system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-11-05 18:23:50 +00:00
Code Issues Projects Releases Packages Wiki Activity

Intel EDAC fixes:

Browse source 
- Old igen6 driver could lose pending events during initialization
 - Sapphire Rapids workstations have fewer memory controllers than their
   bigger siblings. This confused the driver.
 -----BEGIN PGP SIGNATURE-----
 
 iQJIBAABCAAyFiEENIoOqscayAmBOQ5Iq6sjH5ffWIEFAmTudg4UHHRvbnkubHVj
 a0BpbnRlbC5jb20ACgkQq6sjH5ffWIH4wA//Z+pbRElvnWyK8rTx6SbWFu82D8a/
 dAXx5V+8I6v64MPb9VZXP6KEiBQgk2jD2AsC0+2QrZL9FUnKwnBSDC3rgVWPTxBo
 dTxu8j1PDTlnffU+wuaB+3cCRikwa1h+Fr/SQaphwTLA3nm13CHj+dUOp3ZUR8fT
 vz+M4t3SRgcU/0W40jcLnn1h5hsTNjQWr//zVVdctGr++sl7xtVh7wxZPakTC9RL
 FBMx3elqdroeQ5ILMxC5e1V02tAZVrXxZbSNpLWhH25MBwe8P7rc+SHYfNaddnpx
 3qrOOzRZl3fGifoM+GU/JsMeIYh6FYUhOfBNTjUFWQZP+6mDvgj9WaLxVgw9V99R
 W384K7KnjLSnE01/REZ0x9R1sehXyQIv2zGosJitRuKyLuw5UODx/khzpCG6a0P3
 RPi4tNemscCIr5djX8VBqmyxS5tqUzlBBDskDnsHHS7NXLuYv1O6SqR/7kvCqhFQ
 7/qGWNFbzZOMJZiLGUmmxEv3Pk+tfTlZdYOipfaHpSlNNr9zO07VXBRNK18aqQVp
 3GCpRp3IhTL3EmOE2RaV2uhyRIcpSnjvqi8shoN6p1wy8jQwNKoe3/nt7QobKhCl
 4kYC9q0jNDWgh/QWxgtoB6UzWHIieeVZQQcW0Da4fvlsIBwbzcpu5+j3qaCxUNBD
 jUt/DwSD+D91yPI=
 =4Uqu
 -----END PGP SIGNATURE-----

Merge tag 'edac_updates_for_v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras

Pull intel EDAC fixes from Tony Luck:

 - Old igen6 driver could lose pending events during initialization

 - Sapphire Rapids workstations have fewer memory controllers than their
   bigger siblings. This confused the driver.

* tag 'edac_updates_for_v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
  EDAC/igen6: Fix the issue of no error events
  EDAC/i10nm: Skip the absent memory controllers
This commit is contained in:
Linus Torvalds 2023-08-30 19:23:00 -07:00
commit bb511d4b25
2 changed files with 53 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
drivers/edac/i10nm_base.c
View file

@ -658,13 +658,49 @@ static struct pci_dev *get_ddr_munit(struct skx_dev *d, int i, u32 *offset, unsi
return mdev;
}
/**
* i10nm_imc_absent() - Check whether the memory controller @imc is absent
*
* @imc : The pointer to the structure of memory controller EDAC device.
*
* RETURNS : true if the memory controller EDAC device is absent, false otherwise.
*/
static bool i10nm_imc_absent(struct skx_imc *imc)
{
u32 mcmtr;
int i;
switch (res_cfg->type) {
case SPR:
for (i = 0; i < res_cfg->ddr_chan_num; i++) {
mcmtr = I10NM_GET_MCMTR(imc, i);
edac_dbg(1, "ch%d mcmtr reg %x\n", i, mcmtr);
if (mcmtr != ~0)
return false;
}
/*
* Some workstations' absent memory controllers still
* appear as PCIe devices, misleading the EDAC driver.
* By observing that the MMIO registers of these absent
* memory controllers consistently hold the value of ~0.
*
* We identify a memory controller as absent by checking
* if its MMIO register "mcmtr" == ~0 in all its channels.
*/
return true;
default:
return false;
}
}
static int i10nm_get_ddr_munits(void)
{
struct pci_dev *mdev;
void __iomem *mbase;
unsigned long size;
struct skx_dev *d;
int i, j = 0;
int i, lmc, j = 0;
u32 reg, off;
u64 base;
@ -690,7 +726,7 @@ static int i10nm_get_ddr_munits(void)
edac_dbg(2, "socket%d mmio base 0x%llx (reg 0x%x)\n",
j++, base, reg);
for (i = 0; i < res_cfg->ddr_imc_num; i++) {
for (lmc = 0, i = 0; i < res_cfg->ddr_imc_num; i++) {
mdev = get_ddr_munit(d, i, &off, &size);
if (i == 0 && !mdev) {
@ -700,8 +736,6 @@ static int i10nm_get_ddr_munits(void)
if (!mdev)
continue;
d->imc[i].mdev = mdev;
edac_dbg(2, "mc%d mmio base 0x%llx size 0x%lx (reg 0x%x)\n",
i, base + off, size, reg);
@ -712,7 +746,17 @@ static int i10nm_get_ddr_munits(void)
return -ENODEV;
}
d->imc[i].mbase = mbase;
d->imc[lmc].mbase = mbase;
if (i10nm_imc_absent(&d->imc[lmc])) {
pci_dev_put(mdev);
iounmap(mbase);
d->imc[lmc].mbase = NULL;
edac_dbg(2, "Skip absent mc%d\n", i);
continue;
} else {
d->imc[lmc].mdev = mdev;
lmc++;
}
}
}

8
drivers/edac/igen6_edac.c
View file

@ -27,7 +27,7 @@
#include "edac_mc.h"
#include "edac_module.h"
#define IGEN6_REVISION "v2.5"
#define IGEN6_REVISION "v2.5.1"
#define EDAC_MOD_STR "igen6_edac"
#define IGEN6_NMI_NAME "igen6_ibecc"
@ -1216,9 +1216,6 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
INIT_WORK(&ecclog_work, ecclog_work_cb);
init_irq_work(&ecclog_irq_work, ecclog_irq_work_cb);
/* Check if any pending errors before registering the NMI handler */
ecclog_handler();
rc = register_err_handler();
if (rc)
goto fail3;
@ -1230,6 +1227,9 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto fail4;
}
/* Check if any pending errors before/during the registration of the error handler */
ecclog_handler();
igen6_debug_setup();
return 0;
fail4: