[PATCH 0/5] MCA and EDAC updates for AMD Family 19h

[PATCH 0/5] MCA and EDAC updates for AMD Family 19h

[Yazen Ghannam]

From: Yazen Ghannam <yazen.ghannam@amd.com>

Hi Boris,

This patchset adds MCA and EDAC support for AMD Family 19h.

There aren't any functional changes. Mostly we just need to add new PCI
IDs and a new MCA bank type. I've also included a couple of patches that
do away with family checks where appropriate.

Thanks,
Yazen

Yazen Ghannam (5):
  x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType
  EDAC/mce_amd: Always load on SMCA systems
  x86/amd_nb: Add Family 19h PCI IDs
  EDAC/amd64: Add family ops for Family 19h Models 00h-0Fh
  EDAC/amd64: Drop some family checks for newer systems

 arch/x86/include/asm/mce.h    |  1 +
 arch/x86/kernel/amd_nb.c      |  3 ++
 arch/x86/kernel/cpu/mce/amd.c |  2 ++
 drivers/edac/amd64_edac.c     | 62 ++++++++++++++++++++---------------
 drivers/edac/amd64_edac.h     |  3 ++
 drivers/edac/mce_amd.c        | 41 ++++++++++++++++++++---
 include/linux/pci_ids.h       |  1 +
 7 files changed, 82 insertions(+), 31 deletions(-)

-- 
2.17.1

[PATCH 1/5] x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType

[Yazen Ghannam]

From: Yazen Ghannam <yazen.ghannam@amd.com>

Future SMCA systems may see a new version of the Load Store unit bank
type as indicated by its McaType value.

Add the new (HWID, MCATYPE) tuple. Reuse the same name, since this is
logically the same to the user.

Also, add the new error descriptions to edac_mce_amd.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 arch/x86/include/asm/mce.h    |  1 +
 arch/x86/kernel/cpu/mce/amd.c |  2 ++
 drivers/edac/mce_amd.c        | 28 ++++++++++++++++++++++++++++
 3 files changed, 31 insertions(+)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index dc2d4b206ab7..0f84c20c5429 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -290,6 +290,7 @@ extern void apei_mce_report_mem_error(int corrected,
 /* These may be used by multiple smca_hwid_mcatypes */
 enum smca_bank_types {
 	SMCA_LS = 0,	/* Load Store */
+	SMCA_LS_V2,	/* Load Store */
 	SMCA_IF,	/* Instruction Fetch */
 	SMCA_L2_CACHE,	/* L2 Cache */
 	SMCA_DE,	/* Decoder Unit */
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d6cf5c18a7e0..b3a50d962851 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -78,6 +78,7 @@ struct smca_bank_name {
 
 static struct smca_bank_name smca_names[] = {
 	[SMCA_LS]	= { "load_store",	"Load Store Unit" },
+	[SMCA_LS_V2]	= { "load_store",	"Load Store Unit" },
 	[SMCA_IF]	= { "insn_fetch",	"Instruction Fetch Unit" },
 	[SMCA_L2_CACHE]	= { "l2_cache",		"L2 Cache" },
 	[SMCA_DE]	= { "decode_unit",	"Decode Unit" },
@@ -138,6 +139,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 
 	/* ZN Core (HWID=0xB0) MCA types */
 	{ SMCA_LS,	 HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF },
+	{ SMCA_LS_V2,	 HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF },
 	{ SMCA_IF,	 HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
 	{ SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF },
 	{ SMCA_DE,	 HWID_MCATYPE(0xB0, 0x3), 0x1FF },
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index ea622c6f3a39..aa6ea53f7d14 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -175,6 +175,33 @@ static const char * const smca_ls_mce_desc[] = {
 	"L2 Fill Data error",
 };
 
