From 028c221ed1904af9ac3c5162ee98f48966de6b3d Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 9 Nov 2020 21:06:56 +0000 Subject: x86/CPU/AMD: Save AMD NodeId as cpu_die_id AMD systems provide a "NodeId" value that represents a global ID indicating to which "Node" a logical CPU belongs. The "Node" is a physical structure equivalent to a Die, and it should not be confused with logical structures like NUMA nodes. Logical nodes can be adjusted based on firmware or other settings whereas the physical nodes/dies are fixed based on hardware topology. The NodeId value can be used when a physical ID is needed by software. Save the AMD NodeId to struct cpuinfo_x86.cpu_die_id. Use the value from CPUID or MSR as appropriate. Default to phys_proc_id otherwise. Do so for both AMD and Hygon systems. Drop the node_id parameter from cacheinfo_*_init_llc_id() as it is no longer needed. Update the x86 topology documentation. Suggested-by: Borislav Petkov Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201109210659.754018-2-Yazen.Ghannam@amd.com --- arch/x86/include/asm/cacheinfo.h | 4 ++-- arch/x86/kernel/cpu/amd.c | 11 +++++------ arch/x86/kernel/cpu/cacheinfo.c | 6 +++--- arch/x86/kernel/cpu/hygon.c | 11 +++++------ 4 files changed, 15 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h index 86b63c7feab7..86b2e0dcc4bf 100644 --- a/arch/x86/include/asm/cacheinfo.h +++ b/arch/x86/include/asm/cacheinfo.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_CACHEINFO_H #define _ASM_X86_CACHEINFO_H -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id); -void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id); +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu); +void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu); #endif /* _ASM_X86_CACHEINFO_H */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6062ce586b95..2f1fbd8150af 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -330,7 +330,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) */ static void amd_get_topology(struct cpuinfo_x86 *c) { - u8 node_id; int cpu = smp_processor_id(); /* get information required for multi-node processors */ @@ -340,7 +339,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 0xff; + c->cpu_die_id = ecx & 0xff; if (c->x86 == 0x15) c->cu_id = ebx & 0xff; @@ -360,15 +359,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c) if (!err) c->x86_coreid_bits = get_count_order(c->x86_max_cores); - cacheinfo_amd_init_llc_id(c, cpu, node_id); + cacheinfo_amd_init_llc_id(c, cpu); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - node_id = value & 7; + c->cpu_die_id = value & 7; - per_cpu(cpu_llc_id, cpu) = node_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; } else return; @@ -393,7 +392,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) /* Convert the initial APIC ID into the socket ID */ c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ - per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id; } static void amd_detect_ppin(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 57074cf3ad7c..f9ac682e75e7 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -646,7 +646,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu) { /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -657,7 +657,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) if (c->x86 < 0x17) { /* LLC is at the node level. */ - per_cpu(cpu_llc_id, cpu) = node_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) { /* * LLC is at the core complex level. @@ -684,7 +684,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) } } -void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu) { /* * We may have multiple LLCs if L3 caches exist, so check if we diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index ac6c30e5801d..dc0840aae26c 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -65,7 +65,6 @@ static void hygon_get_topology_early(struct cpuinfo_x86 *c) */ static void hygon_get_topology(struct cpuinfo_x86 *c) { - u8 node_id; int cpu = smp_processor_id(); /* get information required for multi-node processors */ @@ -75,7 +74,7 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 0xff; + c->cpu_die_id = ecx & 0xff; c->cpu_core_id = ebx & 0xff; @@ -93,14 +92,14 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) /* Socket ID is ApicId[6] for these processors. */ c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; - cacheinfo_hygon_init_llc_id(c, cpu, node_id); + cacheinfo_hygon_init_llc_id(c, cpu); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - node_id = value & 7; + c->cpu_die_id = value & 7; - per_cpu(cpu_llc_id, cpu) = node_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; } else return; @@ -123,7 +122,7 @@ static void hygon_detect_cmp(struct cpuinfo_x86 *c) /* Convert the initial APIC ID into the socket ID */ c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ - per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id; } static void srat_detect_node(struct cpuinfo_x86 *c) -- cgit From db970bd231c2264a062e0de4dcf4ead5e6669e7a Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 9 Nov 2020 21:06:57 +0000 Subject: x86/CPU/AMD: Remove amd_get_nb_id() The Last Level Cache ID is returned by amd_get_nb_id(). In practice, this value is the same as the AMD NodeId for callers of this function. The NodeId is saved in struct cpuinfo_x86.cpu_die_id. Replace calls to amd_get_nb_id() with the logical CPU's cpu_die_id and remove the function. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201109210659.754018-3-Yazen.Ghannam@amd.com --- arch/x86/events/amd/core.c | 2 +- arch/x86/include/asm/processor.h | 2 -- arch/x86/kernel/amd_nb.c | 4 ++-- arch/x86/kernel/cpu/amd.c | 6 ------ arch/x86/kernel/cpu/cacheinfo.c | 2 +- arch/x86/kernel/cpu/mce/amd.c | 4 ++-- arch/x86/kernel/cpu/mce/inject.c | 4 ++-- 7 files changed, 8 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 39eb276d0277..2c1791c4a518 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -538,7 +538,7 @@ static void amd_pmu_cpu_starting(int cpu) if (!x86_pmu.amd_nb_constraints) return; - nb_id = amd_get_nb_id(cpu); + nb_id = topology_die_id(cpu); WARN_ON_ONCE(nb_id == BAD_APICID); for_each_online_cpu(i) { diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 82a08b585818..c20a52b5534b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -813,10 +813,8 @@ extern int set_tsc_mode(unsigned int val); DECLARE_PER_CPU(u64, msr_misc_features_shadow); #ifdef CONFIG_CPU_SUP_AMD -extern u16 amd_get_nb_id(int cpu); extern u32 amd_get_nodes_per_socket(void); #else -static inline u16 amd_get_nb_id(int cpu) { return 0; } static inline u32 amd_get_nodes_per_socket(void) { return 0; } #endif diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 18f6b7c4bd79..b4396952c9a6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -384,7 +384,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res) int amd_get_subcaches(int cpu) { - struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; + struct pci_dev *link = node_to_amd_nb(topology_die_id(cpu))->link; unsigned int mask; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) @@ -398,7 +398,7 @@ int amd_get_subcaches(int cpu) int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; - struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); + struct amd_northbridge *nb = node_to_amd_nb(topology_die_id(cpu)); unsigned int reg; int cuid; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2f1fbd8150af..1f71c7616917 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -424,12 +424,6 @@ clear_ppin: clear_cpu_cap(c, X86_FEATURE_AMD_PPIN); } -u16 amd_get_nb_id(int cpu) -{ - return per_cpu(cpu_llc_id, cpu); -} -EXPORT_SYMBOL_GPL(amd_get_nb_id); - u32 amd_get_nodes_per_socket(void) { return nodes_per_socket; diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index f9ac682e75e7..3ca9be482a9e 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -580,7 +580,7 @@ static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) if (index < 3) return; - node = amd_get_nb_id(smp_processor_id()); + node = topology_die_id(smp_processor_id()); this_leaf->nb = node_to_amd_nb(node); if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) amd_calc_l3_indices(this_leaf->nb); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 0c6b02dd744c..e486f96b3cb3 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1341,7 +1341,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, return -ENODEV; if (is_shared_bank(bank)) { - nb = node_to_amd_nb(amd_get_nb_id(cpu)); + nb = node_to_amd_nb(topology_die_id(cpu)); /* threshold descriptor already initialized on this node? */ if (nb && nb->bank4) { @@ -1445,7 +1445,7 @@ static void threshold_remove_bank(struct threshold_bank *bank) * The last CPU on this node using the shared bank is going * away, remove that bank now. */ - nb = node_to_amd_nb(amd_get_nb_id(smp_processor_id())); + nb = node_to_amd_nb(topology_die_id(smp_processor_id())); nb->bank4 = NULL; } diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 3a44346f2276..7b360731fc2d 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -522,8 +522,8 @@ static void do_inject(void) if (boot_cpu_has(X86_FEATURE_AMD_DCM) && b == 4 && boot_cpu_data.x86 < 0x17) { - toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); - cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + toggle_nb_mca_mst_cpu(topology_die_id(cpu)); + cpu = get_nbc_for_node(topology_die_id(cpu)); } get_online_cpus(); -- cgit From cb09a379724d299c603a7a79f444f52a9a75b8d2 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 9 Nov 2020 21:06:59 +0000 Subject: x86/topology: Set cpu_die_id only if DIE_TYPE found CPUID Leaf 0x1F defines a DIE_TYPE level (nb: ECX[8:15] level type == 0x5), but CPUID Leaf 0xB does not. However, detect_extended_topology() will set struct cpuinfo_x86.cpu_die_id regardless of whether a valid Die ID was found. Only set cpu_die_id if a DIE_TYPE level is found. CPU topology code may use another value for cpu_die_id, e.g. the AMD NodeId on AMD-based systems. Code ordering should be maintained so that the CPUID Leaf 0x1F Die ID value will take precedence on systems that may use another value. Suggested-by: Borislav Petkov Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201109210659.754018-5-Yazen.Ghannam@amd.com --- arch/x86/kernel/cpu/topology.