From 37a19366e10b95380bf33e7a8b02509980399d7e Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Mon, 27 Feb 2023 17:03:52 +0100 Subject: x86/microcode/AMD: Get rid of __find_equiv_id() Merge it into its only call site. No functional changes. Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230227160352.7260-1-bp@alien8.de --- arch/x86/kernel/cpu/microcode/amd.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index f5fdeb1e3606..dd33ee872339 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -596,11 +596,6 @@ void reload_ucode_amd(unsigned int cpu) } } } -static u16 __find_equiv_id(unsigned int cpu) -{ - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - return find_equiv_id(&equiv_table, uci->cpu_sig.sig); -} /* * a small, trivial cache of per-family ucode patches @@ -651,9 +646,11 @@ static void free_cache(void) static struct ucode_patch *find_patch(unsigned int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; u16 equiv_id; - equiv_id = __find_equiv_id(cpu); + + equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig); if (!equiv_id) return NULL; -- cgit v1.2.3 From e281d5cad1f3924edf1042441b98c25204ae0def Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Tue, 2 May 2023 12:42:32 -0500 Subject: x86/microcode/amd: Remove unneeded pointer arithmetic Remove unneeded pointer increment arithmetic, the pointer is set at the beginning of the loop. Signed-off-by: Nathan Fontenot Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230502174232.73880-1-nathan.fontenot@amd.com --- arch/x86/kernel/cpu/microcode/amd.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index dd33ee872339..f14f4ea0b537 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -78,8 +78,6 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig) if (sig == e->installed_cpu) return e->equiv_cpu; - - e++; } return 0; } -- cgit v1.2.3 From f6b980646b93a8c585b4ed991b8a34e8fc6ef847 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:16 +0200 Subject: x86/mtrr: Remove physical address size calculation The physical address width calculation in mtrr_bp_init() can easily be replaced with using the already available value x86_phys_bits from struct cpuinfo_x86. The same information source can be used in mtrr/cleanup.c, removing the need to pass that value on to mtrr_cleanup(). In print_mtrr_state() use x86_phys_bits instead of recalculating it from size_or_mask. Move setting of size_or_mask and size_and_mask into a dedicated new function in mtrr/generic.c, enabling to make those 2 variables static, as they are used in generic.c only now. Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-2-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/cleanup.c | 16 +++++----- arch/x86/kernel/cpu/mtrr/generic.c | 12 +++++++- arch/x86/kernel/cpu/mtrr/mtrr.c | 61 +++++--------------------------------- arch/x86/kernel/cpu/mtrr/mtrr.h | 4 +-- 4 files changed, 29 insertions(+), 64 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index b5f43049fa5f..70314093bb9b 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -173,7 +173,7 @@ early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup); static void __init set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, - unsigned char type, unsigned int address_bits) + unsigned char type) { u32 base_lo, base_hi, mask_lo, mask_hi; u64 base, mask; @@ -183,7 +183,7 @@ set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, return; } - mask = (1ULL << address_bits) - 1; + mask = (1ULL << boot_cpu_data.x86_phys_bits) - 1; mask &= ~((((u64)sizek) << 10) - 1); base = ((u64)basek) << 10; @@ -209,7 +209,7 @@ save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, range_state[reg].type = type; } -static void __init set_var_mtrr_all(unsigned int address_bits) +static void __init set_var_mtrr_all(void) { unsigned long basek, sizek; unsigned char type; @@ -220,7 +220,7 @@ static void __init set_var_mtrr_all(unsigned int address_bits) sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10); type = range_state[reg].type; - set_var_mtrr(reg, basek, sizek, type, address_bits); + set_var_mtrr(reg, basek, sizek, type); } } @@ -680,7 +680,7 @@ static int __init mtrr_search_optimal_index(void) return index_good; } -int __init mtrr_cleanup(unsigned address_bits) +int __init mtrr_cleanup(void) { unsigned long x_remove_base, x_remove_size; unsigned long base, size, def, dummy; @@ -742,7 +742,7 @@ int __init mtrr_cleanup(unsigned address_bits) mtrr_print_out_one_result(i); if (!result[i].bad) { - set_var_mtrr_all(address_bits); + set_var_mtrr_all(); pr_debug("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; @@ -786,7 +786,7 @@ int __init mtrr_cleanup(unsigned address_bits) gran_size = result[i].gran_sizek; gran_size <<= 10; x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); - set_var_mtrr_all(address_bits); + set_var_mtrr_all(); pr_debug("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; @@ -802,7 +802,7 @@ int __init mtrr_cleanup(unsigned address_bits) return 0; } #else -int __init mtrr_cleanup(unsigned address_bits) +int __init mtrr_cleanup(void) { return 0; } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index ee09d359e08f..3922552340b1 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -38,6 +38,16 @@ u64 mtrr_tom2; struct mtrr_state_type mtrr_state; EXPORT_SYMBOL_GPL(mtrr_state); +static u64 size_or_mask, size_and_mask; + +void __init mtrr_set_mask(void) +{ + unsigned int phys_addr = boot_cpu_data.x86_phys_bits; + + size_or_mask = ~GENMASK_ULL(phys_addr - PAGE_SHIFT - 1, 0); + size_and_mask = ~size_or_mask & GENMASK_ULL(39, 20); +} + /* * BIOS is expected to clear MtrrFixDramModEn bit, see for example * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD @@ -422,7 +432,7 @@ static void __init print_mtrr_state(void) } pr_debug("MTRR variable ranges %sabled:\n", mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); - high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; + high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 783f3210d582..1bdab16f16bd 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -67,8 +67,6 @@ static bool mtrr_enabled(void) unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; static DEFINE_MUTEX(mtrr_mutex); -u64 size_or_mask, size_and_mask; - const struct mtrr_ops *mtrr_if; /* Returns non-zero if we have the write-combining memory type */ @@ -619,77 +617,34 @@ static struct syscore_ops mtrr_syscore_ops = { int __initdata changed_by_mtrr_cleanup; -#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1)) /** - * mtrr_bp_init - initialize mtrrs on the boot CPU + * mtrr_bp_init - initialize MTRRs on the boot CPU * * This needs to be called early; before any of the other CPUs are * initialized (i.e. before smp_init()). - * */ void __init mtrr_bp_init(void) { const char *why = "(not available)"; - u32 phys_addr; - phys_addr = 32; + mtrr_set_mask(); - if (boot_cpu_has(X86_FEATURE_MTRR)) { + if (cpu_feature_enabled(X86_FEATURE_MTRR)) { mtrr_if = &generic_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(36); - size_and_mask = 0x00f00000; - phys_addr = 36; - - /* - * This is an AMD specific MSR, but we assume(hope?) that - * Intel will implement it too when they extend the address - * bus of the Xeon. - */ - if (cpuid_eax(0x80000000) >= 0x80000008) { - phys_addr = cpuid_eax(0x80000008) & 0xff; - /* CPUID workaround for Intel 0F33/0F34 CPU */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_data.x86 == 0xF && - boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_stepping == 0x3 || - boot_cpu_data.x86_stepping == 0x4)) - phys_addr = 36; - - size_or_mask = SIZE_OR_MASK_BITS(phys_addr); - size_and_mask = ~size_or_mask & 0xfffff00000ULL; - } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && - boot_cpu_data.x86 == 6) { - /* - * VIA C* family have Intel style MTRRs, - * but don't support PAE - */ - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - phys_addr = 32; - } } else { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: - if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) { - /* Pre-Athlon (K6) AMD CPU MTRRs */ + /* Pre-Athlon (K6) AMD CPU MTRRs */ + if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) mtrr_if = &amd_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - } break; case X86_VENDOR_CENTAUR: - if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) { + if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) mtrr_if = ¢aur_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - } break; case X86_VENDOR_CYRIX: - if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) { + if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) mtrr_if = &cyrix_mtrr_ops; - size_or_mask = SIZE_OR_MASK_BITS(32); - size_and_mask = 0; - } break; default: break; @@ -703,7 +658,7 @@ void __init mtrr_bp_init(void) /* BIOS may override */ if (get_mtrr_state()) { memory_caching_control |= CACHE_MTRR; - changed_by_mtrr_cleanup = mtrr_cleanup(phys_addr); + changed_by_mtrr_cleanup = mtrr_cleanup(); } else { mtrr_if = NULL; why = "by BIOS"; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 02eb5871492d..a00987e6cc1c 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -51,7 +51,6 @@ void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); -extern u64 size_or_mask, size_and_mask; extern const struct mtrr_ops *mtrr_if; #define is_cpu(vnd) (mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd) @@ -60,6 +59,7 @@ extern unsigned int num_var_ranges; extern u64 mtrr_tom2; extern struct mtrr_state_type mtrr_state; +void mtrr_set_mask(void); void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); @@ -70,4 +70,4 @@ extern const struct mtrr_ops cyrix_mtrr_ops; extern const struct mtrr_ops centaur_mtrr_ops; extern int changed_by_mtrr_cleanup; -extern int mtrr_cleanup(unsigned address_bits); +extern int mtrr_cleanup(void); -- cgit v1.2.3 From e94cd1503b153ea753f0c4ed9d5ed12e7abd1306 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:12 +0200 Subject: x86/smpboot: Get rid of cpu_init_secondary() The synchronization of the AP with the control CPU is a SMP boot problem and has nothing to do with cpu_init(). Open code cpu_init_secondary() in start_secondary() and move wait_for_master_cpu() into the SMP boot code. No functional change. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205255.981999763@linutronix.de --- arch/x86/include/asm/processor.h | 1 - arch/x86/kernel/cpu/common.c | 27 --------------------------- arch/x86/kernel/smpboot.c | 24 +++++++++++++++++++----- 3 files changed, 19 insertions(+), 33 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a1e4fa58b357..d46300e94f85 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -551,7 +551,6 @@ extern void switch_gdt_and_percpu_base(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void cpu_init(void); -extern void cpu_init_secondary(void); extern void cpu_init_exception_handling(void); extern void cr4_init(void); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 80710a68ef7d..e25fb13cd6ef 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2123,19 +2123,6 @@ static void dbg_restore_debug_regs(void) #define dbg_restore_debug_regs() #endif /* ! CONFIG_KGDB */ -static void wait_for_master_cpu(int cpu) -{ -#ifdef CONFIG_SMP - /* - * wait for ACK from master CPU before continuing - * with AP initialization - */ - WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)); - while (!cpumask_test_cpu(cpu, cpu_callout_mask)) - cpu_relax(); -#endif -} - static inline void setup_getcpu(int cpu) { unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); @@ -2239,8 +2226,6 @@ void cpu_init(void) struct task_struct *cur = current; int cpu = raw_smp_processor_id(); - wait_for_master_cpu(cpu); - ucode_cpu_init(cpu); #ifdef CONFIG_NUMA @@ -2293,18 +2278,6 @@ void cpu_init(void) load_fixmap_gdt(cpu); } -#ifdef CONFIG_SMP -void cpu_init_secondary(void) -{ - /* - * Relies on the BP having set-up the IDT tables, which are loaded - * on this CPU in cpu_init_exception_handling(). - */ - cpu_init_exception_handling(); - cpu_init(); -} -#endif - #ifdef CONFIG_MICROCODE_LATE_LOADING /** * store_cpu_caps() - Store a snapshot of CPU capabilities diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0bd9c9f7861f..50eff9b7fe7f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -220,6 +220,17 @@ static void ap_calibrate_delay(void) cpu_data(smp_processor_id()).loops_per_jiffy = loops_per_jiffy; } +static void wait_for_master_cpu(int cpu) +{ + /* + * Wait for release by control CPU before continuing with AP + * initialization. + */ + WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)); + while (!cpumask_test_cpu(cpu, cpu_callout_mask)) + cpu_relax(); +} + /* * Activate a secondary processor. */ @@ -237,13 +248,16 @@ static void notrace start_secondary(void *unused) load_cr3(swapper_pg_dir); __flush_tlb_all(); #endif + cpu_init_exception_handling(); + /* - * Sync point with wait_cpu_initialized(). Before proceeding through - * cpu_init(), the AP will call wait_for_master_cpu() which sets its - * own bit in cpu_initialized_mask and then waits for the BSP to set - * its bit in cpu_callout_mask to release it. + * Sync point with wait_cpu_initialized(). Sets AP in + * cpu_initialized_mask and then waits for the control CPU + * to release it. */ - cpu_init_secondary(); + wait_for_master_cpu(raw_smp_processor_id()); + + cpu_init(); rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); -- cgit v1.2.3 From a32226fa3b7d33d380494cf94cf1d4f8ebb70004 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:14 +0200 Subject: x86/cpu/cacheinfo: Remove cpu_callout_mask dependency cpu_callout_mask is used for the stop machine based MTRR/PAT init. In preparation of moving the BP/AP synchronization to the core hotplug code, use a private CPU mask for cacheinfo and manage it in the starting/dying hotplug state. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205256.035041005@linutronix.de --- arch/x86/kernel/cpu/cacheinfo.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 4063e8991211..8f86eacf69f7 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -39,6 +39,8 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); /* Shared L2 cache maps */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); +static cpumask_var_t cpu_cacheinfo_mask; + /* Kernel controls MTRR and/or PAT MSRs. */ unsigned int memory_caching_control __ro_after_init; @@ -1172,8 +1174,10 @@ void cache_bp_restore(void) cache_cpu_init(); } -static int cache_ap_init(unsigned int cpu) +static int cache_ap_online(unsigned int cpu) { + cpumask_set_cpu(cpu, cpu_cacheinfo_mask); + if (!memory_caching_control || get_cache_aps_delayed_init()) return 0; @@ -1191,11 +1195,17 @@ static int cache_ap_init(unsigned int cpu) * lock to prevent MTRR entry changes */ stop_machine_from_inactive_cpu(cache_rendezvous_handler, NULL, - cpu_callout_mask); + cpu_cacheinfo_mask); return 0; } +static int cache_ap_offline(unsigned int cpu) +{ + cpumask_clear_cpu(cpu, cpu_cacheinfo_mask); + return 0; +} + /* * Delayed cache initialization for all AP's */ @@ -1210,9 +1220,12 @@ void cache_aps_init(void) static int __init cache_ap_register(void) { + zalloc_cpumask_var(&cpu_cacheinfo_mask, GFP_KERNEL); + cpumask_set_cpu(smp_processor_id(), cpu_cacheinfo_mask); + cpuhp_setup_state_nocalls(CPUHP_AP_CACHECTRL_STARTING, "x86/cachectrl:starting", - cache_ap_init, NULL); + cache_ap_online, cache_ap_offline); return 0; } -core_initcall(cache_ap_register); +early_initcall(cache_ap_register); -- cgit v1.2.3 From d4f28f07c2fe736bce8ca415a86fb74c629200f3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:16 +0200 Subject: x86/smpboot: Move synchronization masks to SMP boot code The usage is in smpboot.c and not in the CPU initialization code. The XEN_PV usage of cpu_callout_mask is obsolete as cpu_init() not longer waits and cacheinfo has its own CPU mask now, so cpu_callout_mask can be made static too. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205256.091511483@linutronix.de --- arch/x86/include/asm/cpumask.h | 5 ----- arch/x86/kernel/cpu/common.c | 17 ----------------- arch/x86/kernel/smpboot.c | 16 ++++++++++++++++ arch/x86/xen/smp_pv.c | 3 --- 4 files changed, 16 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index c5aed9e9226c..4acfd57de8f1 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -4,11 +4,6 @@ #ifndef __ASSEMBLY__ #include -extern cpumask_var_t cpu_callin_mask; -extern cpumask_var_t cpu_callout_mask; -extern cpumask_var_t cpu_initialized_mask; -extern cpumask_var_t cpu_sibling_setup_mask; - extern void setup_cpu_local_masks(void); /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e25fb13cd6ef..640fd1802c72 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -67,14 +67,6 @@ u32 elf_hwcap2 __read_mostly; -/* all of these masks are initialized in setup_cpu_local_masks() */ -cpumask_var_t cpu_initialized_mask; -cpumask_var_t cpu_callout_mask; -cpumask_var_t cpu_callin_mask; - -/* representing cpus for which sibling maps can be computed */ -cpumask_var_t cpu_sibling_setup_mask; - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); @@ -169,15 +161,6 @@ clear_ppin: clear_cpu_cap(c, info->feature); } -/* correctly size the local cpu masks */ -void __init setup_cpu_local_masks(void) -{ - alloc_bootmem_cpumask_var(&cpu_initialized_mask); - alloc_bootmem_cpumask_var(&cpu_callin_mask); - alloc_bootmem_cpumask_var(&cpu_callout_mask); - alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); -} - static void default_init(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 50eff9b7fe7f..8b07c6e6d620 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,6 +101,13 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +/* All of these masks are initialized in setup_cpu_local_masks() */ +static cpumask_var_t cpu_initialized_mask; +static cpumask_var_t cpu_callout_mask; +static cpumask_var_t cpu_callin_mask; +/* Representing CPUs for which sibling maps can be computed */ +static cpumask_var_t cpu_sibling_setup_mask; + /* Logical package management. We might want to allocate that dynamically */ unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); @@ -1545,6 +1552,15 @@ __init void prefill_possible_map(void) set_cpu_possible(i, true); } +/* correctly size the local cpu masks */ +void __init setup_cpu_local_masks(void) +{ + alloc_bootmem_cpumask_var(&cpu_initialized_mask); + alloc_bootmem_cpumask_var(&cpu_callin_mask); + alloc_bootmem_cpumask_var(&cpu_callout_mask); + alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); +} + #ifdef CONFIG_HOTPLUG_CPU /* Recompute SMT state for all CPUs on offline */ diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index a9cf8c8fa074..a6f9128a4091 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -254,15 +254,12 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) struct desc_struct *gdt; unsigned long gdt_mfn; - /* used to tell cpu_init() that it can proceed with initialization */ - cpumask_set_cpu(cpu, cpu_callout_mask); if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map)) return 0; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (ctxt == NULL) { cpumask_clear_cpu(cpu, xen_cpu_initialized_map); - cpumask_clear_cpu(cpu, cpu_callout_mask); return -ENOMEM; } -- cgit v1.2.3 From 0c7ffa32dbd6b09a87fea4ad1de8b27145dfd9a6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:56 +0200 Subject: x86/smpboot/64: Implement arch_cpuhp_init_parallel_bringup() and enable it Implement the validation function which tells the core code whether parallel bringup is possible. The only condition for now is that the kernel does not run in an encrypted guest as these will trap the RDMSR via #VC, which cannot be handled at that point in early startup. There was an earlier variant for AMD-SEV which used the GHBC protocol for retrieving the APIC ID via CPUID, but there is no guarantee that the initial APIC ID in CPUID is the same as the real APIC ID. There is no enforcement from the secure firmware and the hypervisor can assign APIC IDs as it sees fit as long as the ACPI/MADT table is consistent with that assignment. Unfortunately there is no RDMSR GHCB protocol at the moment, so enabling AMD-SEV guests for parallel startup needs some more thought. Intel-TDX provides a secure RDMSR hypercall, but supporting that is outside the scope of this change. Fixup announce_cpu() as e.g. on Hyper-V CPU1 is the secondary sibling of CPU0, which makes the @cpu == 1 logic in announce_cpu() fall apart. [ mikelley: Reported the announce_cpu() fallout Originally-by: David Woodhouse Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205257.467571745@linutronix.de --- arch/x86/Kconfig | 3 +- arch/x86/kernel/cpu/common.c | 6 +-- arch/x86/kernel/smpboot.c | 87 ++++++++++++++++++++++++++++++++++++-------- 3 files changed, 75 insertions(+), 21 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c140a73b4295..953823fdf57b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -274,8 +274,9 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select HAVE_GENERIC_VDSO + select HOTPLUG_PARALLEL if SMP && X86_64 select HOTPLUG_SMT if SMP - select HOTPLUG_SPLIT_STARTUP if SMP + select HOTPLUG_SPLIT_STARTUP if SMP && X86_32 select IRQ_FORCED_THREADING select NEED_PER_CPU_EMBED_FIRST_CHUNK select NEED_PER_CPU_PAGE_FIRST_CHUNK diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 640fd1802c72..7cc44ebead5a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2128,11 +2128,7 @@ static inline void setup_getcpu(int cpu) } #ifdef CONFIG_X86_64 -static inline void ucode_cpu_init(int cpu) -{ - if (cpu) - load_ucode_ap(); -} +static inline void ucode_cpu_init(int cpu) { } static inline void tss_setup_ist(struct tss_struct *tss) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 4b97373d82c8..660709e94823 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include @@ -75,7 +76,7 @@ #include #include #include -#include +#include #include #include #include @@ -128,7 +129,6 @@ int arch_update_cpu_topology(void) return retval; } - static unsigned int smpboot_warm_reset_vector_count; static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) @@ -226,16 +226,43 @@ static void notrace start_secondary(void *unused) */ cr4_init(); -#ifdef CONFIG_X86_32 - /* switch away from the initial page table */ - load_cr3(swapper_pg_dir); - __flush_tlb_all(); -#endif + /* + * 32-bit specific. 64-bit reaches this code with the correct page + * table established. Yet another historical divergence. + */ + if (IS_ENABLED(CONFIG_X86_32)) { + /* switch away from the initial page table */ + load_cr3(swapper_pg_dir); + __flush_tlb_all(); + } + cpu_init_exception_handling(); /* - * Synchronization point with the hotplug core. Sets the - * synchronization state to ALIVE and waits for the control CPU to + * 32-bit systems load the microcode from the ASM startup code for + * historical reasons. + * + * On 64-bit systems load it before reaching the AP alive + * synchronization point below so it is not part of the full per + * CPU serialized bringup part when "parallel" bringup is enabled. + * + * That's even safe when hyperthreading is enabled in the CPU as + * the core code starts the primary threads first and leaves the + * secondary threads waiting for SIPI. Loading microcode on + * physical cores concurrently is a safe operation. + * + * This covers both the Intel specific issue that concurrent + * microcode loading on SMT siblings must be prohibited and the + * vendor independent issue`that microcode loading which changes + * CPUID, MSRs etc. must be strictly serialized to maintain + * software state correctness. + */ + if (IS_ENABLED(CONFIG_X86_64)) + load_ucode_ap(); + + /* + * Synchronization point with the hotplug core. Sets this CPUs + * synchronization state to ALIVE and spin-waits for the control CPU to * release this CPU for further bringup. */ cpuhp_ap_sync_alive(); @@ -918,9 +945,9 @@ static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_ei /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { + static int width, node_width, first = 1; static int current_node = NUMA_NO_NODE; int node = early_cpu_to_node(cpu); - static int width, node_width; if (!width) width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */ @@ -928,10 +955,10 @@ static void announce_cpu(int cpu, int apicid) if (!node_width) node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */ - if (cpu == 1) - printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state < SYSTEM_RUNNING) { + if (first) + pr_info("x86: Booting SMP configuration:\n"); + if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); @@ -942,11 +969,11 @@ static void announce_cpu(int cpu, int apicid) } /* Add padding for the BSP */ - if (cpu == 1) + if (first) pr_cont("%*s", width + 1, " "); + first = 0; pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu); - } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", node, cpu, apicid); @@ -1236,6 +1263,36 @@ void __init smp_prepare_cpus_common(void) set_cpu_sibling_map(0); } +#ifdef CONFIG_X86_64 +/* Establish whether parallel bringup can be supported. */ +bool __init arch_cpuhp_init_parallel_bringup(void) +{ + /* + * Encrypted guests require special handling. They enforce X2APIC + * mode but the RDMSR to read the APIC ID is intercepted and raises + * #VC or #VE which cannot be handled in the early startup code. + * + * AMD-SEV does not provide a RDMSR GHCB protocol so the early + * startup code cannot directly communicate with the secure + * firmware. The alternative solution to retrieve the APIC ID via + * CPUID(0xb), which is covered by the GHCB protocol, is not viable + * either because there is no enforcement of the CPUID(0xb) + * provided "initial" APIC ID to be the same as the real APIC ID. + * + * Intel-TDX has a secure RDMSR hypercall, but that needs to be + * implemented seperately in the low level startup ASM code. + */ + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) { + pr_info("Parallel CPU startup disabled due to guest state encryption\n"); + return false; + } + + smpboot_control = STARTUP_READ_APICID; + pr_debug("Parallel CPU startup enabled: 0x%08x\n", smpboot_control); + return true; +} +#endif + /* * Prepare for SMP bootup. * @max_cpus: configured maximum number of CPUs, It is a legacy parameter -- cgit v1.2.3 From 7583e8fbdc49a4dbd916d14863cf1deeddb982f9 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 10 May 2023 08:57:13 +0200 Subject: x86/cpu: Remove X86_FEATURE_NAMES While discussing to change the visibility of X86_FEATURE_NAMES (see Link) in order to remove CONFIG_EMBEDDED, Boris suggested to simply make the X86_FEATURE_NAMES functionality unconditional. As the need for really tiny kernel images has gone away and kernel images with !X86_FEATURE_NAMES are hardly tested, remove this config and the whole ifdeffery in the source code. Suggested-by: Borislav Petkov Signed-off-by: Lukas Bulwahn Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/all/20230509084007.24373-1-lukas.bulwahn@gmail.com/ Link: https://lore.kernel.org/r/20230510065713.10996-3-lukas.bulwahn@gmail.com --- arch/x86/Kconfig | 12 ------------ arch/x86/Kconfig.cpu | 2 +- arch/x86/boot/Makefile | 2 -- arch/x86/boot/cpu.c | 13 ------------- arch/x86/include/asm/cpufeature.h | 5 ----- arch/x86/kernel/cpu/Makefile | 4 +--- arch/x86/kernel/cpu/common.c | 4 ---- 7 files changed, 2 insertions(+), 40 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a7db116e429a..f6aa7e0ca47d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -291,7 +291,6 @@ config X86 select TRACE_IRQFLAGS_NMI_SUPPORT select USER_STACKTRACE_SUPPORT select HAVE_ARCH_KCSAN if X86_64 - select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS select HAVE_ARCH_NODE_DEV_GROUP if X86_SGX select FUNCTION_ALIGNMENT_16B if X86_64 || X86_ALIGNMENT_16 @@ -441,17 +440,6 @@ config SMP If you don't know what to do here, say N. -config X86_FEATURE_NAMES - bool - default y - help - This option compiles in a table of x86 feature bits and corresponding - names. This is required to support /proc/cpuinfo and a few kernel - messages. You can disable this to save space, at the expense of - making those few kernel messages show numeric feature bits instead. - - If in doubt, say Y. - config X86_X2APIC bool "Support x2apic" depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 542377cd419d..00468adf180f 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -389,7 +389,7 @@ config IA32_FEAT_CTL config X86_VMX_FEATURE_NAMES def_bool y - depends on IA32_FEAT_CTL && X86_FEATURE_NAMES + depends on IA32_FEAT_CTL menuconfig PROCESSOR_SELECT bool "Supported processor vendors" if EXPERT diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 9e38ffaadb5d..f33e45ed1437 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -55,14 +55,12 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include \ -include include/generated/autoconf.h \ -D__EXPORTED_HEADERS__ -ifdef CONFIG_X86_FEATURE_NAMES $(obj)/cpu.o: $(obj)/cpustr.h quiet_cmd_cpustr = CPUSTR $@ cmd_cpustr = $(obj)/mkcpustr > $@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE $(call if_changed,cpustr) -endif targets += cpustr.h # --------------------------------------------------------------------------- diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c index 0bbf4f3707d2..feb6dbd7ca86 100644 --- a/arch/x86/boot/cpu.c +++ b/arch/x86/boot/cpu.c @@ -14,9 +14,7 @@ */ #include "boot.h" -#ifdef CONFIG_X86_FEATURE_NAMES #include "cpustr.h" -#endif static char *cpu_name(int level) { @@ -35,7 +33,6 @@ static char *cpu_name(int level) static void show_cap_strs(u32 *err_flags) { int i, j; -#ifdef CONFIG_X86_FEATURE_NAMES const unsigned char *msg_strs = (const unsigned char *)x86_cap_strs; for (i = 0; i < NCAPINTS; i++) { u32 e = err_flags[i]; @@ -58,16 +55,6 @@ static void show_cap_strs(u32 *err_flags) e >>= 1; } } -#else - for (i = 0; i < NCAPINTS; i++) { - u32 e = err_flags[i]; - for (j = 0; j < 32; j++) { - if (e & 1) - printf("%d:%d ", i, j); - e >>= 1; - } - } -#endif } int validate_cpu(void) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ce0c8f7d3218..a26bebbdff87 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -38,15 +38,10 @@ enum cpuid_leafs #define X86_CAP_FMT_NUM "%d:%d" #define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31) -#ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] -#else -#define X86_CAP_FMT X86_CAP_FMT_NUM -#define x86_cap_flag x86_cap_flag_num -#endif /* * In order to save room, we index into this array by doing diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d7e3ceaf75c1..4350f6bfc064 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -27,7 +27,7 @@ obj-y += cpuid-deps.o obj-y += umwait.o obj-$(CONFIG_PROC_FS) += proc.o -obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o +obj-y += capflags.o powerflags.o obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL @@ -54,7 +54,6 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o obj-$(CONFIG_ACRN_GUEST) += acrn.o -ifdef CONFIG_X86_FEATURE_NAMES quiet_cmd_mkcapflags = MKCAP $@ cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ @@ -63,5 +62,4 @@ vmxfeature = $(src)/../../include/asm/vmxfeatures.h $(obj)/capflags.c: $(cpufeature) $(vmxfeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) -endif targets += capflags.c diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 80710a68ef7d..849ed7e2a726 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1502,12 +1502,10 @@ static void __init cpu_parse_early_param(void) if (!kstrtouint(opt, 10, &bit)) { if (bit < NCAPINTS * 32) { -#ifdef CONFIG_X86_FEATURE_NAMES /* empty-string, i.e., ""-defined feature flags */ if (!x86_cap_flags[bit]) pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit)); else -#endif pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); setup_clear_cpu_cap(bit); @@ -1520,7 +1518,6 @@ static void __init cpu_parse_early_param(void) continue; } -#ifdef CONFIG_X86_FEATURE_NAMES for (bit = 0; bit < 32 * NCAPINTS; bit++) { if (!x86_cap_flag(bit)) continue; @@ -1537,7 +1534,6 @@ static void __init cpu_parse_early_param(void) if (!found) pr_cont(" (unknown: %s)", opt); -#endif } pr_cont("\n"); -- cgit v1.2.3 From e40879b6d7d858b03813cd53c17dfef9c297f525 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Fri, 8 Jan 2021 04:00:35 +0000 Subject: x86/MCE: Check a hw error's address to determine proper recovery action Make sure that machine check errors with a usable address are properly marked as poison. This is needed for errors that occur on memory which have MCG_STATUS[RIPV] clear - i.e., the interrupted process cannot be restarted reliably. One example is data poison consumption through the instruction fetch units on AMD Zen-based systems. The MF_MUST_KILL flag is passed to memory_failure() when MCG_STATUS[RIPV] is not set. So the associated process will still be killed. What this does, practically, is get rid of one more check to kill_current_task with the eventual goal to remove it completely. Also, make the handling identical to what is done on the notifier path (uc_decode_notifier() does that address usability check too). The scenario described above occurs when hardware can precisely identify the address of poisoned memory, but execution cannot reliably continue for the interrupted hardware thread. [ bp: Massage commit message. ] Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Tony Luck Link: https://lore.kernel.org/r/20230322005131.174499-1-tony.luck@intel.com --- arch/x86/kernel/cpu/mce/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2eec60f50057..22dfcb2adcd7 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1533,7 +1533,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - if (kill_current_task) + if (!mce_usable_address(&m)) queue_task_work(&m, msg, kill_me_now); else queue_task_work(&m, msg, kill_me_maybe); -- cgit v1.2.3 From edc0a2b5957652f4685ef3516f519f84807087db Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Thu, 23 Mar 2023 09:56:40 +0800 Subject: x86/topology: Fix erroneous smp_num_siblings on Intel Hybrid platforms Traditionally, all CPUs in a system have identical numbers of SMT siblings. That changes with hybrid processors where some logical CPUs have a sibling and others have none. Today, the CPU boot code sets the global variable smp_num_siblings when every CPU thread is brought up. The last thread to boot will overwrite it with the number of siblings of *that* thread. That last thread to boot will "win". If the thread is a Pcore, smp_num_siblings == 2. If it is an Ecore, smp_num_siblings == 1. smp_num_siblings describes if the *system* supports SMT. It should specify the maximum number of SMT threads among all cores. Ensure that smp_num_siblings represents the system-wide maximum number of siblings by always increasing its value. Never allow it to decrease. On MeteorLake-P platform, this fixes a problem that the Ecore CPUs are not updated in any cpu sibling map because the system is treated as an UP system when probing Ecore CPUs. Below shows part of the CPU topology information before and after the fix, for both Pcore and Ecore CPU (cpu0 is Pcore, cpu 12 is Ecore). ... -/sys/devices/system/cpu/cpu0/topology/package_cpus:000fff -/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-11 +/sys/devices/system/cpu/cpu0/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-21 ... -/sys/devices/system/cpu/cpu12/topology/package_cpus:001000 -/sys/devices/system/cpu/cpu12/topology/package_cpus_list:12 +/sys/devices/system/cpu/cpu12/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu12/topology/package_cpus_list:0-21 Notice that the "before" 'package_cpus_list' has only one CPU. This means that userspace tools like lscpu will see a little laptop like an 11-socket system: -Core(s) per socket: 1 -Socket(s): 11 +Core(s) per socket: 16 +Socket(s): 1 This is also expected to make the scheduler do rather wonky things too. [ dhansen: remove CPUID detail from changelog, add end user effects ] CC: stable@kernel.org Fixes: bbb65d2d365e ("x86: use cpuid vector 0xb when available for detecting cpu topology") Fixes: 95f3d39ccf7a ("x86/cpu/topology: Provide detect_extended_topology_early()") Suggested-by: Len Brown Signed-off-by: Zhang Rui Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230323015640.27906-1-rui.zhang%40intel.com --- arch/x86/kernel/cpu/topology.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 5e868b62a7c4..0270925fe013 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -79,7 +79,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; - smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; } @@ -109,7 +109,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); c->initial_apicid = edx; - core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); -- cgit v1.2.3 From 2997d94b5dd0e8b10076f5e0b6f18410c73e28bd Mon Sep 17 00:00:00 2001 From: Shawn Wang Date: Mon, 15 May 2023 14:04:48 +0800 Subject: x86/resctrl: Only show tasks' pid in current pid namespace When writing a task id to the "tasks" file in an rdtgroup, rdtgroup_tasks_write() treats the pid as a number in the current pid namespace. But when reading the "tasks" file, rdtgroup_tasks_show() shows the list of global pids from the init namespace, which is confusing and incorrect. To be more robust, let the "tasks" file only show pids in the current pid namespace. Fixes: e02737d5b826 ("x86/intel_rdt: Add tasks files") Signed-off-by: Shawn Wang Signed-off-by: Borislav Petkov (AMD) Acked-by: Reinette Chatre Acked-by: Fenghua Yu Tested-by: Reinette Chatre Link: https://lore.kernel.org/all/20230116071246.97717-1-shawnwang@linux.alibaba.com/ --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 6ad33f355861..61cdd9b1bb6d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -726,11 +726,15 @@ unlock: static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) { struct task_struct *p, *t; + pid_t pid; rcu_read_lock(); for_each_process_thread(p, t) { - if (is_closid_match(t, r) || is_rmid_match(t, r)) - seq_printf(s, "%d\n", t->pid); + if (is_closid_match(t, r) || is_rmid_match(t, r)) { + pid = task_pid_vnr(t); + if (pid) + seq_printf(s, "%d\n", pid); + } } rcu_read_unlock(); } -- cgit v1.2.3 From d053b481a5f16dbd4f020c6b3ebdf9173fdef0e2 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:17 +0200 Subject: x86/mtrr: Replace size_or_mask and size_and_mask with a much easier concept MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace size_or_mask and size_and_mask with the much easier concept of high reserved bits. While at it, instead of using constants in the MTRR code, use some new [ bp: - Drop mtrr_set_mask() - Unbreak long lines - Move struct mtrr_state_type out of the uapi header as it doesn't belong there. It also fixes a HDRTEST breakage "unknown type name ‘bool’" as Reported-by: kernel test robot - Massage. ] Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230502120931.20719-3-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/mtrr.h | 32 +++++++++++++++-- arch/x86/include/uapi/asm/mtrr.h | 8 ----- arch/x86/kernel/cpu/mtrr/cleanup.c | 2 +- arch/x86/kernel/cpu/mtrr/generic.c | 70 +++++++++++++++++--------------------- arch/x86/kernel/cpu/mtrr/mtrr.c | 4 +-- arch/x86/kernel/cpu/mtrr/mtrr.h | 2 +- 6 files changed, 65 insertions(+), 53 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index f0eeaf6e5f5f..1421fe811401 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -23,8 +23,35 @@ #ifndef _ASM_X86_MTRR_H #define _ASM_X86_MTRR_H +#include #include +/* Defines for hardware MTRR registers. */ +#define MTRR_CAP_VCNT GENMASK(7, 0) +#define MTRR_CAP_FIX BIT_MASK(8) +#define MTRR_CAP_WC BIT_MASK(10) + +#define MTRR_DEF_TYPE_TYPE GENMASK(7, 0) +#define MTRR_DEF_TYPE_FE BIT_MASK(10) +#define MTRR_DEF_TYPE_E BIT_MASK(11) + +#define MTRR_DEF_TYPE_ENABLE (MTRR_DEF_TYPE_FE | MTRR_DEF_TYPE_E) +#define MTRR_DEF_TYPE_DISABLE ~(MTRR_DEF_TYPE_TYPE | MTRR_DEF_TYPE_ENABLE) + +#define MTRR_PHYSBASE_TYPE GENMASK(7, 0) +#define MTRR_PHYSBASE_RSVD GENMASK(11, 8) + +#define MTRR_PHYSMASK_RSVD GENMASK(10, 0) +#define MTRR_PHYSMASK_V BIT_MASK(11) + +struct mtrr_state_type { + struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES]; + mtrr_type fixed_ranges[MTRR_NUM_FIXED_RANGES]; + unsigned char enabled; + bool have_fixed; + mtrr_type def_type; +}; + /* * The following functions are for use by other drivers that cannot use * arch_phys_wc_add and arch_phys_wc_del. @@ -121,7 +148,8 @@ struct mtrr_gentry32 { #endif /* CONFIG_COMPAT */ /* Bit fields for enabled in struct mtrr_state_type */ -#define MTRR_STATE_MTRR_FIXED_ENABLED 0x01 -#define MTRR_STATE_MTRR_ENABLED 0x02 +#define MTRR_STATE_SHIFT 10 +#define MTRR_STATE_MTRR_FIXED_ENABLED (MTRR_DEF_TYPE_FE >> MTRR_STATE_SHIFT) +#define MTRR_STATE_MTRR_ENABLED (MTRR_DEF_TYPE_E >> MTRR_STATE_SHIFT) #endif /* _ASM_X86_MTRR_H */ diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h index 376563f2bac1..ab194c831625 100644 --- a/arch/x86/include/uapi/asm/mtrr.h +++ b/arch/x86/include/uapi/asm/mtrr.h @@ -81,14 +81,6 @@ typedef __u8 mtrr_type; #define MTRR_NUM_FIXED_RANGES 88 #define MTRR_MAX_VAR_RANGES 256 -struct mtrr_state_type { - struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES]; - mtrr_type fixed_ranges[MTRR_NUM_FIXED_RANGES]; - unsigned char enabled; - unsigned char have_fixed; - mtrr_type def_type; -}; - #define MTRRphysBase_MSR(reg) (0x200 + 2 * (reg)) #define MTRRphysMask_MSR(reg) (0x200 + 2 * (reg) + 1) diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 70314093bb9b..ca2d567e729e 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -890,7 +890,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) return 0; rdmsr(MSR_MTRRdefType, def, dummy); - def &= 0xff; + def &= MTRR_DEF_TYPE_TYPE; if (def != MTRR_TYPE_UNCACHABLE) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3922552340b1..08ba55832182 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -38,15 +38,8 @@ u64 mtrr_tom2; struct mtrr_state_type mtrr_state; EXPORT_SYMBOL_GPL(mtrr_state); -static u64 size_or_mask, size_and_mask; - -void __init mtrr_set_mask(void) -{ - unsigned int phys_addr = boot_cpu_data.x86_phys_bits; - - size_or_mask = ~GENMASK_ULL(phys_addr - PAGE_SHIFT - 1, 0); - size_and_mask = ~size_or_mask & GENMASK_ULL(39, 20); -} +/* Reserved bits in the high portion of the MTRRphysBaseN MSR. */ +u32 phys_hi_rsvd; /* * BIOS is expected to clear MtrrFixDramModEn bit, see for example @@ -79,10 +72,9 @@ static u64 get_mtrr_size(u64 mask) { u64 size; - mask >>= PAGE_SHIFT; - mask |= size_or_mask; + mask |= (u64)phys_hi_rsvd << 32; size = -mask; - size <<= PAGE_SHIFT; + return size; } @@ -181,7 +173,7 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state, inclusive; - if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11))) + if (!(mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V)) continue; base = (((u64)mtrr_state.var_ranges[i].base_hi) << 32) + @@ -233,7 +225,7 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, if ((start & mask) != (base & mask)) continue; - curr_match = mtrr_state.var_ranges[i].base_lo & 0xff; + curr_match = mtrr_state.var_ranges[i].base_lo & MTRR_PHYSBASE_TYPE; if (prev_match == MTRR_TYPE_INVALID) { prev_match = curr_match; continue; @@ -435,7 +427,7 @@ static void __init print_mtrr_state(void) high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { - if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) + if (mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V) pr_debug(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", i, high_width, @@ -444,7 +436,8 @@ static void __init print_mtrr_state(void) high_width, mtrr_state.var_ranges[i].mask_hi, mtrr_state.var_ranges[i].mask_lo >> 12, - mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & 0xff)); + mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & + MTRR_PHYSBASE_TYPE)); else pr_debug(" %u disabled\n", i); } @@ -462,7 +455,7 @@ bool __init get_mtrr_state(void) vrs = mtrr_state.var_ranges; rdmsr(MSR_MTRRcap, lo, dummy); - mtrr_state.have_fixed = (lo >> 8) & 1; + mtrr_state.have_fixed = lo & MTRR_CAP_FIX; for (i = 0; i < num_var_ranges; i++) get_mtrr_var_range(i, &vrs[i]); @@ -470,8 +463,8 @@ bool __init get_mtrr_state(void) get_fixed_ranges(mtrr_state.fixed_ranges); rdmsr(MSR_MTRRdefType, lo, dummy); - mtrr_state.def_type = (lo & 0xff); - mtrr_state.enabled = (lo & 0xc00) >> 10; + mtrr_state.def_type = lo & MTRR_DEF_TYPE_TYPE; + mtrr_state.enabled = (lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT; if (amd_special_default_mtrr()) { unsigned low, high; @@ -584,7 +577,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); - if ((mask_lo & 0x800) == 0) { + if (!(mask_lo & MTRR_PHYSMASK_V)) { /* Invalid (i.e. free) range */ *base = 0; *size = 0; @@ -595,8 +588,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ - tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; - mask = size_or_mask | tmp; + tmp = (u64)mask_hi << 32 | (mask_lo & PAGE_MASK); + mask = (u64)phys_hi_rsvd << 32 | tmp; /* Expand tmp with high bits to all 1s: */ hi = fls64(tmp); @@ -614,9 +607,9 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, * This works correctly if size is a power of two, i.e. a * contiguous range: */ - *size = -mask; + *size = -mask >> PAGE_SHIFT; *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; - *type = base_lo & 0xff; + *type = base_lo & MTRR_PHYSBASE_TYPE; out_put_cpu: put_cpu(); @@ -654,9 +647,8 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) bool changed = false; rdmsr(MTRRphysBase_MSR(index), lo, hi); - if ((vr->base_lo & 0xfffff0ffUL) != (lo & 0xfffff0ffUL) - || (vr->base_hi & (size_and_mask >> (32 - PAGE_SHIFT))) != - (hi & (size_and_mask >> (32 - PAGE_SHIFT)))) { + if ((vr->base_lo & ~MTRR_PHYSBASE_RSVD) != (lo & ~MTRR_PHYSBASE_RSVD) + || (vr->base_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi); changed = true; @@ -664,9 +656,8 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) rdmsr(MTRRphysMask_MSR(index), lo, hi); - if ((vr->mask_lo & 0xfffff800UL) != (lo & 0xfffff800UL) - || (vr->mask_hi & (size_and_mask >> (32 - PAGE_SHIFT))) != - (hi & (size_and_mask >> (32 - PAGE_SHIFT)))) { + if ((vr->mask_lo & ~MTRR_PHYSMASK_RSVD) != (lo & ~MTRR_PHYSMASK_RSVD) + || (vr->mask_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); changed = true; } @@ -701,11 +692,12 @@ static unsigned long set_mtrr_state(void) * Set_mtrr_restore restores the old value of MTRRdefType, * so to set it we fiddle with the saved value: */ - if ((deftype_lo & 0xff) != mtrr_state.def_type - || ((deftype_lo & 0xc00) >> 10) != mtrr_state.enabled) { + if ((deftype_lo & MTRR_DEF_TYPE_TYPE) != mtrr_state.def_type || + ((deftype_lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT) != mtrr_state.enabled) { - deftype_lo = (deftype_lo & ~0xcff) | mtrr_state.def_type | - (mtrr_state.enabled << 10); + deftype_lo = (deftype_lo & MTRR_DEF_TYPE_DISABLE) | + mtrr_state.def_type | + (mtrr_state.enabled << MTRR_STATE_SHIFT); change_mask |= MTRR_CHANGE_MASK_DEFTYPE; } @@ -718,7 +710,7 @@ void mtrr_disable(void) rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Disable MTRRs, and set the default type to uncached */ - mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi); + mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & MTRR_DEF_TYPE_DISABLE, deftype_hi); } void mtrr_enable(void) @@ -772,9 +764,9 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base, memset(vr, 0, sizeof(struct mtrr_var_range)); } else { vr->base_lo = base << PAGE_SHIFT | type; - vr->base_hi = (base & size_and_mask) >> (32 - PAGE_SHIFT); - vr->mask_lo = -size << PAGE_SHIFT | 0x800; - vr->mask_hi = (-size & size_and_mask) >> (32 - PAGE_SHIFT); + vr->base_hi = (base >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; + vr->mask_lo = -size << PAGE_SHIFT | MTRR_PHYSMASK_V; + vr->mask_hi = (-size >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; mtrr_wrmsr(MTRRphysBase_MSR(reg), vr->base_lo, vr->base_hi); mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi); @@ -827,7 +819,7 @@ static int generic_have_wrcomb(void) { unsigned long config, dummy; rdmsr(MSR_MTRRcap, config, dummy); - return config & (1 << 10); + return config & MTRR_CAP_WC; } int positive_have_wrcomb(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 1bdab16f16bd..1067f128bded 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -115,7 +115,7 @@ static void __init set_num_var_ranges(bool use_generic) else if (is_cpu(CYRIX) || is_cpu(CENTAUR)) config = 8; - num_var_ranges = config & 0xff; + num_var_ranges = config & MTRR_CAP_VCNT; } static void __init init_table(void) @@ -627,7 +627,7 @@ void __init mtrr_bp_init(void) { const char *why = "(not available)"; - mtrr_set_mask(); + phys_hi_rsvd = GENMASK(31, boot_cpu_data.x86_phys_bits - 32); if (cpu_feature_enabled(X86_FEATURE_MTRR)) { mtrr_if = &generic_mtrr_ops; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index a00987e6cc1c..59e8fb26bf9d 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -58,8 +58,8 @@ extern const struct mtrr_ops *mtrr_if; extern unsigned int num_var_ranges; extern u64 mtrr_tom2; extern struct mtrr_state_type mtrr_state; +extern u32 phys_hi_rsvd; -void mtrr_set_mask(void); void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); -- cgit v1.2.3 From 29055dc74287467bd7a053d60b4afe753832960d Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:18 +0200 Subject: x86/mtrr: Support setting MTRR state for software defined MTRRs When running virtualized, MTRR access can be reduced (e.g. in Xen PV guests or when running as a SEV-SNP guest under Hyper-V). Typically, the hypervisor will not advertize the MTRR feature in CPUID data, resulting in no MTRR memory type information being available for the kernel. This has turned out to result in problems (Link tags below): - Hyper-V SEV-SNP guests using uncached mappings where they shouldn't - Xen PV dom0 mapping memory as WB which should be UC- instead Solve those problems by allowing an MTRR static state override, overwriting the empty state used today. In case such a state has been set, don't call get_mtrr_state() in mtrr_bp_init(). The set state will only be used by mtrr_type_lookup(), as in all other cases mtrr_enabled() is being checked, which will return false. Accept the overwrite call only for selected cases when running as a guest. Disable X86_FEATURE_MTRR in order to avoid any MTRR modifications by just refusing them. [ bp: Massage. ] Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/all/4fe9541e-4d4c-2b2a-f8c8-2d34a7284930@nerdbynature.de/ Link: https://lore.kernel.org/lkml/BYAPR21MB16883ABC186566BD4D2A1451D7FE9@BYAPR21MB1688.namprd21.prod.outlook.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/mtrr.h | 8 +++++ arch/x86/kernel/cpu/mtrr/generic.c | 60 +++++++++++++++++++++++++++++++++++++- arch/x86/kernel/cpu/mtrr/mtrr.c | 14 ++++++++- arch/x86/kernel/setup.c | 2 ++ 4 files changed, 82 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 1421fe811401..1bae790a553a 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -58,6 +58,8 @@ struct mtrr_state_type { */ # ifdef CONFIG_MTRR void mtrr_bp_init(void); +void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type); extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); @@ -75,6 +77,12 @@ void mtrr_disable(void); void mtrr_enable(void); void mtrr_generic_set_state(void); # else +static inline void mtrr_overwrite_state(struct mtrr_var_range *var, + unsigned int num_var, + mtrr_type def_type) +{ +} + static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform) { /* diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 08ba55832182..e81d832475a1 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -8,10 +8,12 @@ #include #include #include - +#include #include #include #include +#include +#include #include #include #include @@ -242,6 +244,62 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, return mtrr_state.def_type; } +/** + * mtrr_overwrite_state - set static MTRR state + * + * Used to set MTRR state via different means (e.g. with data obtained from + * a hypervisor). + * Is allowed only for special cases when running virtualized. Must be called + * from the x86_init.hyper.init_platform() hook. It can be called only once. + * The MTRR state can't be changed afterwards. To ensure that, X86_FEATURE_MTRR + * is cleared. + */ +void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type) +{ + unsigned int i; + + /* Only allowed to be called once before mtrr_bp_init(). */ + if (WARN_ON_ONCE(mtrr_state_set)) + return; + + /* Only allowed when running virtualized. */ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return; + + /* + * Only allowed for special virtualization cases: + * - when running as Hyper-V, SEV-SNP guest using vTOM + * - when running as Xen PV guest + * - when running as SEV-SNP or TDX guest to avoid unnecessary + * VMM communication/Virtualization exceptions (#VC, #VE) + */ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && + !hv_is_isolation_supported() && + !cpu_feature_enabled(X86_FEATURE_XENPV) && + !cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return; + + /* Disable MTRR in order to disable MTRR modifications. */ + setup_clear_cpu_cap(X86_FEATURE_MTRR); + + if (var) { + if (num_var > MTRR_MAX_VAR_RANGES) { + pr_warn("Trying to overwrite MTRR state with %u variable entries\n", + num_var); + num_var = MTRR_MAX_VAR_RANGES; + } + for (i = 0; i < num_var; i++) + mtrr_state.var_ranges[i] = var[i]; + num_var_ranges = num_var; + } + + mtrr_state.def_type = def_type; + mtrr_state.enabled |= MTRR_STATE_MTRR_ENABLED; + + mtrr_state_set = 1; +} + /** * mtrr_type_lookup - look up memory type in MTRR * diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 1067f128bded..be35a0b09604 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -625,11 +625,23 @@ int __initdata changed_by_mtrr_cleanup; */ void __init mtrr_bp_init(void) { + bool generic_mtrrs = cpu_feature_enabled(X86_FEATURE_MTRR); const char *why = "(not available)"; phys_hi_rsvd = GENMASK(31, boot_cpu_data.x86_phys_bits - 32); - if (cpu_feature_enabled(X86_FEATURE_MTRR)) { + if (!generic_mtrrs && mtrr_state.enabled) { + /* + * Software overwrite of MTRR state, only for generic case. + * Note that X86_FEATURE_MTRR has been reset in this case. + */ + init_table(); + pr_info("MTRRs set to read-only\n"); + + return; + } + + if (generic_mtrrs) { mtrr_if = &generic_mtrr_ops; } else { switch (boot_cpu_data.x86_vendor) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 16babff771bd..0cccfeb67c3a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1037,6 +1037,8 @@ void __init setup_arch(char **cmdline_p) /* * VMware detection requires dmi to be available, so this * needs to be done after dmi_setup(), for the boot CPU. + * For some guest types (Xen PV, SEV-SNP, TDX) it is required to be + * called before cache_bp_init() for setting up MTRR state. */ init_hypervisor_platform(); -- cgit v1.2.3 From 03409069520974361ffb510c725305239b78b39f Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:21 +0200 Subject: x86/mtrr: Replace vendor tests in MTRR code Modern CPUs all share the same MTRR interface implemented via generic_mtrr_ops. At several places in MTRR code this generic interface is deduced via is_cpu(INTEL) tests, which is only working due to X86_VENDOR_INTEL being 0 (the is_cpu() macro is testing mtrr_if->vendor, which isn't explicitly set in generic_mtrr_ops). Test the generic CPU feature X86_FEATURE_MTRR instead. The only other place where the .vendor member of struct mtrr_ops is being used is in set_num_var_ranges(), where depending on the vendor the number of MTRR registers is determined. This can easily be changed by replacing .vendor with the static number of MTRR registers. It should be noted that the test "is_cpu(HYGON)" wasn't ever returning true, as there is no struct mtrr_ops with that vendor information. [ bp: Use mtrr_enabled() before doing mtrr_if-> accesses, esp. in mtrr_trim_uncached_memory() which gets called independently from whether mtrr_if is set or not. ] Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230502120931.20719-7-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/amd.c | 2 +- arch/x86/kernel/cpu/mtrr/centaur.c | 2 +- arch/x86/kernel/cpu/mtrr/cleanup.c | 10 ++++++++-- arch/x86/kernel/cpu/mtrr/cyrix.c | 2 +- arch/x86/kernel/cpu/mtrr/generic.c | 2 +- arch/x86/kernel/cpu/mtrr/mtrr.c | 28 ++++++++-------------------- arch/x86/kernel/cpu/mtrr/mtrr.h | 14 +++++++++++--- 7 files changed, 31 insertions(+), 29 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c index eff6ac62c0ff..ef3e8e42b782 100644 --- a/arch/x86/kernel/cpu/mtrr/amd.c +++ b/arch/x86/kernel/cpu/mtrr/amd.c @@ -110,7 +110,7 @@ amd_validate_add_page(unsigned long base, unsigned long size, unsigned int type) } const struct mtrr_ops amd_mtrr_ops = { - .vendor = X86_VENDOR_AMD, + .var_regs = 2, .set = amd_set_mtrr, .get = amd_get_mtrr, .get_free_region = generic_get_free_region, diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index b8a74eddde83..4466ddeb0125 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -112,7 +112,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t } const struct mtrr_ops centaur_mtrr_ops = { - .vendor = X86_VENDOR_CENTAUR, + .var_regs = 8, .set = centaur_set_mcr, .get = centaur_get_mcr, .get_free_region = centaur_get_free_region, diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index ca2d567e729e..ed5f84c20ac2 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -689,7 +689,10 @@ int __init mtrr_cleanup(void) int index_good; int i; - if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1) + if (!mtrr_enabled()) + return 0; + + if (!cpu_feature_enabled(X86_FEATURE_MTRR) || enable_mtrr_cleanup < 1) return 0; rdmsr(MSR_MTRRdefType, def, dummy); @@ -882,11 +885,14 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* extra one for all 0 */ int num[MTRR_NUM_TYPES + 1]; + if (!mtrr_enabled()) + return 0; + /* * Make sure we only trim uncachable memory on machines that * support the Intel MTRR architecture: */ - if (!is_cpu(INTEL) || disable_mtrr_trim) + if (!cpu_feature_enabled(X86_FEATURE_MTRR) || disable_mtrr_trim) return 0; rdmsr(MSR_MTRRdefType, def, dummy); diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 173b9e01e623..238dad57d4d6 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -235,7 +235,7 @@ static void cyrix_set_arr(unsigned int reg, unsigned long base, } const struct mtrr_ops cyrix_mtrr_ops = { - .vendor = X86_VENDOR_CYRIX, + .var_regs = 8, .set = cyrix_set_arr, .get = cyrix_get_arr, .get_free_region = cyrix_get_free_region, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index e81d832475a1..4d8ca6234bbf 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -843,7 +843,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, * For Intel PPro stepping <= 7 * must be 4 MiB aligned and not touch 0x70000000 -> 0x7003FFFF */ - if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && + if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index be35a0b09604..85113af35393 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -59,10 +59,6 @@ #define MTRR_TO_PHYS_WC_OFFSET 1000 u32 num_var_ranges; -static bool mtrr_enabled(void) -{ - return !!mtrr_if; -} unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; static DEFINE_MUTEX(mtrr_mutex); @@ -103,21 +99,6 @@ static int have_wrcomb(void) return mtrr_if->have_wrcomb ? mtrr_if->have_wrcomb() : 0; } -/* This function returns the number of variable MTRRs */ -static void __init set_num_var_ranges(bool use_generic) -{ - unsigned long config = 0, dummy; - - if (use_generic) - rdmsr(MSR_MTRRcap, config, dummy); - else if (is_cpu(AMD) || is_cpu(HYGON)) - config = 2; - else if (is_cpu(CYRIX) || is_cpu(CENTAUR)) - config = 8; - - num_var_ranges = config & MTRR_CAP_VCNT; -} - static void __init init_table(void) { int i, max; @@ -627,6 +608,7 @@ void __init mtrr_bp_init(void) { bool generic_mtrrs = cpu_feature_enabled(X86_FEATURE_MTRR); const char *why = "(not available)"; + unsigned long config, dummy; phys_hi_rsvd = GENMASK(31, boot_cpu_data.x86_phys_bits - 32); @@ -664,7 +646,13 @@ void __init mtrr_bp_init(void) } if (mtrr_enabled()) { - set_num_var_ranges(mtrr_if == &generic_mtrr_ops); + /* Get the number of variable MTRR ranges. */ + if (mtrr_if == &generic_mtrr_ops) + rdmsr(MSR_MTRRcap, config, dummy); + else + config = mtrr_if->var_regs; + num_var_ranges = config & MTRR_CAP_VCNT; + init_table(); if (mtrr_if == &generic_mtrr_ops) { /* BIOS may override */ diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 59e8fb26bf9d..6f3312be4b27 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -13,7 +13,7 @@ extern unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; struct mtrr_ops { - u32 vendor; + u32 var_regs; void (*set)(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); void (*get)(unsigned int reg, unsigned long *base, @@ -53,8 +53,6 @@ bool get_mtrr_state(void); extern const struct mtrr_ops *mtrr_if; -#define is_cpu(vnd) (mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd) - extern unsigned int num_var_ranges; extern u64 mtrr_tom2; extern struct mtrr_state_type mtrr_state; @@ -71,3 +69,13 @@ extern const struct mtrr_ops centaur_mtrr_ops; extern int changed_by_mtrr_cleanup; extern int mtrr_cleanup(void); +void generic_rebuild_map(void); + +/* + * Must be used by code which uses mtrr_if to call platform-specific + * MTRR manipulation functions. + */ +static inline bool mtrr_enabled(void) +{ + return !!mtrr_if; +} -- cgit v1.2.3 From 34cf2d19552bbe3b72b34fc859a19cd5070c466a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:22 +0200 Subject: x86/mtrr: Have only one set_mtrr() variant Today there are two variants of set_mtrr(): one calling stop_machine() and one calling stop_machine_cpuslocked(). The first one (set_mtrr()) has only one caller, and this caller is running only when resuming from suspend when the interrupts are still off and only one CPU is active. Additionally this code is used only on rather old 32-bit CPUs not supporting SMP. For these reasons the first variant can be replaced by a simple call of mtrr_if->set(). Rename the second variant set_mtrr_cpuslocked() to set_mtrr() now that there is only one variant left, in order to have a shorter function name. Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-8-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/mtrr.c | 28 ++++++++-------------------- 1 file changed, 8 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 85113af35393..007ecca62676 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -173,20 +173,8 @@ static inline int types_compatible(mtrr_type type1, mtrr_type type2) * Note that the mechanism is the same for UP systems, too; all the SMP stuff * becomes nops. */ -static void -set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) -{ - struct set_mtrr_data data = { .smp_reg = reg, - .smp_base = base, - .smp_size = size, - .smp_type = type - }; - - stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); -} - -static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, - unsigned long size, mtrr_type type) +static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, + mtrr_type type) { struct set_mtrr_data data = { .smp_reg = reg, .smp_base = base, @@ -316,7 +304,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* Search for an empty MTRR */ i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { - set_mtrr_cpuslocked(i, base, size, type); + set_mtrr(i, base, size, type); if (likely(replace < 0)) { mtrr_usage_table[i] = 1; } else { @@ -324,7 +312,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (increment) mtrr_usage_table[i]++; if (unlikely(replace != i)) { - set_mtrr_cpuslocked(replace, 0, 0, 0); + set_mtrr(replace, 0, 0, 0); mtrr_usage_table[replace] = 0; } } @@ -452,7 +440,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) goto out; } if (--mtrr_usage_table[reg] < 1) - set_mtrr_cpuslocked(reg, 0, 0, 0); + set_mtrr(reg, 0, 0, 0); error = reg; out: mutex_unlock(&mtrr_mutex); @@ -582,9 +570,9 @@ static void mtrr_restore(void) for (i = 0; i < num_var_ranges; i++) { if (mtrr_value[i].lsize) { - set_mtrr(i, mtrr_value[i].lbase, - mtrr_value[i].lsize, - mtrr_value[i].ltype); + mtrr_if->set(i, mtrr_value[i].lbase, + mtrr_value[i].lsize, + mtrr_value[i].ltype); } } } -- cgit v1.2.3 From b5d3c72829b1f2b181cd7c5b426f7deaae452045 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:23 +0200 Subject: x86/mtrr: Move 32-bit code from mtrr.c to legacy.c There is some code in mtrr.c which is relevant for old 32-bit CPUs only. Move it to a new source legacy.c. While modifying mtrr_init_finalize() fix spelling of its name. Suggested-by: Borislav Petkov Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-9-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/Makefile | 2 +- arch/x86/kernel/cpu/mtrr/legacy.c | 84 +++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/mtrr/mtrr.c | 80 +++---------------------------------- arch/x86/kernel/cpu/mtrr/mtrr.h | 7 ++++ 4 files changed, 98 insertions(+), 75 deletions(-) create mode 100644 arch/x86/kernel/cpu/mtrr/legacy.c (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile index cc4f9f1cb94c..aee4bc5ad496 100644 --- a/arch/x86/kernel/cpu/mtrr/Makefile +++ b/arch/x86/kernel/cpu/mtrr/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := mtrr.o if.o generic.o cleanup.o -obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o +obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o legacy.o diff --git a/arch/x86/kernel/cpu/mtrr/legacy.c b/arch/x86/kernel/cpu/mtrr/legacy.c new file mode 100644 index 000000000000..7d379fb26cce --- /dev/null +++ b/arch/x86/kernel/cpu/mtrr/legacy.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include "mtrr.h" + +void mtrr_set_if(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + /* Pre-Athlon (K6) AMD CPU MTRRs */ + if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) + mtrr_if = &amd_mtrr_ops; + break; + case X86_VENDOR_CENTAUR: + if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) + mtrr_if = ¢aur_mtrr_ops; + break; + case X86_VENDOR_CYRIX: + if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) + mtrr_if = &cyrix_mtrr_ops; + break; + default: + break; + } +} + +/* + * The suspend/resume methods are only for CPUs without MTRR. CPUs using generic + * MTRR driver don't require this. + */ +struct mtrr_value { + mtrr_type ltype; + unsigned long lbase; + unsigned long lsize; +}; + +static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES]; + +static int mtrr_save(void) +{ + int i; + + for (i = 0; i < num_var_ranges; i++) { + mtrr_if->get(i, &mtrr_value[i].lbase, + &mtrr_value[i].lsize, + &mtrr_value[i].ltype); + } + return 0; +} + +static void mtrr_restore(void) +{ + int i; + + for (i = 0; i < num_var_ranges; i++) { + if (mtrr_value[i].lsize) { + mtrr_if->set(i, mtrr_value[i].lbase, + mtrr_value[i].lsize, + mtrr_value[i].ltype); + } + } +} + +static struct syscore_ops mtrr_syscore_ops = { + .suspend = mtrr_save, + .resume = mtrr_restore, +}; + +void mtrr_register_syscore(void) +{ + /* + * The CPU has no MTRR and seems to not support SMP. They have + * specific drivers, we use a tricky method to support + * suspend/resume for them. + * + * TBD: is there any system with such CPU which supports + * suspend/resume? If no, we should remove the code. + */ + register_syscore_ops(&mtrr_syscore_ops); +} diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 007ecca62676..b7793a442791 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -541,49 +541,6 @@ int arch_phys_wc_index(int handle) } EXPORT_SYMBOL_GPL(arch_phys_wc_index); -/* The suspend/resume methods are only for CPU without MTRR. CPU using generic - * MTRR driver doesn't require this - */ -struct mtrr_value { - mtrr_type ltype; - unsigned long lbase; - unsigned long lsize; -}; - -static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES]; - -static int mtrr_save(void) -{ - int i; - - for (i = 0; i < num_var_ranges; i++) { - mtrr_if->get(i, &mtrr_value[i].lbase, - &mtrr_value[i].lsize, - &mtrr_value[i].ltype); - } - return 0; -} - -static void mtrr_restore(void) -{ - int i; - - for (i = 0; i < num_var_ranges; i++) { - if (mtrr_value[i].lsize) { - mtrr_if->set(i, mtrr_value[i].lbase, - mtrr_value[i].lsize, - mtrr_value[i].ltype); - } - } -} - - - -static struct syscore_ops mtrr_syscore_ops = { - .suspend = mtrr_save, - .resume = mtrr_restore, -}; - int __initdata changed_by_mtrr_cleanup; /** @@ -611,27 +568,10 @@ void __init mtrr_bp_init(void) return; } - if (generic_mtrrs) { + if (generic_mtrrs) mtrr_if = &generic_mtrr_ops; - } else { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - /* Pre-Athlon (K6) AMD CPU MTRRs */ - if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) - mtrr_if = &amd_mtrr_ops; - break; - case X86_VENDOR_CENTAUR: - if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) - mtrr_if = ¢aur_mtrr_ops; - break; - case X86_VENDOR_CYRIX: - if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) - mtrr_if = &cyrix_mtrr_ops; - break; - default: - break; - } - } + else + mtrr_set_if(); if (mtrr_enabled()) { /* Get the number of variable MTRR ranges. */ @@ -673,7 +613,7 @@ void mtrr_save_state(void) smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); } -static int __init mtrr_init_finialize(void) +static int __init mtrr_init_finalize(void) { if (!mtrr_enabled()) return 0; @@ -684,16 +624,8 @@ static int __init mtrr_init_finialize(void) return 0; } - /* - * The CPU has no MTRR and seems to not support SMP. They have - * specific drivers, we use a tricky method to support - * suspend/resume for them. - * - * TBD: is there any system with such CPU which supports - * suspend/resume? If no, we should remove the code. - */ - register_syscore_ops(&mtrr_syscore_ops); + mtrr_register_syscore(); return 0; } -subsys_initcall(mtrr_init_finialize); +subsys_initcall(mtrr_init_finalize); diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 6f3312be4b27..e1e886486ae8 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -61,6 +61,13 @@ extern u32 phys_hi_rsvd; void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); +#ifdef CONFIG_X86_32 +void mtrr_set_if(void); +void mtrr_register_syscore(void); +#else +static inline void mtrr_set_if(void) { } +static inline void mtrr_register_syscore(void) { } +#endif /* CPU specific mtrr_ops vectors. */ extern const struct mtrr_ops amd_mtrr_ops; -- cgit v1.2.3 From 961c6a4326643e6588352b7f1f5d77364415386f Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:24 +0200 Subject: x86/mtrr: Allocate mtrr_value array dynamically The mtrr_value[] array is a static variable which is used only in a few configurations. Consuming 6kB is ridiculous for this case, especially as the array doesn't need to be that large and it can easily be allocated dynamically. Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-10-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/legacy.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/legacy.c b/arch/x86/kernel/cpu/mtrr/legacy.c index 7d379fb26cce..d25882fcf181 100644 --- a/arch/x86/kernel/cpu/mtrr/legacy.c +++ b/arch/x86/kernel/cpu/mtrr/legacy.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include #include #include #include @@ -38,12 +39,15 @@ struct mtrr_value { unsigned long lsize; }; -static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES]; +static struct mtrr_value *mtrr_value; static int mtrr_save(void) { int i; + if (!mtrr_value) + return -ENOMEM; + for (i = 0; i < num_var_ranges; i++) { mtrr_if->get(i, &mtrr_value[i].lbase, &mtrr_value[i].lsize, @@ -72,6 +76,8 @@ static struct syscore_ops mtrr_syscore_ops = { void mtrr_register_syscore(void) { + mtrr_value = kcalloc(num_var_ranges, sizeof(*mtrr_value), GFP_KERNEL); + /* * The CPU has no MTRR and seems to not support SMP. They have * specific drivers, we use a tricky method to support -- cgit v1.2.3 From 1ca12099040fec8c6bbcd9fabf37f04ac0d08e48 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:25 +0200 Subject: x86/mtrr: Add get_effective_type() service function Add a service function for obtaining the effective cache mode of overlapping MTRR registers. Make use of that function in check_type_overlap(). Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-11-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/generic.c | 39 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 4d8ca6234bbf..b9442717977f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -80,31 +80,30 @@ static u64 get_mtrr_size(u64 mask) return size; } +static u8 get_effective_type(u8 type1, u8 type2) +{ + if (type1 == MTRR_TYPE_UNCACHABLE || type2 == MTRR_TYPE_UNCACHABLE) + return MTRR_TYPE_UNCACHABLE; + + if ((type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH) || + (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK)) + return MTRR_TYPE_WRTHROUGH; + + if (type1 != type2) + return MTRR_TYPE_UNCACHABLE; + + return type1; +} + /* * Check and return the effective type for MTRR-MTRR type overlap. - * Returns 1 if the effective type is UNCACHEABLE, else returns 0 + * Returns true if the effective type is UNCACHEABLE, else returns false */ -static int check_type_overlap(u8 *prev, u8 *curr) +static bool check_type_overlap(u8 *prev, u8 *curr) { - if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) { - *prev = MTRR_TYPE_UNCACHABLE; - *curr = MTRR_TYPE_UNCACHABLE; - return 1; - } - - if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) || - (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) { - *prev = MTRR_TYPE_WRTHROUGH; - *curr = MTRR_TYPE_WRTHROUGH; - } + *prev = *curr = get_effective_type(*curr, *prev); - if (*prev != *curr) { - *prev = MTRR_TYPE_UNCACHABLE; - *curr = MTRR_TYPE_UNCACHABLE; - return 1; - } - - return 0; + return *prev == MTRR_TYPE_UNCACHABLE; } /** -- cgit v1.2.3 From 061b984aab5845dc958f248b5b0f9040fe45b5e1 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:26 +0200 Subject: x86/mtrr: Construct a memory map with cache modes After MTRR initialization construct a memory map with cache modes from MTRR values. This will speed up lookups via mtrr_lookup_type() especially in case of overlapping MTRRs. This will be needed when switching the semantics of the "uniform" parameter of mtrr_lookup_type() from "only covered by one MTRR" to "memory range has a uniform cache mode", which is the data the callers really want to know. Today this information is not easily available, in case MTRRs are not well sorted regarding base address. The map will be built in __initdata. When memory management is up, the map will be moved to dynamically allocated memory, in order to avoid the need of an overly large array. The size of this array is calculated using the number of variable MTRR registers and the needed size for fixed entries. Only add the map creation and expansion for now. The lookup will be added later. When writing new MTRR entries in the running system rebuild the map inside the call from mtrr_rendezvous_handler() in order to avoid nasty race conditions with concurrent lookups. [ bp: Move out rebuild_map() call and rename it. ] Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-12-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/generic.c | 299 +++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/mtrr/mtrr.c | 12 +- arch/x86/kernel/cpu/mtrr/mtrr.h | 5 +- 3 files changed, 314 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index b9442717977f..e0db6fc1bfd4 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -33,6 +33,38 @@ static struct fixed_range_block fixed_range_blocks[] = { {} }; +struct cache_map { + u64 start; + u64 end; + u64 flags; + u64 type:8; + u64 fixed:1; +}; + +/* + * CACHE_MAP_MAX is the maximum number of memory ranges in cache_map, where + * no 2 adjacent ranges have the same cache mode (those would be merged). + * The number is based on the worst case: + * - no two adjacent fixed MTRRs share the same cache mode + * - one variable MTRR is spanning a huge area with mode WB + * - 255 variable MTRRs with mode UC all overlap with the WB MTRR, creating 2 + * additional ranges each (result like "ababababa...aba" with a = WB, b = UC), + * accounting for MTRR_MAX_VAR_RANGES * 2 - 1 range entries + * - a TOP_MEM2 area (even with overlapping an UC MTRR can't add 2 range entries + * to the possible maximum, as it always starts at 4GB, thus it can't be in + * the middle of that MTRR, unless that MTRR starts at 0, which would remove + * the initial "a" from the "abababa" pattern above) + * The map won't contain ranges with no matching MTRR (those fall back to the + * default cache mode). + */ +#define CACHE_MAP_MAX (MTRR_NUM_FIXED_RANGES + MTRR_MAX_VAR_RANGES * 2) + +static struct cache_map init_cache_map[CACHE_MAP_MAX] __initdata; +static struct cache_map *cache_map __refdata = init_cache_map; +static unsigned int cache_map_size = CACHE_MAP_MAX; +static unsigned int cache_map_n; +static unsigned int cache_map_fixed; + static unsigned long smp_changes_mask; static int mtrr_state_set; u64 mtrr_tom2; @@ -80,6 +112,20 @@ static u64 get_mtrr_size(u64 mask) return size; } +static u8 get_var_mtrr_state(unsigned int reg, u64 *start, u64 *size) +{ + struct mtrr_var_range *mtrr = mtrr_state.var_ranges + reg; + + if (!(mtrr->mask_lo & MTRR_PHYSMASK_V)) + return MTRR_TYPE_INVALID; + + *start = (((u64)mtrr->base_hi) << 32) + (mtrr->base_lo & PAGE_MASK); + *size = get_mtrr_size((((u64)mtrr->mask_hi) << 32) + + (mtrr->mask_lo & PAGE_MASK)); + + return mtrr->base_lo & MTRR_PHYSBASE_TYPE; +} + static u8 get_effective_type(u8 type1, u8 type2) { if (type1 == MTRR_TYPE_UNCACHABLE || type2 == MTRR_TYPE_UNCACHABLE) @@ -243,6 +289,259 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, return mtrr_state.def_type; } +static void rm_map_entry_at(int idx) +{ + cache_map_n--; + if (cache_map_n > idx) { + memmove(cache_map + idx, cache_map + idx + 1, + sizeof(*cache_map) * (cache_map_n - idx)); + } +} + +/* + * Add an entry into cache_map at a specific index. Merges adjacent entries if + * appropriate. Return the number of merges for correcting the scan index + * (this is needed as merging will reduce the number of entries, which will + * result in skipping entries in future iterations if the scan index isn't + * corrected). + * Note that the corrected index can never go below -1 (resulting in being 0 in + * the next scan iteration), as "2" is returned only if the current index is + * larger than zero. + */ +static int add_map_entry_at(u64 start, u64 end, u8 type, int idx) +{ + bool merge_prev = false, merge_next = false; + + if (start >= end) + return 0; + + if (idx > 0) { + struct cache_map *prev = cache_map + idx - 1; + + if (!prev->fixed && start == prev->end && type == prev->type) + merge_prev = true; + } + + if (idx < cache_map_n) { + struct cache_map *next = cache_map + idx; + + if (!next->fixed && end == next->start && type == next->type) + merge_next = true; + } + + if (merge_prev && merge_next) { + cache_map[idx - 1].end = cache_map[idx].end; + rm_map_entry_at(idx); + return 2; + } + if (merge_prev) { + cache_map[idx - 1].end = end; + return 1; + } + if (merge_next) { + cache_map[idx].start = start; + return 1; + } + + /* Sanity check: the array should NEVER be too small! */ + if (cache_map_n == cache_map_size) { + WARN(1, "MTRR cache mode memory map exhausted!\n"); + cache_map_n = cache_map_fixed; + return 0; + } + + if (cache_map_n > idx) { + memmove(cache_map + idx + 1, cache_map + idx, + sizeof(*cache_map) * (cache_map_n - idx)); + } + + cache_map[idx].start = start; + cache_map[idx].end = end; + cache_map[idx].type = type; + cache_map[idx].fixed = 0; + cache_map_n++; + + return 0; +} + +/* Clear a part of an entry. Return 1 if start of entry is still valid. */ +static int clr_map_range_at(u64 start, u64 end, int idx) +{ + int ret = start != cache_map[idx].start; + u64 tmp; + + if (start == cache_map[idx].start && end == cache_map[idx].end) { + rm_map_entry_at(idx); + } else if (start == cache_map[idx].start) { + cache_map[idx].start = end; + } else if (end == cache_map[idx].end) { + cache_map[idx].end = start; + } else { + tmp = cache_map[idx].end; + cache_map[idx].end = start; + add_map_entry_at(end, tmp, cache_map[idx].type, idx + 1); + } + + return ret; +} + +/* + * Add MTRR to the map. The current map is scanned and each part of the MTRR + * either overlapping with an existing entry or with a hole in the map is + * handled separately. + */ +static void add_map_entry(u64 start, u64 end, u8 type) +{ + u8 new_type, old_type; + u64 tmp; + int i; + + for (i = 0; i < cache_map_n && start < end; i++) { + if (start >= cache_map[i].end) + continue; + + if (start < cache_map[i].start) { + /* Region start has no overlap. */ + tmp = min(end, cache_map[i].start); + i -= add_map_entry_at(start, tmp, type, i); + start = tmp; + continue; + } + + new_type = get_effective_type(type, cache_map[i].type); + old_type = cache_map[i].type; + + if (cache_map[i].fixed || new_type == old_type) { + /* Cut off start of new entry. */ + start = cache_map[i].end; + continue; + } + + /* Handle only overlapping part of region. */ + tmp = min(end, cache_map[i].end); + i += clr_map_range_at(start, tmp, i); + i -= add_map_entry_at(start, tmp, new_type, i); + start = tmp; + } + + /* Add rest of region after last map entry (rest might be empty). */ + add_map_entry_at(start, end, type, i); +} + +/* Add variable MTRRs to cache map. */ +static void map_add_var(void) +{ + u64 start, size; + unsigned int i; + u8 type; + + /* + * Add AMD TOP_MEM2 area. Can't be added in mtrr_build_map(), as it + * needs to be added again when rebuilding the map due to potentially + * having moved as a result of variable MTRRs for memory below 4GB. + */ + if (mtrr_tom2) { + add_map_entry(BIT_ULL(32), mtrr_tom2, MTRR_TYPE_WRBACK); + cache_map[cache_map_n - 1].fixed = 1; + } + + for (i = 0; i < num_var_ranges; i++) { + type = get_var_mtrr_state(i, &start, &size); + if (type != MTRR_TYPE_INVALID) + add_map_entry(start, start + size, type); + } +} + +/* + * Rebuild map by replacing variable entries. Needs to be called when MTRR + * registers are being changed after boot, as such changes could include + * removals of registers, which are complicated to handle without rebuild of + * the map. + */ +void generic_rebuild_map(void) +{ + if (mtrr_if != &generic_mtrr_ops) + return; + + cache_map_n = cache_map_fixed; + + map_add_var(); +} + +static unsigned int __init get_cache_map_size(void) +{ + return cache_map_fixed + 2 * num_var_ranges + (mtrr_tom2 != 0); +} + +/* Build the cache_map containing the cache modes per memory range. */ +void __init mtrr_build_map(void) +{ + u64 start, end, size; + unsigned int i; + u8 type; + + /* Add fixed MTRRs, optimize for adjacent entries with same type. */ + if (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED) { + /* + * Start with 64k size fixed entries, preset 1st one (hence the + * loop below is starting with index 1). + */ + start = 0; + end = size = 0x10000; + type = mtrr_state.fixed_ranges[0]; + + for (i = 1; i < MTRR_NUM_FIXED_RANGES; i++) { + /* 8 64k entries, then 16 16k ones, rest 4k. */ + if (i == 8 || i == 24) + size >>= 2; + + if (mtrr_state.fixed_ranges[i] != type) { + add_map_entry(start, end, type); + start = end; + type = mtrr_state.fixed_ranges[i]; + } + end += size; + } + add_map_entry(start, end, type); + } + + /* Mark fixed, they take precedence. */ + for (i = 0; i < cache_map_n; i++) + cache_map[i].fixed = 1; + cache_map_fixed = cache_map_n; + + map_add_var(); + + pr_info("MTRR map: %u entries (%u fixed + %u variable; max %u), built from %u variable MTRRs\n", + cache_map_n, cache_map_fixed, cache_map_n - cache_map_fixed, + get_cache_map_size(), num_var_ranges + (mtrr_tom2 != 0)); +} + +/* Copy the cache_map from __initdata memory to dynamically allocated one. */ +void __init mtrr_copy_map(void) +{ + unsigned int new_size = get_cache_map_size(); + + if (!mtrr_state.enabled || !new_size) { + cache_map = NULL; + return; + } + + mutex_lock(&mtrr_mutex); + + cache_map = kcalloc(new_size, sizeof(*cache_map), GFP_KERNEL); + if (cache_map) { + memmove(cache_map, init_cache_map, + cache_map_n * sizeof(*cache_map)); + cache_map_size = new_size; + } else { + mtrr_state.enabled = 0; + pr_err("MTRRs disabled due to allocation failure for lookup map.\n"); + } + + mutex_unlock(&mtrr_mutex); +} + /** * mtrr_overwrite_state - set static MTRR state * diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index b7793a442791..ec8670bb5d88 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -61,7 +61,7 @@ u32 num_var_ranges; unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; -static DEFINE_MUTEX(mtrr_mutex); +DEFINE_MUTEX(mtrr_mutex); const struct mtrr_ops *mtrr_if; @@ -183,6 +183,8 @@ static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, }; stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); + + generic_rebuild_map(); } /** @@ -563,6 +565,7 @@ void __init mtrr_bp_init(void) * Note that X86_FEATURE_MTRR has been reset in this case. */ init_table(); + mtrr_build_map(); pr_info("MTRRs set to read-only\n"); return; @@ -587,6 +590,7 @@ void __init mtrr_bp_init(void) if (get_mtrr_state()) { memory_caching_control |= CACHE_MTRR; changed_by_mtrr_cleanup = mtrr_cleanup(); + mtrr_build_map(); } else { mtrr_if = NULL; why = "by BIOS"; @@ -615,6 +619,12 @@ void mtrr_save_state(void) static int __init mtrr_init_finalize(void) { + /* + * Map might exist if mtrr_overwrite_state() has been called or if + * mtrr_enabled() returns true. + */ + mtrr_copy_map(); + if (!mtrr_enabled()) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index e1e886486ae8..8385d7d3a865 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void fill_mtrr_var_range(unsigned int index, bool get_mtrr_state(void); extern const struct mtrr_ops *mtrr_if; +extern struct mutex mtrr_mutex; extern unsigned int num_var_ranges; extern u64 mtrr_tom2; @@ -68,6 +69,8 @@ void mtrr_register_syscore(void); static inline void mtrr_set_if(void) { } static inline void mtrr_register_syscore(void) { } #endif +void mtrr_build_map(void); +void mtrr_copy_map(void); /* CPU specific mtrr_ops vectors. */ extern const struct mtrr_ops amd_mtrr_ops; @@ -76,7 +79,6 @@ extern const struct mtrr_ops centaur_mtrr_ops; extern int changed_by_mtrr_cleanup; extern int mtrr_cleanup(void); -void generic_rebuild_map(void); /* * Must be used by code which uses mtrr_if to call platform-specific @@ -86,3 +88,4 @@ static inline bool mtrr_enabled(void) { return !!mtrr_if; } +void generic_rebuild_map(void); -- cgit v1.2.3 From a4316603534cf7f4dcd9f9f1ed170257b987cca9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:27 +0200 Subject: x86/mtrr: Add mtrr=debug command line option Add a new command line option "mtrr=debug" for getting debug output after building the new cache mode map. The output will include MTRR register values and the resulting map. Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-13-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- Documentation/admin-guide/kernel-parameters.txt | 4 ++ arch/x86/kernel/cpu/mtrr/generic.c | 64 +++++++++++++++++-------- 2 files changed, 49 insertions(+), 19 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9e5bab29685f..44a87ada7145 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3423,6 +3423,10 @@ [HW] Make the MicroTouch USB driver use raw coordinates ('y', default) or cooked coordinates ('n') + mtrr=debug [X86] + Enable printing debug information related to MTRR + registers at boot time. + mtrr_chunk_size=nn[KMG] [X86] used for mtrr cleanup. It is largest continuous chunk that could hold holes aka. UC entries. diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index e0db6fc1bfd4..852031ef4780 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -41,6 +41,23 @@ struct cache_map { u64 fixed:1; }; +static bool mtrr_debug; + +static int __init mtrr_param_setup(char *str) +{ + int rc = 0; + + if (!str) + return -EINVAL; + if (!strcmp(str, "debug")) + mtrr_debug = true; + else + rc = -EINVAL; + + return rc; +} +early_param("mtrr", mtrr_param_setup); + /* * CACHE_MAP_MAX is the maximum number of memory ranges in cache_map, where * no 2 adjacent ranges have the same cache mode (those would be merged). @@ -515,6 +532,14 @@ void __init mtrr_build_map(void) pr_info("MTRR map: %u entries (%u fixed + %u variable; max %u), built from %u variable MTRRs\n", cache_map_n, cache_map_fixed, cache_map_n - cache_map_fixed, get_cache_map_size(), num_var_ranges + (mtrr_tom2 != 0)); + + if (mtrr_debug) { + for (i = 0; i < cache_map_n; i++) { + pr_info("%3u: %016llx-%016llx %s\n", i, + cache_map[i].start, cache_map[i].end - 1, + mtrr_attrib_to_str(cache_map[i].type)); + } + } } /* Copy the cache_map from __initdata memory to dynamically allocated one. */ @@ -721,8 +746,8 @@ static void __init print_fixed_last(void) if (!last_fixed_end) return; - pr_debug(" %05X-%05X %s\n", last_fixed_start, - last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); + pr_info(" %05X-%05X %s\n", last_fixed_start, + last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); last_fixed_end = 0; } @@ -760,10 +785,10 @@ static void __init print_mtrr_state(void) unsigned int i; int high_width; - pr_debug("MTRR default type: %s\n", - mtrr_attrib_to_str(mtrr_state.def_type)); + pr_info("MTRR default type: %s\n", + mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { - pr_debug("MTRR fixed ranges %sabled:\n", + pr_info("MTRR fixed ranges %sabled:\n", ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? "en" : "dis"); @@ -778,27 +803,27 @@ static void __init print_mtrr_state(void) /* tail */ print_fixed_last(); } - pr_debug("MTRR variable ranges %sabled:\n", - mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); + pr_info("MTRR variable ranges %sabled:\n", + mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V) - pr_debug(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", - i, - high_width, - mtrr_state.var_ranges[i].base_hi, - mtrr_state.var_ranges[i].base_lo >> 12, - high_width, - mtrr_state.var_ranges[i].mask_hi, - mtrr_state.var_ranges[i].mask_lo >> 12, - mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & + pr_info(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", + i, + high_width, + mtrr_state.var_ranges[i].base_hi, + mtrr_state.var_ranges[i].base_lo >> 12, + high_width, + mtrr_state.var_ranges[i].mask_hi, + mtrr_state.var_ranges[i].mask_lo >> 12, + mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & MTRR_PHYSBASE_TYPE)); else - pr_debug(" %u disabled\n", i); + pr_info(" %u disabled\n", i); } if (mtrr_tom2) - pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); + pr_info("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } /* Grab all of the MTRR state for this CPU into *state */ @@ -833,7 +858,8 @@ bool __init get_mtrr_state(void) mtrr_tom2 &= 0xffffff800000ULL; } - print_mtrr_state(); + if (mtrr_debug) + print_mtrr_state(); mtrr_state_set = 1; -- cgit v1.2.3 From 8227f40ade2362982505f66f1614b78a3a083ec9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:28 +0200 Subject: x86/mtrr: Use new cache_map in mtrr_type_lookup() Instead of crawling through the MTRR register state, use the new cache_map for looking up the cache type(s) of a memory region. This allows now to set the uniform parameter according to the uniformity of the cache mode of the region, instead of setting it only if the complete region is mapped by a single MTRR. This now includes even the region covered by the fixed MTRR registers. Make sure uniform is always set. [ bp: Massage. ] [ jgross: Explain mtrr_type_lookup() logic. ] Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-14-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/kernel/cpu/mtrr/generic.c | 237 +++++++------------------------------ 1 file changed, 43 insertions(+), 194 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 852031ef4780..4443e71084b8 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -158,154 +158,6 @@ static u8 get_effective_type(u8 type1, u8 type2) return type1; } -/* - * Check and return the effective type for MTRR-MTRR type overlap. - * Returns true if the effective type is UNCACHEABLE, else returns false - */ -static bool check_type_overlap(u8 *prev, u8 *curr) -{ - *prev = *curr = get_effective_type(*curr, *prev); - - return *prev == MTRR_TYPE_UNCACHABLE; -} - -/** - * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries - * - * Return the MTRR fixed memory type of 'start'. - * - * MTRR fixed entries are divided into the following ways: - * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges - * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges - * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges - * - * Return Values: - * MTRR_TYPE_(type) - Matched memory type - * MTRR_TYPE_INVALID - Unmatched - */ -static u8 mtrr_type_lookup_fixed(u64 start, u64 end) -{ - int idx; - - if (start >= 0x100000) - return MTRR_TYPE_INVALID; - - /* 0x0 - 0x7FFFF */ - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state.fixed_ranges[idx]; - /* 0x80000 - 0xBFFFF */ - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state.fixed_ranges[idx]; - } - - /* 0xC0000 - 0xFFFFF */ - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state.fixed_ranges[idx]; -} - -/** - * mtrr_type_lookup_variable - look up memory type in MTRR variable entries - * - * Return Value: - * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched) - * - * Output Arguments: - * repeat - Set to 1 when [start:end] spanned across MTRR range and type - * returned corresponds only to [start:*partial_end]. Caller has - * to lookup again for [*partial_end:end]. - * - * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the - * region is fully covered by a single MTRR entry or the default - * type. - */ -static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, - int *repeat, u8 *uniform) -{ - int i; - u64 base, mask; - u8 prev_match, curr_match; - - *repeat = 0; - *uniform = 1; - - prev_match = MTRR_TYPE_INVALID; - for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state, inclusive; - - if (!(mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V)) - continue; - - base = (((u64)mtrr_state.var_ranges[i].base_hi) << 32) + - (mtrr_state.var_ranges[i].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state.var_ranges[i].mask_hi) << 32) + - (mtrr_state.var_ranges[i].mask_lo & PAGE_MASK); - - start_state = ((start & mask) == (base & mask)); - end_state = ((end & mask) == (base & mask)); - inclusive = ((start < base) && (end > base)); - - if ((start_state != end_state) || inclusive) { - /* - * We have start:end spanning across an MTRR. - * We split the region into either - * - * - start_state:1 - * (start:mtrr_end)(mtrr_end:end) - * - end_state:1 - * (start:mtrr_start)(mtrr_start:end) - * - inclusive:1 - * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end) - * - * depending on kind of overlap. - * - * Return the type of the first region and a pointer - * to the start of next region so that caller will be - * advised to lookup again after having adjusted start - * and end. - * - * Note: This way we handle overlaps with multiple - * entries and the default type properly. - */ - if (start_state) - *partial_end = base + get_mtrr_size(mask); - else - *partial_end = base; - - if (unlikely(*partial_end <= start)) { - WARN_ON(1); - *partial_end = start + PAGE_SIZE; - } - - end = *partial_end - 1; /* end is inclusive */ - *repeat = 1; - *uniform = 0; - } - - if ((start & mask) != (base & mask)) - continue; - - curr_match = mtrr_state.var_ranges[i].base_lo & MTRR_PHYSBASE_TYPE; - if (prev_match == MTRR_TYPE_INVALID) { - prev_match = curr_match; - continue; - } - - *uniform = 0; - if (check_type_overlap(&prev_match, &curr_match)) - return curr_match; - } - - if (prev_match != MTRR_TYPE_INVALID) - return prev_match; - - return mtrr_state.def_type; -} - static void rm_map_entry_at(int idx) { cache_map_n--; @@ -623,6 +475,20 @@ void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, mtrr_state_set = 1; } +static u8 type_merge(u8 type, u8 new_type, u8 *uniform) +{ + u8 effective_type; + + if (type == MTRR_TYPE_INVALID) + return new_type; + + effective_type = get_effective_type(type, new_type); + if (type != effective_type) + *uniform = 0; + + return effective_type; +} + /** * mtrr_type_lookup - look up memory type in MTRR * @@ -631,66 +497,49 @@ void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, * MTRR_TYPE_INVALID - MTRR is disabled * * Output Argument: - * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the - * region is fully covered by a single MTRR entry or the default - * type. + * uniform - Set to 1 when the returned MTRR type is valid for the whole + * region, set to 0 else. */ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { - u8 type, prev_type, is_uniform = 1, dummy; - int repeat; - u64 partial_end; - - /* Make end inclusive instead of exclusive */ - end--; + u8 type = MTRR_TYPE_INVALID; + unsigned int i; - if (!mtrr_state_set) + if (!mtrr_state_set) { + /* Uniformity is unknown. */ + *uniform = 0; return MTRR_TYPE_INVALID; + } + + *uniform = 1; if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) return MTRR_TYPE_INVALID; - /* - * Look up the fixed ranges first, which take priority over - * the variable ranges. - */ - if ((start < 0x100000) && - (mtrr_state.have_fixed) && - (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { - is_uniform = 0; - type = mtrr_type_lookup_fixed(start, end); - goto out; - } + for (i = 0; i < cache_map_n && start < end; i++) { + /* Region after current map entry? -> continue with next one. */ + if (start >= cache_map[i].end) + continue; - /* - * Look up the variable ranges. Look of multiple ranges matching - * this address and pick type as per MTRR precedence. - */ - type = mtrr_type_lookup_variable(start, end, &partial_end, - &repeat, &is_uniform); + /* Start of region not covered by current map entry? */ + if (start < cache_map[i].start) { + /* At least some part of region has default type. */ + type = type_merge(type, mtrr_state.def_type, uniform); + /* End of region not covered, too? -> lookup done. */ + if (end <= cache_map[i].start) + return type; + } - /* - * Common path is with repeat = 0. - * However, we can have cases where [start:end] spans across some - * MTRR ranges and/or the default type. Do repeated lookups for - * that case here. - */ - while (repeat) { - prev_type = type; - start = partial_end; - is_uniform = 0; - type = mtrr_type_lookup_variable(start, end, &partial_end, - &repeat, &dummy); - - if (check_type_overlap(&prev_type, &type)) - goto out; + /* At least part of region covered by map entry. */ + type = type_merge(type, cache_map[i].type, uniform); + + start = cache_map[i].end; } - if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2)) - type = MTRR_TYPE_WRBACK; + /* End of region past last entry in map? -> use default type. */ + if (start < end) + type = type_merge(type, mtrr_state.def_type, uniform); -out: - *uniform = is_uniform; return type; } -- cgit v1.2.3 From 973df1942068c0cc72244ce7dce5e5aeca03ad5f Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:29 +0200 Subject: x86/mtrr: Don't let mtrr_type_lookup() return MTRR_TYPE_INVALID mtrr_type_lookup() should always return a valid memory type. In case there is no information available, it should return the default UC. This will remove the last case where mtrr_type_lookup() can return MTRR_TYPE_INVALID, so adjust the comment in include/uapi/asm/mtrr.h. Note that removing the MTRR_TYPE_INVALID #define from that header could break user code, so it has to stay. At the same time the mtrr_type_lookup() stub for the !CONFIG_MTRR case should set uniform to 1, as if the memory range would be covered by no MTRR at all. Suggested-by: Linus Torvalds Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-15-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/mtrr.h | 7 +++++-- arch/x86/include/uapi/asm/mtrr.h | 6 +++--- arch/x86/kernel/cpu/mtrr/generic.c | 4 ++-- 3 files changed, 10 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 1bae790a553a..5a758ee24bf7 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -86,9 +86,12 @@ static inline void mtrr_overwrite_state(struct mtrr_var_range *var, static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform) { /* - * Return no-MTRRs: + * Return the default MTRR type, without any known other types in + * that range. */ - return MTRR_TYPE_INVALID; + *uniform = 1; + + return MTRR_TYPE_UNCACHABLE; } #define mtrr_save_fixed_ranges(arg) do {} while (0) #define mtrr_save_state() do {} while (0) diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h index ab194c831625..3a8a8eb8ac3a 100644 --- a/arch/x86/include/uapi/asm/mtrr.h +++ b/arch/x86/include/uapi/asm/mtrr.h @@ -107,9 +107,9 @@ typedef __u8 mtrr_type; #define MTRR_NUM_TYPES 7 /* - * Invalid MTRR memory type. mtrr_type_lookup() returns this value when - * MTRRs are disabled. Note, this value is allocated from the reserved - * values (0x7-0xff) of the MTRR memory types. + * Invalid MTRR memory type. No longer used outside of MTRR code. + * Note, this value is allocated from the reserved values (0x7-0xff) of + * the MTRR memory types. */ #define MTRR_TYPE_INVALID 0xff diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 4443e71084b8..f6b426d8be4f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -508,13 +508,13 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) if (!mtrr_state_set) { /* Uniformity is unknown. */ *uniform = 0; - return MTRR_TYPE_INVALID; + return MTRR_TYPE_UNCACHABLE; } *uniform = 1; if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) - return MTRR_TYPE_INVALID; + return MTRR_TYPE_UNCACHABLE; for (i = 0; i < cache_map_n && start < end; i++) { /* Region after current map entry? -> continue with next one. */ -- cgit v1.2.3 From 08611a3a9a23e5e2e1a799e966c69ebc4851dfa8 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 2 May 2023 14:09:31 +0200 Subject: x86/mtrr: Remove unused code mtrr_centaur_report_mcr() isn't used by anyone, so it can be removed. Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Tested-by: Michael Kelley Link: https://lore.kernel.org/r/20230502120931.20719-17-jgross@suse.com Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/mtrr.h | 4 ---- arch/x86/kernel/cpu/mtrr/centaur.c | 9 --------- 2 files changed, 13 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 5a758ee24bf7..090d658a85a6 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -69,7 +69,6 @@ extern int mtrr_add_page(unsigned long base, unsigned long size, unsigned int type, bool increment); extern int mtrr_del(int reg, unsigned long base, unsigned long size); extern int mtrr_del_page(int reg, unsigned long base, unsigned long size); -extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi); extern void mtrr_bp_restore(void); extern int mtrr_trim_uncached_memory(unsigned long end_pfn); extern int amd_special_default_mtrr(void); @@ -117,9 +116,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) { return 0; } -static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) -{ -} #define mtrr_bp_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) #define mtrr_disable() do {} while (0) diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index 4466ddeb0125..6f6c3ae92943 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -45,15 +45,6 @@ centaur_get_free_region(unsigned long base, unsigned long size, int replace_reg) return -ENOSPC; } -/* - * Report boot time MCR setups - */ -void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) -{ - centaur_mcr[mcr].low = lo; - centaur_mcr[mcr].high = hi; -} - static void centaur_get_mcr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type * type) -- cgit v1.2.3 From 7c1dee734f3b8003429c40fb9186401485670dfd Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Wed, 31 May 2023 19:23:34 +0200 Subject: x86/mtrr: Unify debugging printing Put all the debugging output behind "mtrr=debug" and get rid of "mtrr_cleanup_debug" which wasn't even documented anywhere. No functional changes. Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20230531174857.GDZHeIib57h5lT5Vh1@fat_crate.local --- arch/x86/kernel/cpu/mtrr/cleanup.c | 59 +++++++++++++++----------------------- arch/x86/kernel/cpu/mtrr/generic.c | 2 +- arch/x86/kernel/cpu/mtrr/mtrr.c | 5 ++-- arch/x86/kernel/cpu/mtrr/mtrr.h | 3 ++ 4 files changed, 29 insertions(+), 40 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index ed5f84c20ac2..18cf79d6e2c5 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -55,9 +55,6 @@ static int __initdata nr_range; static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; -static int __initdata debug_print; -#define Dprintk(x...) do { if (debug_print) pr_debug(x); } while (0) - #define BIOS_BUG_MSG \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" @@ -79,12 +76,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, base, base + size); } - if (debug_print) { - pr_debug("After WB checking\n"); - for (i = 0; i < nr_range; i++) - pr_debug("MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end); - } + + Dprintk("After WB checking\n"); + for (i = 0; i < nr_range; i++) + Dprintk("MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); /* Take out UC ranges: */ for (i = 0; i < num_var_ranges; i++) { @@ -112,24 +108,22 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, subtract_range(range, RANGE_NUM, extra_remove_base, extra_remove_base + extra_remove_size); - if (debug_print) { - pr_debug("After UC checking\n"); - for (i = 0; i < RANGE_NUM; i++) { - if (!range[i].end) - continue; - pr_debug("MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end); - } + Dprintk("After UC checking\n"); + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; + + Dprintk("MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); } /* sort the ranges */ nr_range = clean_sort_range(range, RANGE_NUM); - if (debug_print) { - pr_debug("After sorting\n"); - for (i = 0; i < nr_range; i++) - pr_debug("MTRR MAP PFN: %016llx - %016llx\n", - range[i].start, range[i].end); - } + + Dprintk("After sorting\n"); + for (i = 0; i < nr_range; i++) + Dprintk("MTRR MAP PFN: %016llx - %016llx\n", + range[i].start, range[i].end); return nr_range; } @@ -164,13 +158,6 @@ static int __init enable_mtrr_cleanup_setup(char *str) } early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup); -static int __init mtrr_cleanup_debug_setup(char *str) -{ - debug_print = 1; - return 0; -} -early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup); - static void __init set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, unsigned char type) @@ -267,7 +254,7 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk, align = max_align; sizek = 1UL << align; - if (debug_print) { + if (mtrr_debug) { char start_factor = 'K', size_factor = 'K'; unsigned long start_base, size_base; @@ -542,7 +529,7 @@ static void __init print_out_mtrr_range_state(void) start_base = to_size_factor(start_base, &start_factor); type = range_state[i].type; - pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", + Dprintk("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", i, start_base, start_factor, size_base, size_factor, (type == MTRR_TYPE_UNCACHABLE) ? "UC" : @@ -714,7 +701,7 @@ int __init mtrr_cleanup(void) return 0; /* Print original var MTRRs at first, for debugging: */ - pr_debug("original variable MTRRs\n"); + Dprintk("original variable MTRRs\n"); print_out_mtrr_range_state(); memset(range, 0, sizeof(range)); @@ -746,7 +733,7 @@ int __init mtrr_cleanup(void) if (!result[i].bad) { set_var_mtrr_all(); - pr_debug("New variable MTRRs\n"); + Dprintk("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } @@ -766,7 +753,7 @@ int __init mtrr_cleanup(void) mtrr_calc_range_state(chunk_size, gran_size, x_remove_base, x_remove_size, i); - if (debug_print) { + if (mtrr_debug) { mtrr_print_out_one_result(i); pr_info("\n"); } @@ -790,7 +777,7 @@ int __init mtrr_cleanup(void) gran_size <<= 10; x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); set_var_mtrr_all(); - pr_debug("New variable MTRRs\n"); + Dprintk("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } else { diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index f6b426d8be4f..2d6aa5d2e3d7 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -41,7 +41,7 @@ struct cache_map { u64 fixed:1; }; -static bool mtrr_debug; +bool mtrr_debug; static int __init mtrr_param_setup(char *str) { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index ec8670bb5d88..767bf1c71aad 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -332,7 +332,7 @@ static int mtrr_check(unsigned long base, unsigned long size) { if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { pr_warn("size and base must be multiples of 4 kiB\n"); - pr_debug("size: 0x%lx base: 0x%lx\n", size, base); + Dprintk("size: 0x%lx base: 0x%lx\n", size, base); dump_stack(); return -1; } @@ -423,8 +423,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) } } if (reg < 0) { - pr_debug("no MTRR for %lx000,%lx000 found\n", - base, size); + Dprintk("no MTRR for %lx000,%lx000 found\n", base, size); goto out; } } diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 8385d7d3a865..5655f253d929 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -10,6 +10,9 @@ #define MTRR_CHANGE_MASK_VARIABLE 0x02 #define MTRR_CHANGE_MASK_DEFTYPE 0x04 +extern bool mtrr_debug; +#define Dprintk(x...) do { if (mtrr_debug) pr_info(x); } while (0) + extern unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; struct mtrr_ops { -- cgit v1.2.3 From 0f613bfa8268a89be25f2b6b58fc6fe8ccd9a2ba Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 5 Jun 2023 08:01:15 +0100 Subject: locking/atomic: treewide: use raw_atomic*_() Now that we have raw_atomic*_() definitions, there's no need to use arch_atomic*_() definitions outside of the low-level atomic definitions. Move treewide users of arch_atomic*_() over to the equivalent raw_atomic*_(). There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20230605070124.3741859-19-mark.rutland@arm.com --- arch/powerpc/kernel/smp.c | 12 ++++++------ arch/x86/kernel/alternative.c | 4 ++-- arch/x86/kernel/cpu/mce/core.c | 16 ++++++++-------- arch/x86/kernel/nmi.c | 2 +- arch/x86/kernel/pvclock.c | 4 ++-- arch/x86/kvm/x86.c | 2 +- include/asm-generic/bitops/atomic.h | 12 ++++++------ include/asm-generic/bitops/lock.h | 8 ++++---- include/linux/context_tracking.h | 4 ++-- include/linux/context_tracking_state.h | 2 +- include/linux/cpumask.h | 2 +- include/linux/jump_label.h | 2 +- kernel/context_tracking.c | 12 ++++++------ kernel/sched/clock.c | 2 +- 14 files changed, 42 insertions(+), 42 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 265801a3e94c..e8965f18686f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -417,9 +417,9 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags) { raw_local_irq_save(*flags); hard_irq_disable(); - while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { + while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { raw_local_irq_restore(*flags); - spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0); + spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0); raw_local_irq_save(*flags); hard_irq_disable(); } @@ -427,15 +427,15 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags) noinstr static void nmi_ipi_lock(void) { - while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) - spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0); + while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) + spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0); } noinstr static void nmi_ipi_unlock(void) { smp_mb(); - WARN_ON(arch_atomic_read(&__nmi_ipi_lock) != 1); - arch_atomic_set(&__nmi_ipi_lock, 0); + WARN_ON(raw_atomic_read(&__nmi_ipi_lock) != 1); + raw_atomic_set(&__nmi_ipi_lock, 0); } noinstr static void nmi_ipi_unlock_end(unsigned long *flags) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f615e0cb6d93..18f16e93838f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1799,7 +1799,7 @@ struct bp_patching_desc *try_get_desc(void) { struct bp_patching_desc *desc = &bp_desc; - if (!arch_atomic_inc_not_zero(&desc->refs)) + if (!raw_atomic_inc_not_zero(&desc->refs)) return NULL; return desc; @@ -1810,7 +1810,7 @@ static __always_inline void put_desc(void) struct bp_patching_desc *desc = &bp_desc; smp_mb__before_atomic(); - arch_atomic_dec(&desc->refs); + raw_atomic_dec(&desc->refs); } static __always_inline void *text_poke_addr(struct text_poke_loc *tp) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2eec60f50057..ab156e6e7120 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1022,12 +1022,12 @@ static noinstr int mce_start(int *no_way_out) if (!timeout) return ret; - arch_atomic_add(*no_way_out, &global_nwo); + raw_atomic_add(*no_way_out, &global_nwo); /* * Rely on the implied barrier below, such that global_nwo * is updated before mce_callin. */ - order = arch_atomic_inc_return(&mce_callin); + order = raw_atomic_inc_return(&mce_callin); arch_cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); /* Enable instrumentation around calls to external facilities */ @@ -1036,10 +1036,10 @@ static noinstr int mce_start(int *no_way_out) /* * Wait for everyone. */ - while (arch_atomic_read(&mce_callin) != num_online_cpus()) { + while (raw_atomic_read(&mce_callin) != num_online_cpus()) { if (mce_timed_out(&timeout, "Timeout: Not all CPUs entered broadcast exception handler")) { - arch_atomic_set(&global_nwo, 0); + raw_atomic_set(&global_nwo, 0); goto out; } ndelay(SPINUNIT); @@ -1054,7 +1054,7 @@ static noinstr int mce_start(int *no_way_out) /* * Monarch: Starts executing now, the others wait. */ - arch_atomic_set(&mce_executing, 1); + raw_atomic_set(&mce_executing, 1); } else { /* * Subject: Now start the scanning loop one by one in @@ -1062,10 +1062,10 @@ static noinstr int mce_start(int *no_way_out) * This way when there are any shared banks it will be * only seen by one CPU before cleared, avoiding duplicates. */ - while (arch_atomic_read(&mce_executing) < order) { + while (raw_atomic_read(&mce_executing) < order) { if (mce_timed_out(&timeout, "Timeout: Subject CPUs unable to finish machine check processing")) { - arch_atomic_set(&global_nwo, 0); + raw_atomic_set(&global_nwo, 0); goto out; } ndelay(SPINUNIT); @@ -1075,7 +1075,7 @@ static noinstr int mce_start(int *no_way_out) /* * Cache the global no_way_out state. */ - *no_way_out = arch_atomic_read(&global_nwo); + *no_way_out = raw_atomic_read(&global_nwo); ret = order; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 776f4b1e395b..a0c551846b35 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -496,7 +496,7 @@ DEFINE_IDTENTRY_RAW(exc_nmi) */ sev_es_nmi_complete(); if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) - arch_atomic_long_inc(&nsp->idt_calls); + raw_atomic_long_inc(&nsp->idt_calls); if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 56acf53a782a..b3f81379c2fc 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -101,11 +101,11 @@ u64 __pvclock_clocksource_read(struct pvclock_vcpu_time_info *src, bool dowd) * updating at the same time, and one of them could be slightly behind, * making the assumption that last_value always go forward fail to hold. */ - last = arch_atomic64_read(&last_value); + last = raw_atomic64_read(&last_value); do { if (ret <= last) return last; - } while (!arch_atomic64_try_cmpxchg(&last_value, &last, ret)); + } while (!raw_atomic64_try_cmpxchg(&last_value, &last, ret)); return ret; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ceb7c5e9cf9e..ac6f60906810 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13155,7 +13155,7 @@ EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return arch_atomic_read(&kvm->arch.assigned_device_count); + return raw_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index 71ab4ba9c25d..e076e079f6b2 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -15,21 +15,21 @@ static __always_inline void arch_set_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); - arch_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); + raw_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline void arch_clear_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); - arch_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); + raw_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline void arch_change_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); - arch_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); + raw_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline int @@ -39,7 +39,7 @@ arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p) unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); - old = arch_atomic_long_fetch_or(mask, (atomic_long_t *)p); + old = raw_atomic_long_fetch_or(mask, (atomic_long_t *)p); return !!(old & mask); } @@ -50,7 +50,7 @@ arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p) unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); - old = arch_atomic_long_fetch_andnot(mask, (atomic_long_t *)p); + old = raw_atomic_long_fetch_andnot(mask, (atomic_long_t *)p); return !!(old & mask); } @@ -61,7 +61,7 @@ arch_test_and_change_bit(unsigned int nr, volatile unsigned long *p) unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); - old = arch_atomic_long_fetch_xor(mask, (atomic_long_t *)p); + old = raw_atomic_long_fetch_xor(mask, (atomic_long_t *)p); return !!(old & mask); } diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index 630f2f6b9595..40913516e654 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -25,7 +25,7 @@ arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p) if (READ_ONCE(*p) & mask) return 1; - old = arch_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); + old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); return !!(old & mask); } @@ -41,7 +41,7 @@ static __always_inline void arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); - arch_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); + raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); } /** @@ -63,7 +63,7 @@ arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p) p += BIT_WORD(nr); old = READ_ONCE(*p); old &= ~BIT_MASK(nr); - arch_atomic_long_set_release((atomic_long_t *)p, old); + raw_atomic_long_set_release((atomic_long_t *)p, old); } /** @@ -83,7 +83,7 @@ static inline bool arch_clear_bit_unlock_is_negative_byte(unsigned int nr, unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); - old = arch_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p); + old = raw_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p); return !!(old & BIT(7)); } #define arch_clear_bit_unlock_is_negative_byte arch_clear_bit_unlock_is_negative_byte diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d3cbb6c16bab..6e76b9dba00e 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -119,7 +119,7 @@ extern void ct_idle_exit(void); */ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) { - return !(arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX); + return !(raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX); } /* @@ -128,7 +128,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) */ static __always_inline unsigned long ct_state_inc(int incby) { - return arch_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state)); + return raw_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state)); } static __always_inline bool warn_rcu_enter(void) diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index fdd537ea513f..bbff5f7f8803 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -51,7 +51,7 @@ DECLARE_PER_CPU(struct context_tracking, context_tracking); #ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { - return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; + return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; } #endif diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ca736b05ec7b..0d2e2a38b92d 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1071,7 +1071,7 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) */ static __always_inline unsigned int num_online_cpus(void) { - return arch_atomic_read(&__num_online_cpus); + return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 4e968ebadce6..f0a949b7c973 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -257,7 +257,7 @@ extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); static __always_inline int static_key_count(struct static_key *key) { - return arch_atomic_read(&key->enabled); + return raw_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index a09f1c19336a..6ef0b35fc28c 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -510,7 +510,7 @@ void noinstr __ct_user_enter(enum ctx_state state) * In this we case we don't care about any concurrency/ordering. */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) - arch_atomic_set(&ct->state, state); + raw_atomic_set(&ct->state, state); } else { /* * Even if context tracking is disabled on this CPU, because it's outside @@ -527,7 +527,7 @@ void noinstr __ct_user_enter(enum ctx_state state) */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { /* Tracking for vtime only, no concurrent RCU EQS accounting */ - arch_atomic_set(&ct->state, state); + raw_atomic_set(&ct->state, state); } else { /* * Tracking for vtime and RCU EQS. Make sure we don't race @@ -535,7 +535,7 @@ void noinstr __ct_user_enter(enum ctx_state state) * RCU only requires RCU_DYNTICKS_IDX increments to be fully * ordered. */ - arch_atomic_add(state, &ct->state); + raw_atomic_add(state, &ct->state); } } } @@ -630,12 +630,12 @@ void noinstr __ct_user_exit(enum ctx_state state) * In this we case we don't care about any concurrency/ordering. */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) - arch_atomic_set(&ct->state, CONTEXT_KERNEL); + raw_atomic_set(&ct->state, CONTEXT_KERNEL); } else { if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { /* Tracking for vtime only, no concurrent RCU EQS accounting */ - arch_atomic_set(&ct->state, CONTEXT_KERNEL); + raw_atomic_set(&ct->state, CONTEXT_KERNEL); } else { /* * Tracking for vtime and RCU EQS. Make sure we don't race @@ -643,7 +643,7 @@ void noinstr __ct_user_exit(enum ctx_state state) * RCU only requires RCU_DYNTICKS_IDX increments to be fully * ordered. */ - arch_atomic_sub(state, &ct->state); + raw_atomic_sub(state, &ct->state); } } } diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index b5cc2b53464d..71443cff31f0 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -287,7 +287,7 @@ again: clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); - if (!arch_try_cmpxchg64(&scd->clock, &old_clock, clock)) + if (!raw_try_cmpxchg64(&scd->clock, &old_clock, clock)) goto again; return clock; -- cgit v1.2.3 From c35977b00fa76ce5f3fe9afdb9cffda970c943d5 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 15 May 2023 11:35:34 +0000 Subject: x86/MCE/AMD, EDAC/mce_amd: Decode UMC_V2 ECC errors The MI200 (Aldebaran) series of devices introduced a new SMCA bank type for Unified Memory Controllers. The MCE subsystem already has support for this new type. The MCE decoder module will decode the common MCA error information for the new bank type, but it will not pass the information to the AMD64 EDAC module for detailed memory error decoding. Have the MCE decoder module recognize the new bank type as an SMCA UMC memory error and pass the MCA information to AMD64 EDAC. Signed-off-by: Yazen Ghannam Co-developed-by: Muralidhara M K Signed-off-by: Muralidhara M K Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230515113537.1052146-3-muralimk@amd.com --- arch/x86/kernel/cpu/mce/amd.c | 6 ++++-- drivers/edac/mce_amd.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 0b971f974096..5e74610b39e7 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -715,11 +715,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) bool amd_mce_is_memory_error(struct mce *m) { + enum smca_bank_types bank_type; /* ErrCodeExt[20:16] */ u8 xec = (m->status >> 16) & 0x1f; + bank_type = smca_get_bank_type(m->extcpu, m->bank); if (mce_flags.smca) - return smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC && xec == 0x0; + return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0; return m->bank == 4 && xec == 0x8; } @@ -1050,7 +1052,7 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol if (bank_type >= N_SMCA_BANK_TYPES) return NULL; - if (b && bank_type == SMCA_UMC) { + if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; return NULL; diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index cc5c63feb26a..9215c06783df 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -1186,7 +1186,8 @@ static void decode_smca_error(struct mce *m) if (xec < smca_mce_descs[bank_type].num_descs) pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]); - if (bank_type == SMCA_UMC && xec == 0 && decode_dram_ecc) + if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && + xec == 0 && decode_dram_ecc) decode_dram_ecc(topology_die_id(m->extcpu), m); } -- cgit v1.2.3 From c45c06d4ae63a0714efbfa435c5a8f64a5f35b9b Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Wed, 19 Apr 2023 14:50:13 +0200 Subject: x86/resctrl: Factor rdtgroup lock for multi-file ops rdtgroup_kn_lock_live() can only release a kernfs reference for a single file before waiting on the rdtgroup_mutex, limiting its usefulness for operations on multiple files, such as rename. Factor the work needed to respectively break and unbreak active protection on an individual file into rdtgroup_kn_{get,put}(). No functional change. Signed-off-by: Peter Newman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lore.kernel.org/r/20230419125015.693566-2-peternewman@google.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 35 +++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 61cdd9b1bb6d..653d258841db 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2305,6 +2305,26 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) } } +static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn) +{ + atomic_inc(&rdtgrp->waitcount); + kernfs_break_active_protection(kn); +} + +static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn) +{ + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + kernfs_unbreak_active_protection(kn); + rdtgroup_remove(rdtgrp); + } else { + kernfs_unbreak_active_protection(kn); + } +} + struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) { struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); @@ -2312,8 +2332,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) if (!rdtgrp) return NULL; - atomic_inc(&rdtgrp->waitcount); - kernfs_break_active_protection(kn); + rdtgroup_kn_get(rdtgrp, kn); mutex_lock(&rdtgroup_mutex); @@ -2332,17 +2351,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) return; mutex_unlock(&rdtgroup_mutex); - - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || - rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) - rdtgroup_pseudo_lock_remove(rdtgrp); - kernfs_unbreak_active_protection(kn); - rdtgroup_remove(rdtgrp); - } else { - kernfs_unbreak_active_protection(kn); - } + rdtgroup_kn_put(rdtgrp, kn); } static int mkdir_mondata_all(struct kernfs_node *parent_kn, -- cgit v1.2.3 From 8da2b938eb7e2ef407b8ef99def12e3054a99645 Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Wed, 19 Apr 2023 14:50:14 +0200 Subject: x86/resctrl: Implement rename op for mon groups To change the resources allocated to a large group of tasks, such as an application container, a container manager must write all of the tasks' IDs into the tasks file interface of the new control group. This is challenging when the container's task list is always changing. In addition, if the container manager is using monitoring groups to separately track the bandwidth of containers assigned to the same control group, when moving a container, it must first move the container's tasks to the default monitoring group of the new control group before it can move these tasks into the container's replacement monitoring group under the destination control group. This is undesirable because it makes bandwidth usage during the move unattributable to the correct tasks and resets monitoring event counters and cache usage information for the group. Implement the rename operation only for resctrlfs monitor groups to enable users to move a monitoring group from one control group to another. This effects a change in resources allocated to all the tasks in the monitoring group while otherwise leaving the monitoring data intact. Signed-off-by: Peter Newman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lore.kernel.org/r/20230419125015.693566-3-peternewman@google.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 128 +++++++++++++++++++++++++++++++++ 1 file changed, 128 insertions(+) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 653d258841db..725344048f85 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3518,6 +3518,133 @@ out: return ret; } +/** + * mongrp_reparent() - replace parent CTRL_MON group of a MON group + * @rdtgrp: the MON group whose parent should be replaced + * @new_prdtgrp: replacement parent CTRL_MON group for @rdtgrp + * @cpus: cpumask provided by the caller for use during this call + * + * Replaces the parent CTRL_MON group for a MON group, resulting in all member + * tasks' CLOSID immediately changing to that of the new parent group. + * Monitoring data for the group is unaffected by this operation. + */ +static void mongrp_reparent(struct rdtgroup *rdtgrp, + struct rdtgroup *new_prdtgrp, + cpumask_var_t cpus) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + + WARN_ON(rdtgrp->type != RDTMON_GROUP); + WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP); + + /* Nothing to do when simply renaming a MON group. */ + if (prdtgrp == new_prdtgrp) + return; + + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_move_tail(&rdtgrp->mon.crdtgrp_list, + &new_prdtgrp->mon.crdtgrp_list); + + rdtgrp->mon.parent = new_prdtgrp; + rdtgrp->closid = new_prdtgrp->closid; + + /* Propagate updated closid to all tasks in this group. */ + rdt_move_group_tasks(rdtgrp, rdtgrp, cpus); + + update_closid_rmid(cpus, NULL); +} + +static int rdtgroup_rename(struct kernfs_node *kn, + struct kernfs_node *new_parent, const char *new_name) +{ + struct rdtgroup *new_prdtgrp; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret; + + rdtgrp = kernfs_to_rdtgroup(kn); + new_prdtgrp = kernfs_to_rdtgroup(new_parent); + if (!rdtgrp || !new_prdtgrp) + return -ENOENT; + + /* Release both kernfs active_refs before obtaining rdtgroup mutex. */ + rdtgroup_kn_get(rdtgrp, kn); + rdtgroup_kn_get(new_prdtgrp, new_parent); + + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + /* + * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if + * either kernfs_node is a file. + */ + if (kernfs_type(kn) != KERNFS_DIR || + kernfs_type(new_parent) != KERNFS_DIR) { + rdt_last_cmd_puts("Source and destination must be directories"); + ret = -EPERM; + goto out; + } + + if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) { + ret = -ENOENT; + goto out; + } + + if (rdtgrp->type != RDTMON_GROUP || !kn->parent || + !is_mon_groups(kn->parent, kn->name)) { + rdt_last_cmd_puts("Source must be a MON group\n"); + ret = -EPERM; + goto out; + } + + if (!is_mon_groups(new_parent, new_name)) { + rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n"); + ret = -EPERM; + goto out; + } + + /* + * If the MON group is monitoring CPUs, the CPUs must be assigned to the + * current parent CTRL_MON group and therefore cannot be assigned to + * the new parent, making the move illegal. + */ + if (!cpumask_empty(&rdtgrp->cpu_mask) && + rdtgrp->mon.parent != new_prdtgrp) { + rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n"); + ret = -EPERM; + goto out; + } + + /* + * Allocate the cpumask for use in mongrp_reparent() to avoid the + * possibility of failing to allocate it after kernfs_rename() has + * succeeded. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) { + ret = -ENOMEM; + goto out; + } + + /* + * Perform all input validation and allocations needed to ensure + * mongrp_reparent() will succeed before calling kernfs_rename(), + * otherwise it would be necessary to revert this call if + * mongrp_reparent() failed. + */ + ret = kernfs_rename(kn, new_parent, new_name); + if (!ret) + mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask); + + free_cpumask_var(tmpmask); + +out: + mutex_unlock(&rdtgroup_mutex); + rdtgroup_kn_put(rdtgrp, kn); + rdtgroup_kn_put(new_prdtgrp, new_parent); + return ret; +} + static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) @@ -3535,6 +3662,7 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { .mkdir = rdtgroup_mkdir, .rmdir = rdtgroup_rmdir, + .rename = rdtgroup_rename, .show_options = rdtgroup_show_options, }; -- cgit v1.2.3 From 54d020692b342f7bd02d7f5795fb5c401caecfcc Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 17 May 2023 20:25:33 +0100 Subject: mm/gup: remove unused vmas parameter from get_user_pages() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "remove the vmas parameter from GUP APIs", v6. (pin_/get)_user_pages[_remote]() each provide an optional output parameter for an array of VMA objects associated with each page in the input range. These provide the means for VMAs to be returned, as long as mm->mmap_lock is never released during the GUP operation (i.e. the internal flag FOLL_UNLOCKABLE is not specified). In addition, these VMAs can only be accessed with the mmap_lock held and become invalidated the moment it is released. The vast majority of invocations do not use this functionality and of those that do, all but one case retrieve a single VMA to perform checks upon. It is not egregious in the single VMA cases to simply replace the operation with a vma_lookup(). In these cases we duplicate the (fast) lookup on a slow path already under the mmap_lock, abstracted to a new get_user_page_vma_remote() inline helper function which also performs error checking and reference count maintenance. The special case is io_uring, where io_pin_pages() specifically needs to assert that the VMAs underlying the range do not result in broken long-term GUP file-backed mappings. As GUP now internally asserts that FOLL_LONGTERM mappings are not file-backed in a broken fashion (i.e. requiring dirty tracking) - as implemented in "mm/gup: disallow FOLL_LONGTERM GUP-nonfast writing to file-backed mappings" - this logic is no longer required and so we can simply remove it altogether from io_uring. Eliminating the vmas parameter eliminates an entire class of danging pointer errors that might have occured should the lock have been incorrectly released. In addition, the API is simplified and now clearly expresses what it is intended for - applying the specified GUP flags and (if pinning) returning pinned pages. This change additionally opens the door to further potential improvements in GUP and the possible marrying of disparate code paths. I have run this series against gup_test with no issues. Thanks to Matthew Wilcox for suggesting this refactoring! This patch (of 6): No invocation of get_user_pages() use the vmas parameter, so remove it. The GUP API is confusing and caveated. Recent changes have done much to improve that, however there is more we can do. Exporting vmas is a prime target as the caller has to be extremely careful to preclude their use after the mmap_lock has expired or otherwise be left with dangling pointers. Removing the vmas parameter focuses the GUP functions upon their primary purpose - pinning (and outputting) pages as well as performing the actions implied by the input flags. This is part of a patch series aiming to remove the vmas parameter altogether. Link: https://lkml.kernel.org/r/cover.1684350871.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/589e0c64794668ffc799651e8d85e703262b1e9d.1684350871.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Suggested-by: Matthew Wilcox (Oracle) Acked-by: Greg Kroah-Hartman Acked-by: David Hildenbrand Reviewed-by: Jason Gunthorpe Acked-by: Christian König (for radeon parts) Acked-by: Jarkko Sakkinen Reviewed-by: Christoph Hellwig Acked-by: Sean Christopherson (KVM) Cc: Catalin Marinas Cc: Dennis Dalessandro Cc: Janosch Frank Cc: Jens Axboe Cc: Sakari Ailus Signed-off-by: Andrew Morton --- arch/x86/kernel/cpu/sgx/ioctl.c | 2 +- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/misc/sgi-gru/grufault.c | 2 +- include/linux/mm.h | 3 +-- mm/gup.c | 9 +++------ mm/gup_test.c | 5 ++--- virt/kvm/kvm_main.c | 2 +- 7 files changed, 10 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 21ca0a831b70..5d390df21440 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -214,7 +214,7 @@ static int __sgx_encl_add_page(struct sgx_encl *encl, if (!(vma->vm_flags & VM_MAYEXEC)) return -EACCES; - ret = get_user_pages(src, 1, 0, &src_page, NULL); + ret = get_user_pages(src, 1, 0, &src_page); if (ret < 1) return -EFAULT; diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 2220cdf6a3f6..3a9db030f98f 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -359,7 +359,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_device *bdev, struct ttm_tt *ttm struct page **pages = ttm->pages + pinned; r = get_user_pages(userptr, num_pages, write ? FOLL_WRITE : 0, - pages, NULL); + pages); if (r < 0) goto release_pages; diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c index b836936e9747..378cf02a2aa1 100644 --- a/drivers/misc/sgi-gru/grufault.c +++ b/drivers/misc/sgi-gru/grufault.c @@ -185,7 +185,7 @@ static int non_atomic_pte_lookup(struct vm_area_struct *vma, #else *pageshift = PAGE_SHIFT; #endif - if (get_user_pages(vaddr, 1, write ? FOLL_WRITE : 0, &page, NULL) <= 0) + if (get_user_pages(vaddr, 1, write ? FOLL_WRITE : 0, &page) <= 0) return -EFAULT; *paddr = page_to_phys(page); put_page(page); diff --git a/include/linux/mm.h b/include/linux/mm.h index 6d7e03d83da7..6336253c18e2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2369,8 +2369,7 @@ long pin_user_pages_remote(struct mm_struct *mm, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas); + unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); diff --git a/mm/gup.c b/mm/gup.c index e19b06a66229..21daeee5f163 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2251,8 +2251,6 @@ long get_user_pages_remote(struct mm_struct *mm, * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to @@ -2260,16 +2258,15 @@ long get_user_pages_remote(struct mm_struct *mm, * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas) + unsigned int gup_flags, struct page **pages) { int locked = 1; - if (!is_valid_gup_args(pages, vmas, NULL, &gup_flags, FOLL_TOUCH)) + if (!is_valid_gup_args(pages, NULL, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, - vmas, &locked, gup_flags); + NULL, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/gup_test.c b/mm/gup_test.c index 8ae7307a1bb6..9ba8ea23f84e 100644 --- a/mm/gup_test.c +++ b/mm/gup_test.c @@ -139,8 +139,7 @@ static int __gup_test_ioctl(unsigned int cmd, pages + i); break; case GUP_BASIC_TEST: - nr = get_user_pages(addr, nr, gup->gup_flags, pages + i, - NULL); + nr = get_user_pages(addr, nr, gup->gup_flags, pages + i); break; case PIN_FAST_BENCHMARK: nr = pin_user_pages_fast(addr, nr, gup->gup_flags, @@ -161,7 +160,7 @@ static int __gup_test_ioctl(unsigned int cmd, pages + i, NULL); else nr = get_user_pages(addr, nr, gup->gup_flags, - pages + i, NULL); + pages + i); break; default: ret = -EINVAL; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 479802a892d4..51e4882d0873 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2477,7 +2477,7 @@ static inline int check_user_page_hwpoison(unsigned long addr) { int rc, flags = FOLL_HWPOISON | FOLL_WRITE; - rc = get_user_pages(addr, 1, flags, NULL, NULL); + rc = get_user_pages(addr, 1, flags, NULL); return rc == -EHWPOISON; } -- cgit v1.2.3 From a32b0f0db3f396f1c9be2fe621e77c09ec3d8e7d Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 2 May 2023 19:53:50 +0200 Subject: x86/microcode/AMD: Load late on both threads too Do the same as early loading - load on both threads. Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/20230605141332.25948-1-bp@alien8.de --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index f14f4ea0b537..87208e46f7ed 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -700,7 +700,7 @@ static enum ucode_state apply_microcode_amd(int cpu) rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); /* need to apply patch? */ - if (rev >= mc_amd->hdr.patch_id) { + if (rev > mc_amd->hdr.patch_id) { ret = UCODE_OK; goto out; } -- cgit v1.2.3 From 1e327963cfab0e02eeeb0331178d6c353c959cd6 Mon Sep 17 00:00:00 2001 From: Jakob Koschel Date: Wed, 1 Mar 2023 12:17:29 +0100 Subject: x86/sgx: Avoid using iterator after loop in sgx_mmu_notifier_release() If &encl_mm->encl->mm_list does not contain the searched 'encl_mm', 'tmp' will not point to a valid sgx_encl_mm struct. Linus proposed to avoid any use of the list iterator variable after the loop, in the attempt to move the list iterator variable declaration into the macro to avoid any potential misuse after the loop. Using it in a pointer comparison after the loop is undefined behavior and should be omitted if possible, see Link tag. Instead, just use a 'found' boolean to indicate if an element was found. [ bp: Massage, fix typos. ] Signed-off-by: Jakob Koschel Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Jarkko Sakkinen Acked-by: Dave Hansen Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ Link: https://lore.kernel.org/r/20230206-sgx-use-after-iter-v2-1-736ca621adc3@gmail.com --- arch/x86/kernel/cpu/sgx/encl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 2a0e90fe2abc..91fa70e51004 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -755,6 +755,7 @@ static void sgx_mmu_notifier_release(struct mmu_notifier *mn, { struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier); struct sgx_encl_mm *tmp = NULL; + bool found = false; /* * The enclave itself can remove encl_mm. Note, objects can't be moved @@ -764,12 +765,13 @@ static void sgx_mmu_notifier_release(struct mmu_notifier *mn, list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) { if (tmp == encl_mm) { list_del_rcu(&encl_mm->list); + found = true; break; } } spin_unlock(&encl_mm->encl->mm_lock); - if (tmp == encl_mm) { + if (found) { synchronize_srcu(&encl_mm->encl->srcu); mmu_notifier_put(mn); } -- cgit v1.2.3 From 7c7077a72674402654f3291354720cd73cdf649e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:24 +0200 Subject: x86/cpu: Switch to arch_cpu_finalize_init() check_bugs() is a dumping ground for finalizing the CPU bringup. Only parts of it has to do with actual CPU bugs. Split it apart into arch_cpu_finalize_init() and cpu_select_mitigations(). Fixup the bogus 32bit comments while at it. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230613224545.019583869@linutronix.de --- arch/x86/Kconfig | 1 + arch/x86/include/asm/bugs.h | 2 -- arch/x86/kernel/cpu/bugs.c | 51 +----------------------------------------- arch/x86/kernel/cpu/common.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/cpu.h | 1 + 5 files changed, 56 insertions(+), 52 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 53bab123a8ee..e8ebafabd099 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -71,6 +71,7 @@ config X86 select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 92ae28389940..f25ca2d709d4 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -4,8 +4,6 @@ #include -extern void check_bugs(void); - #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) int ppro_with_ram_bug(void); #else diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 182af64387d0..9e2a91830f72 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,7 +9,6 @@ * - Andrew D. Balsa (code cleanup). */ #include -#include #include #include #include @@ -27,8 +26,6 @@ #include #include #include -#include -#include #include #include #include @@ -125,21 +122,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); -void __init check_bugs(void) +void __init cpu_select_mitigations(void) { - identify_boot_cpu(); - - /* - * identify_boot_cpu() initialized SMT support information, let the - * core code know. - */ - cpu_smt_check_topology(); - - if (!IS_ENABLED(CONFIG_SMP)) { - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); - } - /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD @@ -176,39 +160,6 @@ void __init check_bugs(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); - - arch_smt_update(); - -#ifdef CONFIG_X86_32 - /* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); - - init_utsname()->machine[1] = - '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); - - fpu__init_check_bugs(); -#else /* CONFIG_X86_64 */ - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -#endif } /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 80710a68ef7d..18612e5e757c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -19,11 +19,14 @@ #include #include #include +#include #include #include #include #include +#include +#include #include #include #include @@ -59,6 +62,7 @@ #include #include #include +#include #include #include #include @@ -2362,3 +2366,52 @@ void arch_smt_update(void) /* Check whether IPI broadcasting can be enabled */ apic_smt_update(); } + +void __init arch_cpu_finalize_init(void) +{ + identify_boot_cpu(); + + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + cpu_select_mitigations(); + + arch_smt_update(); + + if (IS_ENABLED(CONFIG_X86_32)) { + /* + * Check whether this is a real i386 which is not longer + * supported and fixup the utsname. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + } + + alternative_instructions(); + + if (IS_ENABLED(CONFIG_X86_64)) { + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); + } else { + fpu__init_check_bugs(); + } +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index f97b0fe13da8..1c44630d4789 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -79,6 +79,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); -- cgit v1.2.3 From 439e17576eb47f26b78c5bbc72e344d4206d2327 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:41 +0200 Subject: init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init() Invoke the X86ism mem_encrypt_init() from X86 arch_cpu_finalize_init() and remove the weak fallback from the core code. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.670360645@linutronix.de --- arch/x86/include/asm/mem_encrypt.h | 7 ++++--- arch/x86/kernel/cpu/common.c | 11 +++++++++++ init/main.c | 13 ------------- 3 files changed, 15 insertions(+), 16 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index b7126701574c..98ce265f2e33 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -51,6 +51,8 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +void __init mem_encrypt_init(void); + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -83,13 +85,12 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline void mem_encrypt_init(void) { } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void add_encrypt_protection_map(void); /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 18612e5e757c..5ee8b31ef16c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -2414,4 +2415,14 @@ void __init arch_cpu_finalize_init(void) } else { fpu__init_check_bugs(); } + + /* + * This needs to be called before any devices perform DMA + * operations that might use the SWIOTLB bounce buffers. It will + * mark the bounce buffers as decrypted so that their usage will + * not cause "plain-text" data to be decrypted when accessed. It + * must be called after late_time_init() so that Hyper-V x86/x64 + * hypercalls work when the SWIOTLB bounce buffers are decrypted. + */ + mem_encrypt_init(); } diff --git a/init/main.c b/init/main.c index c968c198555a..32c65f28d84a 100644 --- a/init/main.c +++ b/init/main.c @@ -95,7 +95,6 @@ #include #include #include -#include #include #include #include @@ -786,8 +785,6 @@ void __init __weak thread_stack_cache_init(void) } #endif -void __init __weak mem_encrypt_init(void) { } - void __init __weak poking_init(void) { } void __init __weak pgtable_cache_init(void) { } @@ -1043,16 +1040,6 @@ asmlinkage __visible void __init __no_sanitize_address __noreturn start_kernel(v arch_cpu_finalize_init(); - /* - * This needs to be called before any devices perform DMA - * operations that might use the SWIOTLB bounce buffers. It will - * mark the bounce buffers as decrypted so that their usage will - * not cause "plain-text" data to be decrypted when accessed. It - * must be called after late_time_init() so that Hyper-V x86/x64 - * hypercalls work when the SWIOTLB bounce buffers are decrypted. - */ - mem_encrypt_init(); - pid_idr_init(); anon_vma_init(); #ifdef CONFIG_X86 -- cgit v1.2.3 From 54d9a91a3d6713d1332e93be13b4eaf0fa54349d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:42 +0200 Subject: x86/init: Initialize signal frame size late No point in doing this during really early boot. Move it to an early initcall so that it is set up before possible user mode helpers are started during device initialization. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.727330699@linutronix.de --- arch/x86/include/asm/sigframe.h | 2 -- arch/x86/kernel/cpu/common.c | 3 --- arch/x86/kernel/signal.c | 4 +++- 3 files changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 5b1ed650b124..84eab2724875 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -85,6 +85,4 @@ struct rt_sigframe_x32 { #endif /* CONFIG_X86_64 */ -void __init init_sigframe_size(void); - #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5ee8b31ef16c..b8a4db151209 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -64,7 +64,6 @@ #include #include #include -#include #include #include @@ -1607,8 +1606,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) fpu__init_system(c); - init_sigframe_size(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 004cb30b7419..cfeec3ee877e 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -182,7 +182,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; -void __init init_sigframe_size(void) +static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); @@ -194,7 +194,9 @@ void __init init_sigframe_size(void) max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); + return 0; } +early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { -- cgit v1.2.3 From 1f34bb2a24643e0087652d81078e4f616562738d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:43 +0200 Subject: x86/fpu: Remove cpuinfo argument from init functions Nothing in the call chain requires it Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.783704297@linutronix.de --- arch/x86/include/asm/fpu/api.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/fpu/init.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 503a577814b2..b475d9a582b8 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -109,7 +109,7 @@ extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); -extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b8a4db151209..2807e5b01d59 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1604,7 +1604,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(c); + fpu__init_system(); #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 851eb13edc01..5001df943828 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static void fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { @@ -211,10 +211,10 @@ static void __init fpu__init_system_xstate_size_legacy(void) * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ -void __init fpu__init_system(struct cpuinfo_x86 *c) +void __init fpu__init_system(void) { fpstate_reset(¤t->thread.fpu); - fpu__init_system_early_generic(c); + fpu__init_system_early_generic(); /* * The FPU has to be operational for some of the -- cgit v1.2.3 From b81fac906a8f9e682e513ddd95697ec7a20878d4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:46 +0200 Subject: x86/fpu: Move FPU initialization into arch_cpu_finalize_init() Initializing the FPU during the early boot process is a pointless exercise. Early boot is convoluted and fragile enough. Nothing requires that the FPU is set up early. It has to be initialized before fork_init() because the task_struct size depends on the FPU register buffer size. Move the initialization to arch_cpu_finalize_init() which is the perfect place to do so. No functional change. This allows to remove quite some of the custom early command line parsing, but that's subject to the next installment. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.902376621@linutronix.de --- arch/x86/kernel/cpu/common.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/cpu') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2807e5b01d59..46ebdd60fd96 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1604,8 +1604,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says @@ -2287,8 +2285,6 @@ void cpu_init(void) doublefault_init_cpu_tss(); - fpu__init_cpu(); - if (is_uv_system()) uv_cpu_init(); @@ -2304,6 +2300,7 @@ void cpu_init_secondary(void) */ cpu_init_exception_handling(); cpu_init(); + fpu__init_cpu(); } #endif @@ -2396,6 +2393,13 @@ void __init arch_cpu_finalize_init(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); } + /* + * Must be before alternatives because it might set or clear + * feature bits. + */ + fpu__init_system(); + fpu__init_cpu(); + alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { -- cgit v1.2.3