From eec73529a9321616ed13cf732cd21a17eb1a2836 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 10 Mar 2021 08:16:40 +0530 Subject: arch_topology: Rename freq_scale as arch_freq_scale Rename freq_scale to a less generic name, as it will get exported soon for modules. Since x86 already names its own implementation of this as arch_freq_scale, lets stick to that. Suggested-by: Will Deacon Signed-off-by: Viresh Kumar --- arch/arm64/kernel/topology.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index e08a4126453a..aa8d893619ed 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -256,8 +256,8 @@ static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val, * initialized AMU support and enabled invariance. The AMU counters will * keep on working just fine in the absence of the cpufreq driver, and * for the CPUs for which there are no counters available, the last set - * value of freq_scale will remain valid as that is the frequency those - * CPUs are running at. + * value of arch_freq_scale will remain valid as that is the frequency + * those CPUs are running at. */ return 0; @@ -327,7 +327,7 @@ void topology_scale_freq_tick(void) const_cnt - prev_const_cnt); scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); - this_cpu_write(freq_scale, (unsigned long)scale); + this_cpu_write(arch_freq_scale, (unsigned long)scale); } #ifdef CONFIG_ACPI_CPPC_LIB -- cgit v1.2.3 From 01e055c120a46e78650b5f903088badbbdaae9ad Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 10 Mar 2021 08:21:04 +0530 Subject: arch_topology: Allow multiple entities to provide sched_freq_tick() callback This patch attempts to make it generic enough so other parts of the kernel can also provide their own implementation of scale_freq_tick() callback, which is called by the scheduler periodically to update the per-cpu arch_freq_scale variable. The implementations now need to provide 'struct scale_freq_data' for the CPUs for which they have hardware counters available, and a callback gets registered for each possible CPU in a per-cpu variable. The arch specific (or ARM AMU) counters are updated to adapt to this and they take the highest priority if they are available, i.e. they will be used instead of CPPC based counters for example. The special code to rebuild the sched domains, in case invariance status change for the system, is moved out of arm64 specific code and is added to arch_topology.c. Note that this also defines SCALE_FREQ_SOURCE_CPUFREQ but doesn't use it and it is added to show that cpufreq is also acts as source of information for FIE and will be used by default if no other counters are supported for a platform. Reviewed-by: Ionela Voinescu Tested-by: Ionela Voinescu Acked-by: Will Deacon # for arm64 Tested-by: Vincent Guittot Signed-off-by: Viresh Kumar --- arch/arm64/include/asm/topology.h | 10 +--- arch/arm64/kernel/topology.c | 105 ++++++++++++++------------------------ drivers/base/arch_topology.c | 82 +++++++++++++++++++++++++++-- include/linux/arch_topology.h | 14 ++++- 4 files changed, 131 insertions(+), 80 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 3b8dca4eb08d..ec2db3419c41 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -17,17 +17,9 @@ int pcibus_to_node(struct pci_bus *bus); #include void update_freq_counters_refs(void); -void topology_scale_freq_tick(void); - -#ifdef CONFIG_ARM64_AMU_EXTN -/* - * Replace task scheduler's default counter-based - * frequency-invariance scale factor setting. - */ -#define arch_scale_freq_tick topology_scale_freq_tick -#endif /* CONFIG_ARM64_AMU_EXTN */ /* Replace task scheduler's default frequency-invariant accounting */ +#define arch_scale_freq_tick topology_scale_freq_tick #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index aa8d893619ed..4dd14a6620c1 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -199,12 +199,47 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) return 0; } -static DEFINE_STATIC_KEY_FALSE(amu_fie_key); -#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key) +static void amu_scale_freq_tick(void) +{ + u64 prev_core_cnt, prev_const_cnt; + u64 core_cnt, const_cnt, scale; + + prev_const_cnt = this_cpu_read(arch_const_cycles_prev); + prev_core_cnt = this_cpu_read(arch_core_cycles_prev); + + update_freq_counters_refs(); + + const_cnt = this_cpu_read(arch_const_cycles_prev); + core_cnt = this_cpu_read(arch_core_cycles_prev); + + if (unlikely(core_cnt <= prev_core_cnt || + const_cnt <= prev_const_cnt)) + return; + + /* + * /\core arch_max_freq_scale + * scale = ------- * -------------------- + * /\const SCHED_CAPACITY_SCALE + * + * See validate_cpu_freq_invariance_counters() for details on + * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. + */ + scale = core_cnt - prev_core_cnt; + scale *= this_cpu_read(arch_max_freq_scale); + scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, + const_cnt - prev_const_cnt); + + scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); + this_cpu_write(arch_freq_scale, (unsigned long)scale); +} + +static struct scale_freq_data amu_sfd = { + .source = SCALE_FREQ_SOURCE_ARCH, + .set_freq_scale = amu_scale_freq_tick, +}; static void amu_fie_setup(const struct cpumask *cpus) { - bool invariant; int cpu; /* We are already set since the last insmod of cpufreq driver */ @@ -221,25 +256,10 @@ static void amu_fie_setup(const struct cpumask *cpus) cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus); - invariant = topology_scale_freq_invariant(); - - /* We aren't fully invariant yet */ - if (!invariant && !cpumask_equal(amu_fie_cpus, cpu_present_mask)) - return; - - static_branch_enable(&amu_fie_key); + topology_set_scale_freq_source(&amu_sfd, amu_fie_cpus); pr_debug("CPUs[%*pbl]: counters will be used for FIE.", cpumask_pr_args(cpus)); - - /* - * Task scheduler behavior depends on frequency invariance support, - * either cpufreq or counter driven. If the support status changes as - * a result of counter initialisation and use, retrigger the build of - * scheduling domains to ensure the information is propagated properly. - */ - if (!invariant) - rebuild_sched_domains_energy(); } static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val, @@ -283,53 +303,6 @@ static int __init init_amu_fie(void) } core_initcall(init_amu_fie); -bool arch_freq_counters_available(const struct cpumask *cpus) -{ - return amu_freq_invariant() && - cpumask_subset(cpus, amu_fie_cpus); -} - -void topology_scale_freq_tick(void) -{ - u64 prev_core_cnt, prev_const_cnt; - u64 core_cnt, const_cnt, scale; - int cpu = smp_processor_id(); - - if (!amu_freq_invariant()) - return; - - if (!cpumask_test_cpu(cpu, amu_fie_cpus)) - return; - - prev_const_cnt = this_cpu_read(arch_const_cycles_prev); - prev_core_cnt = this_cpu_read(arch_core_cycles_prev); - - update_freq_counters_refs(); - - const_cnt = this_cpu_read(arch_const_cycles_prev); - core_cnt = this_cpu_read(arch_core_cycles_prev); - - if (unlikely(core_cnt <= prev_core_cnt || - const_cnt <= prev_const_cnt)) - return; - - /* - * /\core arch_max_freq_scale - * scale = ------- * -------------------- - * /\const SCHED_CAPACITY_SCALE - * - * See validate_cpu_freq_invariance_counters() for details on - * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. - */ - scale = core_cnt - prev_core_cnt; - scale *= this_cpu_read(arch_max_freq_scale); - scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, - const_cnt - prev_const_cnt); - - scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); - this_cpu_write(arch_freq_scale, (unsigned long)scale); -} - #ifdef CONFIG_ACPI_CPPC_LIB #include diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 2a1cecbde0a4..ebcd2ea3091f 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -21,16 +21,90 @@ #include #include +static DEFINE_PER_CPU(struct scale_freq_data *, sft_data); +static struct cpumask scale_freq_counters_mask; +static bool scale_freq_invariant; + +static bool supports_scale_freq_counters(const struct cpumask *cpus) +{ + return cpumask_subset(cpus, &scale_freq_counters_mask); +} + bool topology_scale_freq_invariant(void) { return cpufreq_supports_freq_invariance() || - arch_freq_counters_available(cpu_online_mask); + supports_scale_freq_counters(cpu_online_mask); } -__weak bool arch_freq_counters_available(const struct cpumask *cpus) +static void update_scale_freq_invariant(bool status) { - return false; + if (scale_freq_invariant == status) + return; + + /* + * Task scheduler behavior depends on frequency invariance support, + * either cpufreq or counter driven. If the support status changes as + * a result of counter initialisation and use, retrigger the build of + * scheduling domains to ensure the information is propagated properly. + */ + if (topology_scale_freq_invariant() == status) { + scale_freq_invariant = status; + rebuild_sched_domains_energy(); + } } + +void topology_set_scale_freq_source(struct scale_freq_data *data, + const struct cpumask *cpus) +{ + struct scale_freq_data *sfd; + int cpu; + + /* + * Avoid calling rebuild_sched_domains() unnecessarily if FIE is + * supported by cpufreq. + */ + if (cpumask_empty(&scale_freq_counters_mask)) + scale_freq_invariant = topology_scale_freq_invariant(); + + for_each_cpu(cpu, cpus) { + sfd = per_cpu(sft_data, cpu); + + /* Use ARCH provided counters whenever possible */ + if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) { + per_cpu(sft_data, cpu) = data; + cpumask_set_cpu(cpu, &scale_freq_counters_mask); + } + } + + update_scale_freq_invariant(true); +} + +void topology_clear_scale_freq_source(enum scale_freq_source source, + const struct cpumask *cpus) +{ + struct scale_freq_data *sfd; + int cpu; + + for_each_cpu(cpu, cpus) { + sfd = per_cpu(sft_data, cpu); + + if (sfd && sfd->source == source) { + per_cpu(sft_data, cpu) = NULL; + cpumask_clear_cpu(cpu, &scale_freq_counters_mask); + } + } + + update_scale_freq_invariant(false); +} + +void topology_scale_freq_tick(void) +{ + struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data); + + if (sfd) + sfd->set_freq_scale(); +} + DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, @@ -47,7 +121,7 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, * want to update the scale factor with information from CPUFREQ. * Instead the scale factor will be updated from arch_scale_freq_tick. */ - if (arch_freq_counters_available(cpus)) + if (supports_scale_freq_counters(cpus)) return; scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq; diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 583af517f123..11e555cfaecb 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -34,7 +34,19 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, unsigned long max_freq); bool topology_scale_freq_invariant(void); -bool arch_freq_counters_available(const struct cpumask *cpus); +enum scale_freq_source { + SCALE_FREQ_SOURCE_CPUFREQ = 0, + SCALE_FREQ_SOURCE_ARCH, +}; + +struct scale_freq_data { + enum scale_freq_source source; + void (*set_freq_scale)(void); +}; + +void topology_scale_freq_tick(void); +void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); +void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); DECLARE_PER_CPU(unsigned long, thermal_pressure); -- cgit v1.2.3 From f5d1499ae2096d7ea301023c4cc54e427300eb0a Mon Sep 17 00:00:00 2001 From: Chris von Recklinghausen Date: Tue, 20 Apr 2021 08:57:39 -0400 Subject: PM: hibernate: x86: Use crc32 instead of md5 for hibernation e820 integrity check Hibernation fails on a system in fips mode because md5 is used for the e820 integrity check and is not available. Use crc32 instead. The check is intended to detect whether the E820 memory map provided by the firmware after cold boot unexpectedly differs from the one that was in use when the hibernation image was created. In this case, the hibernation image cannot be restored, as it may cover memory regions that are no longer available to the OS. A non-cryptographic checksum such as CRC-32 is sufficient to detect such inadvertent deviations. Fixes: 62a03defeabd ("PM / hibernate: Verify the consistent of e820 memory map by md5 digest") Reviewed-by: Eric Biggers Tested-by: Dexuan Cui Reviewed-by: Dexuan Cui Signed-off-by: Chris von Recklinghausen [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/e820.c | 4 +-- arch/x86/power/hibernate.c | 89 ++++++++-------------------------------------- 2 files changed, 16 insertions(+), 77 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 22aad412f965..629c4994f165 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -31,8 +31,8 @@ * - inform the user about the firmware's notion of memory layout * via /sys/firmware/memmap * - * - the hibernation code uses it to generate a kernel-independent MD5 - * fingerprint of the physical memory layout of a system. + * - the hibernation code uses it to generate a kernel-independent CRC32 + * checksum of the physical memory layout of a system. * * - 'e820_table_kexec': a slightly modified (by the kernel) firmware version * passed to us by the bootloader - the major difference between diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index cd3914fc9f3d..e94e0050a583 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -13,8 +13,8 @@ #include #include #include - -#include +#include +#include #include #include @@ -54,95 +54,33 @@ int pfn_is_nosave(unsigned long pfn) return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn; } - -#define MD5_DIGEST_SIZE 16 - struct restore_data_record { unsigned long jump_address; unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; - u8 e820_digest[MD5_DIGEST_SIZE]; + unsigned long e820_checksum; }; -#if IS_BUILTIN(CONFIG_CRYPTO_MD5) /** - * get_e820_md5 - calculate md5 according to given e820 table + * compute_e820_crc32 - calculate crc32 of a given e820 table * * @table: the e820 table to be calculated - * @buf: the md5 result to be stored to + * + * Return: the resulting checksum */ -static int get_e820_md5(struct e820_table *table, void *buf) +static inline u32 compute_e820_crc32(struct e820_table *table) { - struct crypto_shash *tfm; - struct shash_desc *desc; - int size; - int ret = 0; - - tfm = crypto_alloc_shash("md5", 0, 0); - if (IS_ERR(tfm)) - return -ENOMEM; - - desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!desc) { - ret = -ENOMEM; - goto free_tfm; - } - - desc->tfm = tfm; - - size = offsetof(struct e820_table, entries) + + int size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries; - if (crypto_shash_digest(desc, (u8 *)table, size, buf)) - ret = -EINVAL; - - kfree_sensitive(desc); - -free_tfm: - crypto_free_shash(tfm); - return ret; -} - -static int hibernation_e820_save(void *buf) -{ - return get_e820_md5(e820_table_firmware, buf); -} - -static bool hibernation_e820_mismatch(void *buf) -{ - int ret; - u8 result[MD5_DIGEST_SIZE]; - - memset(result, 0, MD5_DIGEST_SIZE); - /* If there is no digest in suspend kernel, let it go. */ - if (!memcmp(result, buf, MD5_DIGEST_SIZE)) - return false; - - ret = get_e820_md5(e820_table_firmware, result); - if (ret) - return true; - - return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; -} -#else -static int hibernation_e820_save(void *buf) -{ - return 0; -} - -static bool hibernation_e820_mismatch(void *buf) -{ - /* If md5 is not builtin for restore kernel, let it go. */ - return false; + return ~crc32_le(~0, (unsigned char const *)table, size); } -#endif #ifdef CONFIG_X86_64 -#define RESTORE_MAGIC 0x23456789ABCDEF01UL +#define RESTORE_MAGIC 0x23456789ABCDEF02UL #else -#define RESTORE_MAGIC 0x12345678UL +#define RESTORE_MAGIC 0x12345679UL #endif /** @@ -179,7 +117,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) */ rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK; - return hibernation_e820_save(rdr->e820_digest); + rdr->e820_checksum = compute_e820_crc32(e820_table_firmware); + return 0; } /** @@ -200,7 +139,7 @@ int arch_hibernation_header_restore(void *addr) jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; - if (hibernation_e820_mismatch(rdr->e820_digest)) { + if (rdr->e820_checksum != compute_e820_crc32(e820_table_firmware)) { pr_crit("Hibernate inconsistent memory map detected!\n"); return -ENODEV; } -- cgit v1.2.3