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index d3a0791bc052..1068002c8532 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; unsigned int core_select_mask, core_level_siblings; unsigned int die_select_mask, die_level_siblings; + bool die_level_present = false; int leaf; leaf = detect_extended_topology_leaf(c); @@ -126,6 +127,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) { + die_level_present = true; die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } @@ -139,8 +141,12 @@ int detect_extended_topology(struct cpuinfo_x86 *c) c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width) & core_select_mask; - c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, - core_plus_mask_width) & die_select_mask; + + if (die_level_present) { + c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, + core_plus_mask_width) & die_select_mask; + } + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, die_plus_mask_width); /* -- cgit From 262bd5724afdefd4c48a260d6100e78cc43ee06b Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Fri, 27 Nov 2020 12:13:24 -0500 Subject: x86/cpu/amd: Remove dead code for TSEG region remapping Commit 26bfa5f89486 ("x86, amd: Cleanup init_amd") moved the code that remaps the TSEG region using 4k pages from init_amd() to bsp_init_amd(). However, bsp_init_amd() is executed well before the direct mapping is actually created: setup_arch() -> early_cpu_init() -> early_identify_cpu() -> this_cpu->c_bsp_init() -> bsp_init_amd() ... -> init_mem_mapping() So the change effectively disabled the 4k remapping, because pfn_range_is_mapped() is always false at this point. It has been over six years since the commit, and no-one seems to have noticed this, so just remove the code. The original code was also incomplete, since it doesn't check how large the TSEG address range actually is, so it might remap only part of it in any case. Hygon has copied the incorrect version, so the code has never run on it since the cpu support was added two years ago. Remove it from there as well. Committer notes: This workaround is incomplete anyway: 1. The code must check MSRC001_0113.TValid (SMM TSeg Mask MSR) first, to check whether the TSeg address range is enabled. 2. The code must check whether the range is not 2M aligned - if it is, there's nothing to work around. 3. In all the BIOSes tested, the TSeg range is in a e820 reserved area and those are not mapped anymore, after 66520ebc2df3 ("x86, mm: Only direct map addresses that are marked as E820_RAM") which means, there's nothing to be worked around either. So let's rip it out. Signed-off-by: Arvind Sankar Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201127171324.1846019-1-nivedita@alum.mit.edu --- arch/x86/kernel/cpu/amd.c | 21 --------------------- arch/x86/kernel/cpu/hygon.c | 20 -------------------- 2 files changed, 41 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 1f71c7616917..f8ca66f3d861 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -23,7 +23,6 @@ #ifdef CONFIG_X86_64 # include -# include #endif #include "cpu.h" @@ -509,26 +508,6 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c) static void bsp_init_amd(struct cpuinfo_x86 *c) { - -#ifdef CONFIG_X86_64 - if (c->x86 >= 0xf) { - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { - unsigned long pfn = tseg >> PAGE_SHIFT; - - pr_debug("tseg: %010llx\n", tseg); - if (pfn_range_is_mapped(pfn, pfn + 1)) - set_memory_4k((unsigned long)__va(tseg), 1); - } - } -#endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { if (c->x86 > 0x10 || diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index dc0840aae26c..ae59115d18f9 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -14,9 +14,6 @@ #include #include #include -#ifdef CONFIG_X86_64 -# include -#endif #include "cpu.h" @@ -203,23 +200,6 @@ static void early_init_hygon_mc(struct cpuinfo_x86 *c) static void bsp_init_hygon(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_64 - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { - unsigned long pfn = tseg >> PAGE_SHIFT; - - pr_debug("tseg: %010llx\n", tseg); - if (pfn_range_is_mapped(pfn, pfn + 1)) - set_memory_4k((unsigned long)__va(tseg), 1); - } -#endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { u64 val; -- cgit