec_param(char *str) int __init parse_cec_param(char *str)
{ {
......
...@@ -31,14 +31,6 @@ struct device; ...@@ -31,14 +31,6 @@ struct device;
extern int edac_op_state; extern int edac_op_state;
struct bus_type *edac_get_sysfs_subsys(void); struct bus_type *edac_get_sysfs_subsys(void);
int edac_get_report_status(void);
void edac_set_report_status(int new);
enum {
EDAC_REPORTING_ENABLED,
EDAC_REPORTING_DISABLED,
EDAC_REPORTING_FORCE
};
static inline void opstate_init(void) static inline void opstate_init(void)
{ {
......
...@@ -550,6 +550,7 @@ ...@@ -550,6 +550,7 @@
#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493
#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b
#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443
#define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653
#define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703
......
...@@ -17,12 +17,7 @@ static inline int ras_add_daemon_trace(void) { return 0; } ...@@ -17,12 +17,7 @@ static inline int ras_add_daemon_trace(void) { return 0; }
#endif #endif
#ifdef CONFIG_RAS_CEC #ifdef CONFIG_RAS_CEC
void __init cec_init(void);
int __init parse_cec_param(char *str); int __init parse_cec_param(char *str);
int cec_add_elem(u64 pfn);
#else
static inline void __init cec_init(void) { }
static inline int cec_add_elem(u64 pfn) { return -ENODEV; }
#endif #endif
#ifdef CONFIG_RAS #ifdef CONFIG_RAS
......
...@@ -1308,7 +1308,9 @@ struct task_struct { ...@@ -1308,7 +1308,9 @@ struct task_struct {
#ifdef CONFIG_X86_MCE #ifdef CONFIG_X86_MCE
u64 mce_addr; u64 mce_addr;
u64 mce_status; __u64 mce_ripv : 1,
mce_whole_page : 1,
__mce_reserved : 62;
struct callback_head mce_kill_me; struct callback_head mce_kill_me;
#endif #endif
......
...@@ -26,7 +26,7 @@ static inline int set_direct_map_default_noflush(struct page *page) ...@@ -26,7 +26,7 @@ static inline int set_direct_map_default_noflush(struct page *page)
#endif #endif
#ifndef set_mce_nospec #ifndef set_mce_nospec
static inline int set_mce_nospec(unsigned long pfn) static inline int set_mce_nospec(unsigned long pfn, bool unmap)
{ {
return 0; return 0;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment