From 772c3ff385eda0d0b4744596f87b79a17f8c9282 Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Tue, 27 Nov 2012 14:32:09 +0800 Subject: x86, AMD, NB: Add multi-domain support Fix get_node_id to match northbridge IDs from the array of detected ones, allowing multi-server support such as with Numascale's NumaConnect, renaming to 'amd_get_node_id' for consistency. Signed-off-by: Daniel J Blueman Link: http://lkml.kernel.org/r/1353997932-8475-1-git-send-email-daniel@numascale-asia.com [Boris: shorten lines to fit 80 cols] Signed-off-by: Borislav Petkov --- drivers/edac/amd64_edac.c | 6 +++--- drivers/edac/amd64_edac.h | 6 ------ 2 files changed, 3 insertions(+), 9 deletions(-) (limited to 'drivers') diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ad8bf2aa629..a3fe39b1f78 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -2474,7 +2474,7 @@ static int amd64_init_one_instance(struct pci_dev *F2) struct mem_ctl_info *mci = NULL; struct edac_mc_layer layers[2]; int err = 0, ret; - u8 nid = get_node_id(F2); + u16 nid = amd_get_node_id(F2); ret = -ENOMEM; pvt = kzalloc(sizeof(struct amd64_pvt), GFP_KERNEL); @@ -2566,7 +2566,7 @@ err_ret: static int amd64_probe_one_instance(struct pci_dev *pdev, const struct pci_device_id *mc_type) { - u8 nid = get_node_id(pdev); + u16 nid = amd_get_node_id(pdev); struct pci_dev *F3 = node_to_amd_nb(nid)->misc; struct ecc_settings *s; int ret = 0; @@ -2616,7 +2616,7 @@ static void amd64_remove_one_instance(struct pci_dev *pdev) { struct mem_ctl_info *mci; struct amd64_pvt *pvt; - u8 nid = get_node_id(pdev); + u16 nid = amd_get_node_id(pdev); struct pci_dev *F3 = node_to_amd_nb(nid)->misc; struct ecc_settings *s = ecc_stngs[nid]; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index e864f407806..cd7845fcc27 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -292,12 +292,6 @@ /* MSRs */ #define MSR_MCGCTL_NBE BIT(4) -/* AMD sets the first MC device at device ID 0x18. */ -static inline u8 get_node_id(struct pci_dev *pdev) -{ - return PCI_SLOT(pdev->devfn) - 0x18; -} - enum amd_families { K8_CPUS = 0, F10_CPUS, -- cgit v1.2.3-70-g09d2 From 8b84c8df38d5796da2e8cd051666d203ddabcb62 Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Tue, 27 Nov 2012 14:32:10 +0800 Subject: x86, AMD, NB: Use u16 for northbridge IDs in amd_get_nb_id Change amd_get_nb_id to return u16 to support >255 memory controllers, and related consistency fixes. Signed-off-by: Daniel J Blueman Link: http://lkml.kernel.org/r/1353997932-8475-2-git-send-email-daniel@numascale-asia.com Signed-off-by: Borislav Petkov --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/amd.c | 4 ++-- drivers/edac/amd64_edac.c | 5 +++-- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'drivers') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 888184b2fc8..cf500543f6f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -943,7 +943,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); -extern int amd_get_nb_id(int cpu); +extern u16 amd_get_nb_id(int cpu); struct aperfmperf { u64 aperf, mperf; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 15239fffd6f..782c456eaa0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -364,9 +364,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) #endif } -int amd_get_nb_id(int cpu) +u16 amd_get_nb_id(int cpu) { - int id = 0; + u16 id = 0; #ifdef CONFIG_SMP id = per_cpu(cpu_llc_id, cpu); #endif diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index