+static const char * const smca_ls2_mce_desc[] = {
+	"An ECC error was detected on a data cache read by a probe or victimization",
+	"An ECC error or L2 poison was detected on a data cache read by a load",
+	"An ECC error was detected on a data cache read-modify-write by a store",
+	"An ECC error or poison bit mismatch was detected on a tag read by a probe or victimization",
+	"An ECC error or poison bit mismatch was detected on a tag read by a load",
+	"An ECC error or poison bit mismatch was detected on a tag read by a store",
+	"An ECC error was detected on an EMEM read by a load",
+	"An ECC error was detected on an EMEM read-modify-write by a store",
+	"A parity error was detected in an L1 TLB entry by any access",
+	"A parity error was detected in an L2 TLB entry by any access",
+	"A parity error was detected in a PWC entry by any access",
+	"A parity error was detected in an STQ entry by any access",
+	"A parity error was detected in an LDQ entry by any access",
+	"A parity error was detected in a MAB entry by any access",
+	"A parity error was detected in an SCB entry state field by any access",
+	"A parity error was detected in an SCB entry address field by any access",
+	"A parity error was detected in an SCB entry data field by any access",
+	"A parity error was detected in a WCB entry by any access",
+	"A poisoned line was detected in an SCB entry by any access",
+	"A SystemReadDataError error was reported on read data returned from L2 for a load",
+	"A SystemReadDataError error was reported on read data returned from L2 for an SCB store",
+	"A SystemReadDataError error was reported on read data returned from L2 for a WCB store",
+	"A hardware assertion error was reported",
+	"A parity error was detected in an STLF, SCB EMEM entry or SRB store data by any access",
+};
+
 static const char * const smca_if_mce_desc[] = {
 	"Op Cache Microtag Probe Port Parity Error",
 	"IC Microtag or Full Tag Multi-hit Error",
@@ -378,6 +405,7 @@ struct smca_mce_desc {
 
 static struct smca_mce_desc smca_mce_descs[] = {
 	[SMCA_LS]	= { smca_ls_mce_desc,	ARRAY_SIZE(smca_ls_mce_desc)	},
+	[SMCA_LS_V2]	= { smca_ls2_mce_desc,	ARRAY_SIZE(smca_ls2_mce_desc)	},
 	[SMCA_IF]	= { smca_if_mce_desc,	ARRAY_SIZE(smca_if_mce_desc)	},
 	[SMCA_L2_CACHE]	= { smca_l2_mce_desc,	ARRAY_SIZE(smca_l2_mce_desc)	},
 	[SMCA_DE]	= { smca_de_mce_desc,	ARRAY_SIZE(smca_de_mce_desc)	},
-- 
2.17.1

Re: [PATCH 1/5] x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType

[Borislav Petkov]

On Fri, Jan 10, 2020 at 01:56:47AM +0000, Yazen Ghannam wrote:
> From: Yazen Ghannam <yazen.ghannam@amd.com>
> 
> Future SMCA systems may see a new version of the Load Store unit bank
		      ^^^^^^^^

Yah, you've been hanging around with hw people too much. I can just as
well reply: "well, I'll apply the patch when I see future SMCA systems"
:-)

All I'm saying is, forget those "may" formulations when it comes to
kernel patches. :-)

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

RE: [PATCH 1/5] x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType

[Ghannam, Yazen]

[AMD Official Use Only - Internal Distribution Only]

> -----Original Message-----
> From: linux-edac-owner@vger.kernel.org <linux-edac-owner@vger.kernel.org> On Behalf Of Borislav Petkov
> Sent: Thursday, January 16, 2020 10:51 AM
> To: Ghannam, Yazen <Yazen.Ghannam@amd.com>
> Cc: linux-edac@vger.kernel.org; linux-kernel@vger.kernel.org; bp@suse.de; tony.luck@intel.com; x86@kernel.org
> Subject: Re: [PATCH 1/5] x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType
> 
> On Fri, Jan 10, 2020 at 01:56:47AM +0000, Yazen Ghannam wrote:
> > From: Yazen Ghannam <yazen.ghannam@amd.com>
> >
> > Future SMCA systems may see a new version of the Load Store unit bank
> 		      ^^^^^^^^
> 
> Yah, you've been hanging around with hw people too much. I can just as
> well reply: "well, I'll apply the patch when I see future SMCA systems"
> :-)
> 

Yes, you "may" be right. :)

> All I'm saying is, forget those "may" formulations when it comes to
> kernel patches. :-)
> 

Seriously though, I'll work on it. Thanks!

-Yazen

Re: [PATCH 1/5] x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType

[Borislav Petkov]

On Fri, Jan 17, 2020 at 03:14:06PM +0000, Ghannam, Yazen wrote:
> [AMD Official Use Only - Internal Distribution Only]

...

> Yes, you "may" be right. :)

:-)

> Seriously though, I'll work on it. Thanks!

Thanks.

Also, you might wanna work on that piece of crap at the beginning of the
mail too:

> [AMD Official Use Only - Internal Distribution Only]

I don't think there's a problem to use another mail provider but keep
your SOB and From: mail for authorship attribution.

Company mail setup is simply inadequate for upstream development. It
almost doesn't matter which company. :-)

Thx.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

[PATCH 2/5] EDAC/mce_amd: Always load on SMCA systems

[Yazen Ghannam]

From: Yazen Ghannam <yazen.ghannam@amd.com>

MCA error decoding on SMCA systems is not dependent on family.

Return success early if the system supports the SMCA feature.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 drivers/edac/mce_amd.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index aa6ea53f7d14..524c63fdad42 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -1189,6 +1189,11 @@ static int __init mce_amd_init(void)
 	if (!fam_ops)
 		return -ENOMEM;
 
+	if (boot_cpu_has(X86_FEATURE_SMCA)) {
+		xec_mask = 0x3f;
+		goto out;
+	}
+
 	switch (c->x86) {
 	case 0xf:
 		fam_ops->mc0_mce = k8_mc0_mce;
@@ -1237,11 +1242,8 @@ static int __init mce_amd_init(void)
 
 	case 0x17:
 	case 0x18:
-		xec_mask = 0x3f;
-		if (!boot_cpu_has(X86_FEATURE_SMCA)) {
-			printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n");
-			goto err_out;
-		}
+		pr_warn("Decoding supported only on Scalable MCA processors.\n");
+		goto err_out;
 		break;
 
 	default:
@@ -1249,6 +1251,7 @@ static int __init mce_amd_init(void)
 		goto err_out;
 	}
 
+out:
 	pr_info("MCE: In-kernel MCE decoding enabled.\n");
 
 	mce_register_decode_chain(&amd_mce_dec_nb);
-- 
2.17.1

[PATCH 3/5] x86/amd_nb: Add Family 19h PCI IDs

[Yazen Ghannam]

From: Yazen Ghannam <yazen.ghannam@amd.com>

Add the new PCI Device 18h IDs for AMD Family 19h systems.

Note that Family 19h systems will not have a new PCI root device ID.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 arch/x86/kernel/amd_nb.c | 3 +++
 include/linux/pci_ids.h  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 251c795b4eb3..69aed0ebbdfc 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -22,6 +22,7 @@
 #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_M70H_DF_F4 0x1444
+#define PCI_DEVICE_ID_AMD_19H_DF_F4	0x1654
 
 /* Protect the PCI config register pairs used for SMN and DF indirect access. */
 static DEFINE_MUTEX(smn_mutex);
@@ -52,6 +53,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_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_19H_DF_F3) },
 	{}
 };
 EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -66,6 +68,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ 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_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_CNB17H_F4) },
 	{}
 };
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 2302d133af6f..352c0d708720 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -549,6 +549,7 @@
 #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_M70H_DF_F3 0x1443
+#define PCI_DEVICE_ID_AMD_19H_DF_F3	0x1653
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
-- 
2.17.1

[PATCH 4/5] EDAC/amd64: Add family ops for Family 19h Models 00h-0Fh

[Yazen Ghannam]

From: Yazen Ghannam <yazen.ghannam@amd.com>

Add family ops to support AMD Family 19h systems. Existing Family 17h
functions can be used.

Also, add Family 19h to the list of families to automatically load the
module.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 drivers/edac/amd64_edac.c | 17 +++++++++++++++++
 drivers/edac/amd64_edac.h |  3 +++
 2 files changed, 20 insertions(+)

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 428ce98f6776..2488cbf76814 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2336,6 +2336,16 @@ static struct amd64_family_type family_types[] = {
 			.dbam_to_cs		= f17_addr_mask_to_cs_size,
 		}
 	},
+	[F19_CPUS] = {
+		.ctl_name = "F19h",
+		.f0_id = PCI_DEVICE_ID_AMD_19H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_19H_DF_F6,
+		.max_mcs = 8,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_addr_mask_to_cs_size,
+		}
+	},
 };
 
 /*
@@ -3368,6 +3378,12 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			family_types[F17_CPUS].ctl_name = "F18h";
 		break;
 
+	case 0x19:
+		fam_type	= &family_types[F19_CPUS];
+		pvt->ops	= &family_types[F19_CPUS].ops;
+		family_types[F19_CPUS].ctl_name = "F19h";
+		break;
+
 	default:
 		amd64_err("Unsupported family!\n");
 		return NULL;
@@ -3626,6 +3642,7 @@ static const struct x86_cpu_id amd64_cpuids[] = {
 	{ X86_VENDOR_AMD, 0x16, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ X86_VENDOR_AMD, 0x17, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ X86_VENDOR_HYGON, 0x18, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
+	{ X86_VENDOR_AMD, 0x19, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, amd64_cpuids);
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 9be31688110b..abbf3c274d74 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -122,6 +122,8 @@
 #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
 #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_19H_DF_F0	0x1650
+#define PCI_DEVICE_ID_AMD_19H_DF_F6	0x1656
 
 /*
  * Function 1 - Address Map
@@ -292,6 +294,7 @@ enum amd_families {
 	F17_M10H_CPUS,
 	F17_M30H_CPUS,
 	F17_M70H_CPUS,
+	F19_CPUS,
 	NUM_FAMILIES,
 };
 
-- 
2.17.1

[PATCH 5/5] EDAC/amd64: Drop some family checks for newer systems

[Yazen Ghannam]

From: Yazen Ghannam <yazen.ghannam@amd.com>

In general, "pvt->umc != NULL" is used to check if the system is Family
17h+. However, there are a few places that are using direct family
checks.

Replace the remaining family checks with a check for "pvt->umc != NULL".

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 drivers/edac/amd64_edac.c | 45 +++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 26 deletions(-)

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 2488cbf76814..4fc9f0b06ed7 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -214,7 +214,7 @@ static int __set_scrub_rate(struct amd64_pvt *pvt, u32 new_bw, u32 min_rate)
 
 	scrubval = scrubrates[i].scrubval;
 
-	if (pvt->fam == 0x17 || pvt->fam == 0x18) {
+	if (pvt->umc) {
 		__f17h_set_scrubval(pvt, scrubval);
 	} else if (pvt->fam == 0x15 && pvt->model == 0x60) {
 		f15h_select_dct(pvt, 0);
@@ -256,18 +256,7 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
 	int i, retval = -EINVAL;
 	u32 scrubval = 0;
 
-	switch (pvt->fam) {
-	case 0x15:
-		/* Erratum #505 */
-		if (pvt->model < 0x10)
-			f15h_select_dct(pvt, 0);
-
-		if (pvt->model == 0x60)
-			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
-		break;
-
-	case 0x17:
-	case 0x18:
+	if (pvt->umc) {
 		amd64_read_pci_cfg(pvt->F6, F17H_SCR_BASE_ADDR, &scrubval);
 		if (scrubval & BIT(0)) {
 			amd64_read_pci_cfg(pvt->F6, F17H_SCR_LIMIT_ADDR, &scrubval);
@@ -276,11 +265,15 @@ static int get_scrub_rate(struct mem_ctl_info *mci)
 		} else {
 			scrubval = 0;
 		}
-		break;
+	} else if (pvt->fam == 0x15) {
+		/* Erratum #505 */
+		if (pvt->model < 0x10)
+			f15h_select_dct(pvt, 0);
 
-	default:
+		if (pvt->model == 0x60)
+			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
+	} else {
 		amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
-		break;
 	}
 
 	scrubval = scrubval & 0x001F;
@@ -1055,6 +1048,16 @@ static void determine_memory_type(struct amd64_pvt *pvt)
 {
 	u32 dram_ctrl, dcsm;
 
+	if (pvt->umc) {
+		if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(5))
+			pvt->dram_type = MEM_LRDDR4;
+		else if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(4))
+			pvt->dram_type = MEM_RDDR4;
+		else
+			pvt->dram_type = MEM_DDR4;
+		return;
+	}
+
 	switch (pvt->fam) {
 	case 0xf:
 		if (pvt->ext_model >= K8_REV_F)
@@ -1100,16 +1103,6 @@ static void determine_memory_type(struct amd64_pvt *pvt)
 	case 0x16:
 		goto ddr3;
 
-	case 0x17:
-	case 0x18:
-		if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(5))
-			pvt->dram_type = MEM_LRDDR4;
-		else if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(4))
-			pvt->dram_type = MEM_RDDR4;
-		else
-			pvt->dram_type = MEM_DDR4;
-		return;
-
 	default:
 		WARN(1, KERN_ERR "%s: Family??? 0x%x\n", __func__, pvt->fam);
 		pvt->dram_type = MEM_EMPTY;
-- 
2.17.1

Re: [PATCH 0/5] MCA and EDAC updates for AMD Family 19h

[Borislav Petkov]

On Fri, Jan 10, 2020 at 01:56:46AM +0000, Yazen Ghannam wrote:
> From: Yazen Ghannam <yazen.ghannam@amd.com>
> 
> Hi Boris,
> 
> This patchset adds MCA and EDAC support for AMD Family 19h.
> 
> There aren't any functional changes. Mostly we just need to add new PCI
> IDs and a new MCA bank type. I've also included a couple of patches that
> do away with family checks where appropriate.
> 
> Thanks,
> Yazen
> 
> Yazen Ghannam (5):
>   x86/MCE/AMD, EDAC/mce_amd: Add new Load Store unit McaType
>   EDAC/mce_amd: Always load on SMCA systems
>   x86/amd_nb: Add Family 19h PCI IDs
>   EDAC/amd64: Add family ops for Family 19h Models 00h-0Fh
>   EDAC/amd64: Drop some family checks for newer systems
> 
>  arch/x86/include/asm/mce.h    |  1 +
>  arch/x86/kernel/amd_nb.c      |  3 ++
>  arch/x86/kernel/cpu/mce/amd.c |  2 ++
>  drivers/edac/amd64_edac.c     | 62 ++++++++++++++++++++---------------
>  drivers/edac/amd64_edac.h     |  3 ++
>  drivers/edac/mce_amd.c        | 41 ++++++++++++++++++++---
>  include/linux/pci_ids.h       |  1 +
>  7 files changed, 82 insertions(+), 31 deletions(-)
> 
> -- 

Btw, I'll slap this ontop:

---
From: Borislav Petkov <bp@suse.de>
Date: Thu, 16 Jan 2020 17:28:39 +0100
Subject: [PATCH] EDAC/mce_amd: Make fam_ops static global

... and do not kmalloc a three-pointer struct. Which simplifies
mce_amd_init() a bit.

No functional changes.

Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/mce_amd.c | 69 ++++++++++++++++++------------------------
 1 file changed, 30 insertions(+), 39 deletions(-)

diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 524c63fdad42..df95a05c9f23 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -6,7 +6,7 @@
 
 #include "mce_amd.h"
 
-static struct amd_decoder_ops *fam_ops;
+static struct amd_decoder_ops fam_ops;
 
 static u8 xec_mask	 = 0xf;
 
@@ -583,7 +583,7 @@ static void decode_mc0_mce(struct mce *m)
 					    : (xec ? "multimatch" : "parity")));
 			return;
 		}
-	} else if (fam_ops->mc0_mce(ec, xec))
+	} else if (fam_ops.mc0_mce(ec, xec))
 		;
 	else
 		pr_emerg(HW_ERR "Corrupted MC0 MCE info?\n");
@@ -697,7 +697,7 @@ static void decode_mc1_mce(struct mce *m)
 			pr_cont("Hardware Assert.\n");
 		else
 			goto wrong_mc1_mce;
-	} else if (fam_ops->mc1_mce(ec, xec))
+	} else if (fam_ops.mc1_mce(ec, xec))
 		;
 	else
 		goto wrong_mc1_mce;
@@ -831,7 +831,7 @@ static void decode_mc2_mce(struct mce *m)
 
 	pr_emerg(HW_ERR "MC2 Error: ");
 
-	if (!fam_ops->mc2_mce(ec, xec))
+	if (!fam_ops.mc2_mce(ec, xec))
 		pr_cont(HW_ERR "Corrupted MC2 MCE info?\n");
 }
 
@@ -1130,7 +1130,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	if (m->tsc)
 		pr_emerg(HW_ERR "TSC: %llu\n", m->tsc);
 
-	if (!fam_ops)
+	/* Doesn't matter which member to test. */
+	if (!fam_ops.mc0_mce)
 		goto err_code;
 
 	switch (m->bank) {
@@ -1185,10 +1186,6 @@ static int __init mce_amd_init(void)
 	    c->x86_vendor != X86_VENDOR_HYGON)
 		return -ENODEV;
 
-	fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);
-	if (!fam_ops)
-		return -ENOMEM;
-
 	if (boot_cpu_has(X86_FEATURE_SMCA)) {
 		xec_mask = 0x3f;
 		goto out;
@@ -1196,59 +1193,58 @@ static int __init mce_amd_init(void)
 
 	switch (c->x86) {
 	case 0xf:
-		fam_ops->mc0_mce = k8_mc0_mce;
-		fam_ops->mc1_mce = k8_mc1_mce;
-		fam_ops->mc2_mce = k8_mc2_mce;
+		fam_ops.mc0_mce = k8_mc0_mce;
+		fam_ops.mc1_mce = k8_mc1_mce;
+		fam_ops.mc2_mce = k8_mc2_mce;
 		break;
 
 	case 0x10:
-		fam_ops->mc0_mce = f10h_mc0_mce;
-		fam_ops->mc1_mce = k8_mc1_mce;
-		fam_ops->mc2_mce = k8_mc2_mce;
+		fam_ops.mc0_mce = f10h_mc0_mce;
+		fam_ops.mc1_mce = k8_mc1_mce;
+		fam_ops.mc2_mce = k8_mc2_mce;
 		break;
 
 	case 0x11:
-		fam_ops->mc0_mce = k8_mc0_mce;
-		fam_ops->mc1_mce = k8_mc1_mce;
-		fam_ops->mc2_mce = k8_mc2_mce;
+		fam_ops.mc0_mce = k8_mc0_mce;
+		fam_ops.mc1_mce = k8_mc1_mce;
+		fam_ops.mc2_mce = k8_mc2_mce;
 		break;
 
 	case 0x12:
-		fam_ops->mc0_mce = f12h_mc0_mce;
-		fam_ops->mc1_mce = k8_mc1_mce;
-		fam_ops->mc2_mce = k8_mc2_mce;
+		fam_ops.mc0_mce = f12h_mc0_mce;
+		fam_ops.mc1_mce = k8_mc1_mce;
+		fam_ops.mc2_mce = k8_mc2_mce;
 		break;
 
 	case 0x14:
-		fam_ops->mc0_mce = cat_mc0_mce;
-		fam_ops->mc1_mce = cat_mc1_mce;
-		fam_ops->mc2_mce = k8_mc2_mce;
+		fam_ops.mc0_mce = cat_mc0_mce;
+		fam_ops.mc1_mce = cat_mc1_mce;
+		fam_ops.mc2_mce = k8_mc2_mce;
 		break;
 
 	case 0x15:
 		xec_mask = c->x86_model == 0x60 ? 0x3f : 0x1f;
 
-		fam_ops->mc0_mce = f15h_mc0_mce;
-		fam_ops->mc1_mce = f15h_mc1_mce;
-		fam_ops->mc2_mce = f15h_mc2_mce;
+		fam_ops.mc0_mce = f15h_mc0_mce;
+		fam_ops.mc1_mce = f15h_mc1_mce;
+		fam_ops.mc2_mce = f15h_mc2_mce;
 		break;
 
 	case 0x16:
 		xec_mask = 0x1f;
-		fam_ops->mc0_mce = cat_mc0_mce;
-		fam_ops->mc1_mce = cat_mc1_mce;
-		fam_ops->mc2_mce = f16h_mc2_mce;
+		fam_ops.mc0_mce = cat_mc0_mce;
+		fam_ops.mc1_mce = cat_mc1_mce;
+		fam_ops.mc2_mce = f16h_mc2_mce;
 		break;
 
 	case 0x17:
 	case 0x18:
 		pr_warn("Decoding supported only on Scalable MCA processors.\n");
-		goto err_out;
-		break;
+		return -EINVAL;
 
 	default:
 		printk(KERN_WARNING "Huh? What family is it: 0x%x?!\n", c->x86);
-		goto err_out;
+		return -EINVAL;
 	}
 
 out:
@@ -1257,11 +1253,6 @@ static int __init mce_amd_init(void)
 	mce_register_decode_chain(&amd_mce_dec_nb);
 
 	return 0;
-
-err_out:
-	kfree(fam_ops);
-	fam_ops = NULL;
-	return -EINVAL;
 }
 early_initcall(mce_amd_init);
 
@@ -1269,7 +1260,7 @@ early_initcall(mce_amd_init);
 static void __exit mce_amd_exit(void)
 {
 	mce_unregister_decode_chain(&amd_mce_dec_nb);
-	kfree(fam_ops);
+	memset(&fam_ops, 0, sizeof(struct amd_decoder_ops));
 }
 
 MODULE_DESCRIPTION("AMD MCE decoder");
-- 
2.21.0


-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette