Merge branch 'akpm' (patches from Andrew)
Merge misc fixes from Andrew Morton:
"16 fixes"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
mm/memblock.c: fix a typo in __next_mem_pfn_range() comments
mm, page_alloc: check for max order in hot path
scripts/spdxcheck.py: make python3 compliant
tmpfs: make lseek(SEEK_DATA/SEK_HOLE) return ENXIO with a negative offset
lib/ubsan.c: don't mark __ubsan_handle_builtin_unreachable as noreturn
mm/vmstat.c: fix NUMA statistics updates
mm/gup.c: fix follow_page_mask() kerneldoc comment
ocfs2: free up write context when direct IO failed
scripts/faddr2line: fix location of start_kernel in comment
mm: don't reclaim inodes with many attached pages
mm, memory_hotplug: check zone_movable in has_unmovable_pages
mm/swapfile.c: use kvzalloc for swap_info_struct allocation
MAINTAINERS: update OMAP MMC entry
hugetlbfs: fix kernel BUG at fs/hugetlbfs/inode.c:444!
kernel/sched/psi.c: simplify cgroup_move_task()
z3fold: fix possible reclaim races
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 0d28924..775cac3 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -111,6 +111,7 @@
#include <linux/kernel.h>
extern unsigned int processor_id;
+struct proc_info_list *lookup_processor(u32 midr);
#ifdef CONFIG_CPU_CP15
#define read_cpuid(reg) \
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index e25f439..e1b6f28 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -23,7 +23,7 @@
/*
* Don't change this structure - ASM code relies on it.
*/
-extern struct processor {
+struct processor {
/* MISC
* get data abort address/flags
*/
@@ -79,9 +79,13 @@
unsigned int suspend_size;
void (*do_suspend)(void *);
void (*do_resume)(void *);
-} processor;
+};
#ifndef MULTI_CPU
+static inline void init_proc_vtable(const struct processor *p)
+{
+}
+
extern void cpu_proc_init(void);
extern void cpu_proc_fin(void);
extern int cpu_do_idle(void);
@@ -98,17 +102,50 @@
extern void cpu_do_suspend(void *);
extern void cpu_do_resume(void *);
#else
-#define cpu_proc_init processor._proc_init
-#define cpu_proc_fin processor._proc_fin
-#define cpu_reset processor.reset
-#define cpu_do_idle processor._do_idle
-#define cpu_dcache_clean_area processor.dcache_clean_area
-#define cpu_set_pte_ext processor.set_pte_ext
-#define cpu_do_switch_mm processor.switch_mm
-/* These three are private to arch/arm/kernel/suspend.c */
-#define cpu_do_suspend processor.do_suspend
-#define cpu_do_resume processor.do_resume
+extern struct processor processor;
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+#include <linux/smp.h>
+/*
+ * This can't be a per-cpu variable because we need to access it before
+ * per-cpu has been initialised. We have a couple of functions that are
+ * called in a pre-emptible context, and so can't use smp_processor_id()
+ * there, hence PROC_TABLE(). We insist in init_proc_vtable() that the
+ * function pointers for these are identical across all CPUs.
+ */
+extern struct processor *cpu_vtable[];
+#define PROC_VTABLE(f) cpu_vtable[smp_processor_id()]->f
+#define PROC_TABLE(f) cpu_vtable[0]->f
+static inline void init_proc_vtable(const struct processor *p)
+{
+ unsigned int cpu = smp_processor_id();
+ *cpu_vtable[cpu] = *p;
+ WARN_ON_ONCE(cpu_vtable[cpu]->dcache_clean_area !=
+ cpu_vtable[0]->dcache_clean_area);
+ WARN_ON_ONCE(cpu_vtable[cpu]->set_pte_ext !=
+ cpu_vtable[0]->set_pte_ext);
+}
+#else
+#define PROC_VTABLE(f) processor.f
+#define PROC_TABLE(f) processor.f
+static inline void init_proc_vtable(const struct processor *p)
+{
+ processor = *p;
+}
+#endif
+
+#define cpu_proc_init PROC_VTABLE(_proc_init)
+#define cpu_check_bugs PROC_VTABLE(check_bugs)
+#define cpu_proc_fin PROC_VTABLE(_proc_fin)
+#define cpu_reset PROC_VTABLE(reset)
+#define cpu_do_idle PROC_VTABLE(_do_idle)
+#define cpu_dcache_clean_area PROC_TABLE(dcache_clean_area)
+#define cpu_set_pte_ext PROC_TABLE(set_pte_ext)
+#define cpu_do_switch_mm PROC_VTABLE(switch_mm)
+
+/* These two are private to arch/arm/kernel/suspend.c */
+#define cpu_do_suspend PROC_VTABLE(do_suspend)
+#define cpu_do_resume PROC_VTABLE(do_resume)
#endif
extern void cpu_resume(void);
diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c
index 7be5113..d41d359 100644
--- a/arch/arm/kernel/bugs.c
+++ b/arch/arm/kernel/bugs.c
@@ -6,8 +6,8 @@
void check_other_bugs(void)
{
#ifdef MULTI_CPU
- if (processor.check_bugs)
- processor.check_bugs();
+ if (cpu_check_bugs)
+ cpu_check_bugs();
#endif
}
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 6e0375e..997b023 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -145,6 +145,9 @@
#endif
.size __mmap_switched_data, . - __mmap_switched_data
+ __FINIT
+ .text
+
/*
* This provides a C-API version of __lookup_processor_type
*/
@@ -156,9 +159,6 @@
ldmfd sp!, {r4 - r6, r9, pc}
ENDPROC(lookup_processor_type)
- __FINIT
- .text
-
/*
* Read processor ID register (CP#15, CR0), and look up in the linker-built
* supported processor list. Note that we can't use the absolute addresses
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index ac7e088..375b13f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -114,6 +114,11 @@
#ifdef MULTI_CPU
struct processor processor __ro_after_init;
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+struct processor *cpu_vtable[NR_CPUS] = {
+ [0] = &processor,
+};
+#endif
#endif
#ifdef MULTI_TLB
struct cpu_tlb_fns cpu_tlb __ro_after_init;
@@ -666,28 +671,33 @@
}
#endif
+/*
+ * locate processor in the list of supported processor types. The linker
+ * builds this table for us from the entries in arch/arm/mm/proc-*.S
+ */
+struct proc_info_list *lookup_processor(u32 midr)
+{
+ struct proc_info_list *list = lookup_processor_type(midr);
+
+ if (!list) {
+ pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n",
+ smp_processor_id(), midr);
+ while (1)
+ /* can't use cpu_relax() here as it may require MMU setup */;
+ }
+
+ return list;
+}
+
static void __init setup_processor(void)
{
- struct proc_info_list *list;
-
- /*
- * locate processor in the list of supported processor
- * types. The linker builds this table for us from the
- * entries in arch/arm/mm/proc-*.S
- */
- list = lookup_processor_type(read_cpuid_id());
- if (!list) {
- pr_err("CPU configuration botched (ID %08x), unable to continue.\n",
- read_cpuid_id());
- while (1);
- }
+ unsigned int midr = read_cpuid_id();
+ struct proc_info_list *list = lookup_processor(midr);
cpu_name = list->cpu_name;
__cpu_architecture = __get_cpu_architecture();
-#ifdef MULTI_CPU
- processor = *list->proc;
-#endif
+ init_proc_vtable(list->proc);
#ifdef MULTI_TLB
cpu_tlb = *list->tlb;
#endif
@@ -699,7 +709,7 @@
#endif
pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
- cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
+ list->cpu_name, midr, midr & 15,
proc_arch[cpu_architecture()], get_cr());
snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 0978282..12a6172 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -42,6 +42,7 @@
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
+#include <asm/procinfo.h>
#include <asm/processor.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
@@ -102,6 +103,30 @@
#endif
}
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+static int secondary_biglittle_prepare(unsigned int cpu)
+{
+ if (!cpu_vtable[cpu])
+ cpu_vtable[cpu] = kzalloc(sizeof(*cpu_vtable[cpu]), GFP_KERNEL);
+
+ return cpu_vtable[cpu] ? 0 : -ENOMEM;
+}
+
+static void secondary_biglittle_init(void)
+{
+ init_proc_vtable(lookup_processor(read_cpuid_id())->proc);
+}
+#else
+static int secondary_biglittle_prepare(unsigned int cpu)
+{
+ return 0;
+}
+
+static void secondary_biglittle_init(void)
+{
+}
+#endif
+
int __cpu_up(unsigned int cpu, struct task_struct *idle)
{
int ret;
@@ -109,6 +134,10 @@
if (!smp_ops.smp_boot_secondary)
return -ENOSYS;
+ ret = secondary_biglittle_prepare(cpu);
+ if (ret)
+ return ret;
+
/*
* We need to tell the secondary core where to find
* its stack and the page tables.
@@ -359,6 +388,8 @@
struct mm_struct *mm = &init_mm;
unsigned int cpu;
+ secondary_biglittle_init();
+
/*
* The identity mapping is uncached (strongly ordered), so
* switch away from it before attempting any exclusive accesses.
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index 5544b82..9a07916 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -52,8 +52,6 @@
case ARM_CPU_PART_CORTEX_A17:
case ARM_CPU_PART_CORTEX_A73:
case ARM_CPU_PART_CORTEX_A75:
- if (processor.switch_mm != cpu_v7_bpiall_switch_mm)
- goto bl_error;
per_cpu(harden_branch_predictor_fn, cpu) =
harden_branch_predictor_bpiall;
spectre_v2_method = "BPIALL";
@@ -61,8 +59,6 @@
case ARM_CPU_PART_CORTEX_A15:
case ARM_CPU_PART_BRAHMA_B15:
- if (processor.switch_mm != cpu_v7_iciallu_switch_mm)
- goto bl_error;
per_cpu(harden_branch_predictor_fn, cpu) =
harden_branch_predictor_iciallu;
spectre_v2_method = "ICIALLU";
@@ -88,11 +84,9 @@
ARM_SMCCC_ARCH_WORKAROUND_1, &res);
if ((int)res.a0 != 0)
break;
- if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu)
- goto bl_error;
per_cpu(harden_branch_predictor_fn, cpu) =
call_hvc_arch_workaround_1;
- processor.switch_mm = cpu_v7_hvc_switch_mm;
+ cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
spectre_v2_method = "hypervisor";
break;
@@ -101,11 +95,9 @@
ARM_SMCCC_ARCH_WORKAROUND_1, &res);
if ((int)res.a0 != 0)
break;
- if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu)
- goto bl_error;
per_cpu(harden_branch_predictor_fn, cpu) =
call_smc_arch_workaround_1;
- processor.switch_mm = cpu_v7_smc_switch_mm;
+ cpu_do_switch_mm = cpu_v7_smc_switch_mm;
spectre_v2_method = "firmware";
break;
@@ -119,11 +111,6 @@
if (spectre_v2_method)
pr_info("CPU%u: Spectre v2: using %s workaround\n",
smp_processor_id(), spectre_v2_method);
- return;
-
-bl_error:
- pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n",
- cpu);
}
#else
static void cpu_v7_spectre_init(void)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 953e316..f4fc1e0 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -313,6 +313,7 @@
arm64_memblock_init();
paging_init();
+ efi_apply_persistent_mem_reservations();
acpi_table_upgrade();
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index e17ab88..cb46d60 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -129,8 +129,15 @@
struct intel_uncore_extra_reg shared_regs[0];
};
-#define UNCORE_BOX_FLAG_INITIATED 0
-#define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */
+/* CFL uncore 8th cbox MSRs */
+#define CFL_UNC_CBO_7_PERFEVTSEL0 0xf70
+#define CFL_UNC_CBO_7_PER_CTR0 0xf76
+
+#define UNCORE_BOX_FLAG_INITIATED 0
+/* event config registers are 8-byte apart */
+#define UNCORE_BOX_FLAG_CTL_OFFS8 1
+/* CFL 8th CBOX has different MSR space */
+#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2
struct uncore_event_desc {
struct kobj_attribute attr;
@@ -297,17 +304,27 @@
static inline
unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
{
- return box->pmu->type->event_ctl +
- (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
- uncore_msr_box_offset(box);
+ if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+ return CFL_UNC_CBO_7_PERFEVTSEL0 +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+ } else {
+ return box->pmu->type->event_ctl +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+ uncore_msr_box_offset(box);
+ }
}
static inline
unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
{
- return box->pmu->type->perf_ctr +
- (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
- uncore_msr_box_offset(box);
+ if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+ return CFL_UNC_CBO_7_PER_CTR0 +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+ } else {
+ return box->pmu->type->perf_ctr +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+ uncore_msr_box_offset(box);
+ }
}
static inline
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 8527c3e..2593b0d 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -15,6 +15,25 @@
#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
+#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f
+#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f
+#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2
+#define PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC 0x3e30
+#define PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC 0x3e18
+#define PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC 0x3ec6
+#define PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC 0x3e31
+#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
+#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
+#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -202,6 +221,10 @@
wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
}
+
+ /* The 8th CBOX has different MSR space */
+ if (box->pmu->pmu_idx == 7)
+ __set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags);
}
static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
@@ -228,7 +251,7 @@
static struct intel_uncore_type skl_uncore_cbox = {
.name = "cbox",
.num_counters = 4,
- .num_boxes = 5,
+ .num_boxes = 8,
.perf_ctr_bits = 44,
.fixed_ctr_bits = 48,
.perf_ctr = SNB_UNC_CBO_0_PER_CTR0,
@@ -569,7 +592,82 @@
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
-
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* end: all zeroes */ },
};
@@ -618,6 +716,25 @@
IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */
IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */
IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */
+ IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */
+ IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */
+ IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */
+ IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */
+ IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */
+ IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */
+ IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */
+ IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */
+ IMC_DEV(CFL_6H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 6 Cores */
+ IMC_DEV(CFL_2S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 2 Cores Desktop */
+ IMC_DEV(CFL_4S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Desktop */
+ IMC_DEV(CFL_6S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Desktop */
+ IMC_DEV(CFL_8S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Desktop */
+ IMC_DEV(CFL_4S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Work Station */
+ IMC_DEV(CFL_6S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Work Station */
+ IMC_DEV(CFL_8S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Work Station */
+ IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
+ IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
+ IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
{ /* end marker */ }
};
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 388a929..1a6a77d 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -265,6 +265,10 @@
(params.mmap & ~PAGE_MASK)));
init_screen_info();
+
+ /* ARM does not permit early mappings to persist across paging_init() */
+ if (IS_ENABLED(CONFIG_ARM))
+ efi_memmap_unmap();
}
static int __init register_gop_device(void)
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 922cfb8..a00934d 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -110,7 +110,7 @@
{
u64 mapsize;
- if (!efi_enabled(EFI_BOOT) || !efi_enabled(EFI_MEMMAP)) {
+ if (!efi_enabled(EFI_BOOT)) {
pr_info("EFI services will not be available.\n");
return 0;
}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 249eb70..fad7c62 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -592,7 +592,11 @@
early_memunmap(tbl, sizeof(*tbl));
}
+ return 0;
+}
+int __init efi_apply_persistent_mem_reservations(void)
+{
if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) {
unsigned long prsv = efi.mem_reserve;
@@ -963,37 +967,44 @@
}
static DEFINE_SPINLOCK(efi_mem_reserve_persistent_lock);
+static struct linux_efi_memreserve *efi_memreserve_root __ro_after_init;
int efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
{
- struct linux_efi_memreserve *rsv, *parent;
+ struct linux_efi_memreserve *rsv;
- if (efi.mem_reserve == EFI_INVALID_TABLE_ADDR)
+ if (!efi_memreserve_root)
return -ENODEV;
- rsv = kmalloc(sizeof(*rsv), GFP_KERNEL);
+ rsv = kmalloc(sizeof(*rsv), GFP_ATOMIC);
if (!rsv)
return -ENOMEM;
- parent = memremap(efi.mem_reserve, sizeof(*rsv), MEMREMAP_WB);
- if (!parent) {
- kfree(rsv);
- return -ENOMEM;
- }
-
rsv->base = addr;
rsv->size = size;
spin_lock(&efi_mem_reserve_persistent_lock);
- rsv->next = parent->next;
- parent->next = __pa(rsv);
+ rsv->next = efi_memreserve_root->next;
+ efi_memreserve_root->next = __pa(rsv);
spin_unlock(&efi_mem_reserve_persistent_lock);
- memunmap(parent);
-
return 0;
}
+static int __init efi_memreserve_root_init(void)
+{
+ if (efi.mem_reserve == EFI_INVALID_TABLE_ADDR)
+ return -ENODEV;
+
+ efi_memreserve_root = memremap(efi.mem_reserve,
+ sizeof(*efi_memreserve_root),
+ MEMREMAP_WB);
+ if (!efi_memreserve_root)
+ return -ENOMEM;
+ return 0;
+}
+early_initcall(efi_memreserve_root_init);
+
#ifdef CONFIG_KEXEC
static int update_efi_random_seed(struct notifier_block *nb,
unsigned long code, void *unused)
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 30ac0c9..3d36142 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -75,6 +75,9 @@
efi_guid_t memreserve_table_guid = LINUX_EFI_MEMRESERVE_TABLE_GUID;
efi_status_t status;
+ if (IS_ENABLED(CONFIG_ARM))
+ return;
+
status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*rsv),
(void **)&rsv);
if (status != EFI_SUCCESS) {
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 8830fa6..0c0d231 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -158,6 +158,10 @@
return efi_status;
}
}
+
+ /* shrink the FDT back to its minimum size */
+ fdt_pack(fdt);
+
return EFI_SUCCESS;
fdt_set_fail:
diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c
index fa2904f..38b686c 100644
--- a/drivers/firmware/efi/memmap.c
+++ b/drivers/firmware/efi/memmap.c
@@ -118,6 +118,9 @@
void __init efi_memmap_unmap(void)
{
+ if (!efi_enabled(EFI_MEMMAP))
+ return;
+
if (!efi.memmap.late) {
unsigned long size;
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index a19d845..8903b9c 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -67,7 +67,7 @@
} \
\
init_completion(&efi_rts_work.efi_rts_comp); \
- INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts); \
+ INIT_WORK(&efi_rts_work.work, efi_call_rts); \
efi_rts_work.arg1 = _arg1; \
efi_rts_work.arg2 = _arg2; \
efi_rts_work.arg3 = _arg3; \
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 845174e..100ce4a 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1167,6 +1167,8 @@
extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
extern bool efi_is_table_address(unsigned long phys_addr);
+
+extern int efi_apply_persistent_mem_reservations(void);
#else
static inline bool efi_enabled(int feature)
{
@@ -1185,6 +1187,11 @@
{
return false;
}
+
+static inline int efi_apply_persistent_mem_reservations(void)
+{
+ return 0;
+}
#endif
extern int efi_status_to_err(efi_status_t status);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3648d03..ac855b2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5674,11 +5674,11 @@
return target;
}
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p);
+static unsigned long cpu_util_without(int cpu, struct task_struct *p);
-static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
{
- return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
+ return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
}
/*
@@ -5738,7 +5738,7 @@
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
- spare_cap = capacity_spare_wake(i, p);
+ spare_cap = capacity_spare_without(i, p);
if (spare_cap > max_spare_cap)
max_spare_cap = spare_cap;
@@ -5889,8 +5889,8 @@
return prev_cpu;
/*
- * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
- * last_update_time.
+ * We need task's util for capacity_spare_without, sync it up to
+ * prev_cpu's last_update_time.
*/
if (!(sd_flag & SD_BALANCE_FORK))
sync_entity_load_avg(&p->se);
@@ -6216,10 +6216,19 @@
}
/*
- * cpu_util_wake: Compute CPU utilization with any contributions from
- * the waking task p removed.
+ * cpu_util_without: compute cpu utilization without any contributions from *p
+ * @cpu: the CPU which utilization is requested
+ * @p: the task which utilization should be discounted
+ *
+ * The utilization of a CPU is defined by the utilization of tasks currently
+ * enqueued on that CPU as well as tasks which are currently sleeping after an
+ * execution on that CPU.
+ *
+ * This method returns the utilization of the specified CPU by discounting the
+ * utilization of the specified task, whenever the task is currently
+ * contributing to the CPU utilization.
*/
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
+static unsigned long cpu_util_without(int cpu, struct task_struct *p)
{
struct cfs_rq *cfs_rq;
unsigned int util;
@@ -6231,7 +6240,7 @@
cfs_rq = &cpu_rq(cpu)->cfs;
util = READ_ONCE(cfs_rq->avg.util_avg);
- /* Discount task's blocked util from CPU's util */
+ /* Discount task's util from CPU's util */
util -= min_t(unsigned int, util, task_util(p));
/*
@@ -6240,14 +6249,14 @@
* a) if *p is the only task sleeping on this CPU, then:
* cpu_util (== task_util) > util_est (== 0)
* and thus we return:
- * cpu_util_wake = (cpu_util - task_util) = 0
+ * cpu_util_without = (cpu_util - task_util) = 0
*
* b) if other tasks are SLEEPING on this CPU, which is now exiting
* IDLE, then:
* cpu_util >= task_util
* cpu_util > util_est (== 0)
* and thus we discount *p's blocked utilization to return:
- * cpu_util_wake = (cpu_util - task_util) >= 0
+ * cpu_util_without = (cpu_util - task_util) >= 0
*
* c) if other tasks are RUNNABLE on that CPU and
* util_est > cpu_util
@@ -6260,8 +6269,33 @@
* covered by the following code when estimated utilization is
* enabled.
*/
- if (sched_feat(UTIL_EST))
- util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued));
+ if (sched_feat(UTIL_EST)) {
+ unsigned int estimated =
+ READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+ /*
+ * Despite the following checks we still have a small window
+ * for a possible race, when an execl's select_task_rq_fair()
+ * races with LB's detach_task():
+ *
+ * detach_task()
+ * p->on_rq = TASK_ON_RQ_MIGRATING;
+ * ---------------------------------- A
+ * deactivate_task() \
+ * dequeue_task() + RaceTime
+ * util_est_dequeue() /
+ * ---------------------------------- B
+ *
+ * The additional check on "current == p" it's required to
+ * properly fix the execl regression and it helps in further
+ * reducing the chances for the above race.
+ */
+ if (unlikely(task_on_rq_queued(p) || current == p)) {
+ estimated -= min_t(unsigned int, estimated,
+ (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+ }
+ util = max(util, estimated);
+ }
/*
* Utilization (estimated) can exceed the CPU capacity, thus let's