a3fe39b1f78..29be39d0207 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -939,7 +939,8 @@ static u64 get_error_address(struct mce *m) struct amd64_pvt *pvt; u64 cc6_base, tmp_addr; u32 tmp; - u8 mce_nid, intlv_en; + u16 mce_nid; + u8 intlv_en; if ((addr & GENMASK(24, 47)) >> 24 != 0x00fdf7) return addr; @@ -2181,7 +2182,7 @@ static int init_csrows(struct mem_ctl_info *mci) } /* get all cores on this DCT */ -static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, unsigned nid) +static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid) { int cpu; -- cgit v1.2.3-70-g09d2 From e2c0bffea2574c088d86a9f1f661a84bc8fea2fd Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Fri, 30 Nov 2012 16:44:19 +0800 Subject: amd64_edac: Fix PCI function lookup Fix locating sibling memory controller PCI functions by using the correct PCI domain and use a northbridge descriptor only if found. We need to at least warn if it wasn't found so that it gets fixed and we don't go off with wrong results. Signed-off-by: Daniel J Blueman Link: http://lkml.kernel.org/r/1354265060-22956-1-git-send-email-daniel@numascale-asia.com [Boris: remove wrong comment, sanitize code and warn if NB desc lookup fails] Signed-off-by: Borislav Petkov --- drivers/edac/amd64_edac.c | 72 +++++++++++++++++++++++++---------------------- 1 file changed, 38 insertions(+), 34 deletions(-) (limited to 'drivers') diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 29be39d0207..da76912a873 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -980,10 +980,29 @@ static u64 get_error_address(struct mce *m) return addr; } +static struct pci_dev *pci_get_related_function(unsigned int vendor, + unsigned int device, + struct pci_dev *related) +{ + struct pci_dev *dev = NULL; + + while ((dev = pci_get_device(vendor, device, dev))) { + if (pci_domain_nr(dev->bus) == pci_domain_nr(related->bus) && + (dev->bus->number == related->bus->number) && + (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn))) + break; + } + + return dev; +} + static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) { + struct amd_northbridge *nb; + struct pci_dev *misc, *f1 = NULL; struct cpuinfo_x86 *c = &boot_cpu_data; int off = range << 3; + u32 llim; amd64_read_pci_cfg(pvt->F1, DRAM_BASE_LO + off, &pvt->ranges[range].base.lo); amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_LO + off, &pvt->ranges[range].lim.lo); @@ -997,30 +1016,32 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) amd64_read_pci_cfg(pvt->F1, DRAM_BASE_HI + off, &pvt->ranges[range].base.hi); amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_HI + off, &pvt->ranges[range].lim.hi); - /* Factor in CC6 save area by reading dst node's limit reg */ - if (c->x86 == 0x15) { - struct pci_dev *f1 = NULL; - u8 nid = dram_dst_node(pvt, range); - u32 llim; + /* F15h: factor in CC6 save area by reading dst node's limit reg */ + if (c->x86 != 0x15) + return; - f1 = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0x18 + nid, 1)); - if (WARN_ON(!f1)) - return; + nb = node_to_amd_nb(dram_dst_node(pvt, range)); + if (WARN_ON(!nb)) + return; - amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); + misc = nb->misc; + f1 = pci_get_related_function(misc->vendor, PCI_DEVICE_ID_AMD_15H_NB_F1, misc); + if (WARN_ON(!f1)) + return; - pvt->ranges[range].lim.lo &= GENMASK(0, 15); + amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); - /* {[39:27],111b} */ - pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16; + pvt->ranges[range].lim.lo &= GENMASK(0, 15); - pvt->ranges[range].lim.hi &= GENMASK(0, 7); + /* {[39:27],111b} */ + pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16; - /* [47:40] */ - pvt->ranges[range].lim.hi |= llim >> 13; + pvt->ranges[range].lim.hi &= GENMASK(0, 7); - pci_dev_put(f1); - } + /* [47:40] */ + pvt->ranges[range].lim.hi |= llim >> 13; + + pci_dev_put(f1); } static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr, @@ -1673,23 +1694,6 @@ static struct amd64_family_type amd64_family_types[] = { }, }; -static struct pci_dev *pci_get_related_function(unsigned int vendor, - unsigned int device, - struct pci_dev *related) -{ - struct pci_dev *dev = NULL; - - dev = pci_get_device(vendor, device, dev); - while (dev) { - if ((dev->bus->number == related->bus->number) && - (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn))) - break; - dev = pci_get_device(vendor, device, dev); - } - - return dev; -} - /* * These are tables of eigenvectors (one per line) which can be used for the * construction of the syndrome tables. The modified syndrome search algorithm -- cgit v1.2.3-70-g09d2 From c7e5301a1b7c3f47af635a8b1b14480b81426025 Mon Sep 17 00:00:00 2001 From: Daniel J Blueman Date: Fri, 30 Nov 2012 16:44:20 +0800 Subject: amd64_edac: Fix type usage in NB IDs and memory ranges Use appropriate types for northbridge IDs and memory ranges. Mark immutable data const and keep within compilation unit on related structures. Signed-off-by: Daniel J Blueman Link: http://lkml.kernel.org/r/1354265060-22956-2-git-send-email-daniel@numascale-asia.com [Boris: Drop arg change to node_to_amd_nb] Signed-off-by: Borislav Petkov --- drivers/edac/amd64_edac.c | 26 +++++++++++++------------- drivers/edac/amd64_edac.h | 6 +++--- 2 files changed, 16 insertions(+), 16 deletions(-) (limited to 'drivers') diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index da76912a873..2d3f8825e8b 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -31,7 +31,7 @@ static struct ecc_settings **ecc_stngs; * *FIXME: Produce a better mapping/linearisation. */ -struct scrubrate { +static const struct scrubrate { u32 scrubval; /* bit pattern for scrub rate */ u32 bandwidth; /* bandwidth consumed (bytes/sec) */ } scrubrates[] = { @@ -239,7 +239,7 @@ static int amd64_get_scrub_rate(struct mem_ctl_info *mci) * DRAM base/limit associated with node_id */ static bool amd64_base_limit_match(struct amd64_pvt *pvt, u64 sys_addr, - unsigned nid) + u8 nid) { u64 addr; @@ -265,7 +265,7 @@ static struct mem_ctl_info *find_mc_by_sys_addr(struct mem_ctl_info *mci, u64 sys_addr) { struct amd64_pvt *pvt; - unsigned node_id; + u8 node_id; u32 intlv_en, bits; /* @@ -1327,7 +1327,7 @@ static u8 f1x_determine_channel(struct amd64_pvt *pvt, u64 sys_addr, } /* Convert the sys_addr to the normalized DCT address */ -static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, unsigned range, +static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range, u64 sys_addr, bool hi_rng, u32 dct_sel_base_addr) { @@ -1403,7 +1403,7 @@ static int f10_process_possible_spare(struct amd64_pvt *pvt, u8 dct, int csrow) * -EINVAL: NOT FOUND * 0..csrow = Chip-Select Row */ -static int f1x_lookup_addr_in_dct(u64 in_addr, u32 nid, u8 dct) +static int f1x_lookup_addr_in_dct(u64 in_addr, u8 nid, u8 dct) { struct mem_ctl_info *mci; struct amd64_pvt *pvt; @@ -1701,7 +1701,7 @@ static struct amd64_family_type amd64_family_types[] = { * * Algorithm courtesy of Ross LaFetra from AMD. */ -static u16 x4_vectors[] = { +static const u16 x4_vectors[] = { 0x2f57, 0x1afe, 0x66cc, 0xdd88, 0x11eb, 0x3396, 0x7f4c, 0xeac8, 0x0001, 0x0002, 0x0004, 0x0008, @@ -1740,7 +1740,7 @@ static u16 x4_vectors[] = { 0x19a9, 0x2efe, 0xb5cc, 0x6f88, }; -static u16 x8_vectors[] = { +static const u16 x8_vectors[] = { 0x0145, 0x028a, 0x2374, 0x43c8, 0xa1f0, 0x0520, 0x0a40, 0x1480, 0x0211, 0x0422, 0x0844, 0x1088, 0x01b0, 0x44e0, 0x23c0, 0xed80, 0x1011, 0x0116, 0x022c, 0x0458, 0x08b0, 0x8c60, 0x2740, 0x4e80, @@ -1762,7 +1762,7 @@ static u16 x8_vectors[] = { 0x0100, 0x0200, 0x0400, 0x0800, 0x1000, 0x2000, 0x4000, 0x8000, }; -static int decode_syndrome(u16 syndrome, u16 *vectors, unsigned num_vecs, +static int decode_syndrome(u16 syndrome, const u16 *vectors, unsigned num_vecs, unsigned v_dim) { unsigned int i, err_sym; @@ -2196,7 +2196,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid) } /* check MCG_CTL on all the cpus on this node */ -static bool amd64_nb_mce_bank_enabled_on_node(unsigned nid) +static bool amd64_nb_mce_bank_enabled_on_node(u16 nid) { cpumask_var_t mask; int cpu, nbe; @@ -2229,7 +2229,7 @@ out: return ret; } -static int toggle_ecc_err_reporting(struct ecc_settings *s, u8 nid, bool on) +static int toggle_ecc_err_reporting(struct ecc_settings *s, u16 nid, bool on) { cpumask_var_t cmask; int cpu; @@ -2267,7 +2267,7 @@ static int toggle_ecc_err_reporting(struct ecc_settings *s, u8 nid, bool on) return 0; } -static bool enable_ecc_error_reporting(struct ecc_settings *s, u8 nid, +static bool enable_ecc_error_reporting(struct ecc_settings *s, u16 nid, struct pci_dev *F3) { bool ret = true; @@ -2319,7 +2319,7 @@ static bool enable_ecc_error_reporting(struct ecc_settings *s, u8 nid, return ret; } -static void restore_ecc_error_reporting(struct ecc_settings *s, u8 nid, +static void restore_ecc_error_reporting(struct ecc_settings *s, u16 nid, struct pci_dev *F3) { u32 value, mask = 0x3; /* UECC/CECC enable */ @@ -2358,7 +2358,7 @@ static const char *ecc_msg = "'ecc_enable_override'.\n" " (Note that use of the override may cause unknown side effects.)\n"; -static bool ecc_enabled(struct pci_dev *F3, u8 nid) +static bool ecc_enabled(struct pci_dev *F3, u16 nid) { u32 value; u8 ecc_en = 0; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index cd7845fcc27..35637d83f23 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -334,7 +334,7 @@ struct amd64_pvt { /* pci_device handles which we utilize */ struct pci_dev *F1, *F2, *F3; - unsigned mc_node_id; /* MC index of this MC node */ + u16 mc_node_id; /* MC index of this MC node */ int ext_model; /* extended model value of this node */ int channel_count; @@ -387,7 +387,7 @@ struct err_info { u32 offset; }; -static inline u64 get_dram_base(struct amd64_pvt *pvt, unsigned i) +static inline u64 get_dram_base(struct amd64_pvt *pvt, u8 i) { u64 addr = ((u64)pvt->ranges[i].base.lo & 0xffff0000) << 8; @@ -397,7 +397,7 @@ static inline u64 get_dram_base(struct amd64_pvt *pvt, unsigned i) return (((u64)pvt->ranges[i].base.hi & 0x000000ff) << 40) | addr; } -static inline u64 get_dram_limit(struct amd64_pvt *pvt, unsigned i) +static inline u64 get_dram_limit(struct amd64_pvt *pvt, u8 i) { u64 lim = (((u64)pvt->ranges[i].lim.lo & 0xffff0000) << 8) | 0x00ffffff; -- cgit v1.2.3-70-g09d2