Commit f0b500ea authored by Lorenzo "Palinuro" Faletra's avatar Lorenzo "Palinuro" Faletra
Browse files

Import Upstream version 4.14.13

parent 2dcbc7be
......@@ -12,8 +12,9 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
... unused hole ...
fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI
fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
vaddr_end for KASLR
fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
fffffe8000000000 - fffffeffffffffff (=39 bits) LDT remap for PTI
ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
... unused hole ...
ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
......@@ -37,13 +38,15 @@ ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
... unused hole ...
ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
... unused hole ...
fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
vaddr_end for KASLR
fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
... unused hole ...
ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
... unused hole ...
ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
... unused hole ...
ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0
ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space
ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space
[fixmap start] - ffffffffff5fffff kernel-internal fixmap range
ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
......@@ -67,9 +70,10 @@ memory window (this size is arbitrary, it can be raised later if needed).
The mappings are not part of any other kernel PGD and are only available
during EFI runtime calls.
The module mapping space size changes based on the CONFIG requirements for the
following fixmap section.
Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
physical memory, vmalloc/ioremap space and virtual memory map are randomized.
Their order is preserved but their base will be offset early at boot time.
Be very careful vs. KASLR when changing anything here. The KASLR address
range must not overlap with anything except the KASAN shadow area, which is
correct as KASAN disables KASLR.
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 14
SUBLEVEL = 12
SUBLEVEL = 13
EXTRAVERSION =
NAME = Petit Gorille
......
......@@ -668,6 +668,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
return 0;
__asm__ __volatile__(
" mov lp_count, %5 \n"
" lp 3f \n"
"1: ldb.ab %3, [%2, 1] \n"
" breq.d %3, 0, 3f \n"
......@@ -684,8 +685,8 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
" .word 1b, 4b \n"
" .previous \n"
: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
: "g"(-EFAULT), "l"(count)
: "memory");
: "g"(-EFAULT), "r"(count)
: "lp_count", "lp_start", "lp_end", "memory");
return res;
}
......
......@@ -12,6 +12,7 @@
for the semaphore. */
#define __PA_LDCW_ALIGNMENT 16
#define __PA_LDCW_ALIGN_ORDER 4
#define __ldcw_align(a) ({ \
unsigned long __ret = (unsigned long) &(a)->lock[0]; \
__ret = (__ret + __PA_LDCW_ALIGNMENT - 1) \
......@@ -29,6 +30,7 @@
ldcd). */
#define __PA_LDCW_ALIGNMENT 4
#define __PA_LDCW_ALIGN_ORDER 2
#define __ldcw_align(a) (&(a)->slock)
#define __LDCW "ldcw,co"
......
......@@ -35,6 +35,7 @@
#include <asm/pgtable.h>
#include <asm/signal.h>
#include <asm/unistd.h>
#include <asm/ldcw.h>
#include <asm/thread_info.h>
#include <linux/linkage.h>
......@@ -46,6 +47,14 @@
#endif
.import pa_tlb_lock,data
.macro load_pa_tlb_lock reg
#if __PA_LDCW_ALIGNMENT > 4
load32 PA(pa_tlb_lock) + __PA_LDCW_ALIGNMENT-1, \reg
depi 0,31,__PA_LDCW_ALIGN_ORDER, \reg
#else
load32 PA(pa_tlb_lock), \reg
#endif
.endm
/* space_to_prot macro creates a prot id from a space id */
......@@ -457,7 +466,7 @@
.macro tlb_lock spc,ptp,pte,tmp,tmp1,fault
#ifdef CONFIG_SMP
cmpib,COND(=),n 0,\spc,2f
load32 PA(pa_tlb_lock),\tmp
load_pa_tlb_lock \tmp
1: LDCW 0(\tmp),\tmp1
cmpib,COND(=) 0,\tmp1,1b
nop
......@@ -480,7 +489,7 @@
/* Release pa_tlb_lock lock. */
.macro tlb_unlock1 spc,tmp
#ifdef CONFIG_SMP
load32 PA(pa_tlb_lock),\tmp
load_pa_tlb_lock \tmp
tlb_unlock0 \spc,\tmp
#endif
.endm
......
......@@ -36,6 +36,7 @@
#include <asm/assembly.h>
#include <asm/pgtable.h>
#include <asm/cache.h>
#include <asm/ldcw.h>
#include <linux/linkage.h>
.text
......@@ -333,8 +334,12 @@ ENDPROC_CFI(flush_data_cache_local)
.macro tlb_lock la,flags,tmp
#ifdef CONFIG_SMP
ldil L%pa_tlb_lock,%r1
ldo R%pa_tlb_lock(%r1),\la
#if __PA_LDCW_ALIGNMENT > 4
load32 pa_tlb_lock + __PA_LDCW_ALIGNMENT-1, \la
depi 0,31,__PA_LDCW_ALIGN_ORDER, \la
#else
load32 pa_tlb_lock, \la
#endif
rsm PSW_SM_I,\flags
1: LDCW 0(\la),\tmp
cmpib,<>,n 0,\tmp,3f
......
......@@ -39,6 +39,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/personality.h>
#include <linux/ptrace.h>
......@@ -183,6 +184,44 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
return 1;
}
/*
* Idle thread support
*
* Detect when running on QEMU with SeaBIOS PDC Firmware and let
* QEMU idle the host too.
*/
int running_on_qemu __read_mostly;
void __cpuidle arch_cpu_idle_dead(void)
{
/* nop on real hardware, qemu will offline CPU. */
asm volatile("or %%r31,%%r31,%%r31\n":::);
}
void __cpuidle arch_cpu_idle(void)
{
local_irq_enable();
/* nop on real hardware, qemu will idle sleep. */
asm volatile("or %%r10,%%r10,%%r10\n":::);
}
static int __init parisc_idle_init(void)
{
const char *marker;
/* check QEMU/SeaBIOS marker in PAGE0 */
marker = (char *) &PAGE0->pad0;
running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
if (!running_on_qemu)
cpu_idle_poll_ctrl(1);
return 0;
}
arch_initcall(parisc_idle_init);
/*
* Copy architecture-specific thread state
*/
......
......@@ -145,6 +145,11 @@ static noinline int bad_area(struct pt_regs *regs, unsigned long address)
return __bad_area(regs, address, SEGV_MAPERR);
}
static noinline int bad_access(struct pt_regs *regs, unsigned long address)
{
return __bad_area(regs, address, SEGV_ACCERR);
}
static int do_sigbus(struct pt_regs *regs, unsigned long address,
unsigned int fault)
{
......@@ -490,7 +495,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
good_area:
if (unlikely(access_error(is_write, is_exec, vma)))
return bad_area(regs, address);
return bad_access(regs, address);
/*
* If for any reason at all we couldn't handle the fault,
......
......@@ -794,11 +794,12 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
if (kvm->arch.use_cmma) {
/*
* Get the last slot. They should be sorted by base_gfn, so the
* last slot is also the one at the end of the address space.
* We have verified above that at least one slot is present.
* Get the first slot. They are reverse sorted by base_gfn, so
* the first slot is also the one at the end of the address
* space. We have verified above that at least one slot is
* present.
*/
ms = slots->memslots + slots->used_slots - 1;
ms = slots->memslots;
/* round up so we only use full longs */
ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
/* allocate enough bytes to store all the bits */
......
......@@ -1009,7 +1009,7 @@ static inline int do_essa(struct kvm_vcpu *vcpu, const int orc)
cbrlo[entries] = gfn << PAGE_SHIFT;
}
if (orc) {
if (orc && gfn < ms->bitmap_size) {
/* increment only if we are really flipping the bit to 1 */
if (!test_and_set_bit(gfn, ms->pgste_bitmap))
atomic64_inc(&ms->dirty_pages);
......
......@@ -5,6 +5,7 @@
#include <asm/cpu_entry_area.h>
#include <asm/perf_event.h>
#include <asm/tlbflush.h>
#include <asm/insn.h>
#include "../perf_event.h"
......@@ -283,20 +284,35 @@ static DEFINE_PER_CPU(void *, insn_buffer);
static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
{
unsigned long start = (unsigned long)cea;
phys_addr_t pa;
size_t msz = 0;
pa = virt_to_phys(addr);
preempt_disable();
for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
cea_set_pte(cea, pa, prot);
/*
* This is a cross-CPU update of the cpu_entry_area, we must shoot down
* all TLB entries for it.
*/
flush_tlb_kernel_range(start, start + size);
preempt_enable();
}
static void ds_clear_cea(void *cea, size_t size)
{
unsigned long start = (unsigned long)cea;
size_t msz = 0;
preempt_disable();
for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
cea_set_pte(cea, 0, PAGE_NONE);
flush_tlb_kernel_range(start, start + size);
preempt_enable();
}
static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
......
......@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
".popsection"
".popsection\n"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
OLDINSTR_2(oldinstr, 1, 2) \
......@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
".popsection"
".popsection\n"
/*
* Alternative instructions for different CPU types or capabilities.
......
......@@ -341,6 +341,6 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */
#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
#endif /* _ASM_X86_CPUFEATURES_H */
......@@ -75,7 +75,13 @@ typedef struct { pteval_t pte; } pte_t;
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
/*
* See Documentation/x86/x86_64/mm.txt for a description of the memory map.
*
* Be very careful vs. KASLR when changing anything here. The KASLR address
* range must not overlap with anything except the KASAN shadow area, which
* is correct as KASAN disables KASLR.
*/
#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
#ifdef CONFIG_X86_5LEVEL
......@@ -88,7 +94,7 @@ typedef struct { pteval_t pte; } pte_t;
# define VMALLOC_SIZE_TB _AC(32, UL)
# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
# define LDT_PGD_ENTRY _AC(-4, UL)
# define LDT_PGD_ENTRY _AC(-3, UL)
# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#endif
......@@ -104,13 +110,13 @@ typedef struct { pteval_t pte; } pte_t;
#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
/* The module sections ends with the start of the fixmap */
#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1)
#define MODULES_END _AC(0xffffffffff000000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
#define ESPFIX_PGD_ENTRY _AC(-2, UL)
#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
#define CPU_ENTRY_AREA_PGD _AC(-3, UL)
#define CPU_ENTRY_AREA_PGD _AC(-4, UL)
#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT)
#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
......
......@@ -22,7 +22,7 @@ obj-y += common.o
obj-y += rdrand.o
obj-y += match.o
obj-y += bugs.o
obj-$(CONFIG_CPU_FREQ) += aperfmperf.o
obj-y += aperfmperf.o
obj-y += cpuid-deps.o
obj-$(CONFIG_PROC_FS) += proc.o
......
......@@ -14,6 +14,8 @@
#include <linux/percpu.h>
#include <linux/smp.h>
#include "cpu.h"
struct aperfmperf_sample {
unsigned int khz;
ktime_t time;
......@@ -24,7 +26,7 @@ struct aperfmperf_sample {
static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
#define APERFMPERF_CACHE_THRESHOLD_MS 10
#define APERFMPERF_REFRESH_DELAY_MS 20
#define APERFMPERF_REFRESH_DELAY_MS 10
#define APERFMPERF_STALE_THRESHOLD_MS 1000
/*
......@@ -38,14 +40,8 @@ static void aperfmperf_snapshot_khz(void *dummy)
u64 aperf, aperf_delta;
u64 mperf, mperf_delta;
struct aperfmperf_sample *s = this_cpu_ptr(&samples);
ktime_t now = ktime_get();
s64 time_delta = ktime_ms_delta(now, s->time);
unsigned long flags;
/* Don't bother re-computing within the cache threshold time. */
if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
return;
local_irq_save(flags);
rdmsrl(MSR_IA32_APERF, aperf);
rdmsrl(MSR_IA32_MPERF, mperf);
......@@ -61,31 +57,68 @@ static void aperfmperf_snapshot_khz(void *dummy)
if (mperf_delta == 0)
return;
s->time = now;
s->time = ktime_get();
s->aperf = aperf;
s->mperf = mperf;
s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
}
/* If the previous iteration was too long ago, discard it. */
if (time_delta > APERFMPERF_STALE_THRESHOLD_MS)
s->khz = 0;
else
s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait)
{
s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu));
/* Don't bother re-computing within the cache threshold time. */
if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
return true;
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait);
/* Return false if the previous iteration was too long ago. */
return time_delta <= APERFMPERF_STALE_THRESHOLD_MS;
}
unsigned int arch_freq_get_on_cpu(int cpu)
unsigned int aperfmperf_get_khz(int cpu)
{
unsigned int khz;
if (!cpu_khz)
return 0;
if (!static_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
return per_cpu(samples.khz, cpu);
}
void arch_freq_prepare_all(void)
{
ktime_t now = ktime_get();
bool wait = false;
int cpu;
if (!cpu_khz)
return;
if (!static_cpu_has(X86_FEATURE_APERFMPERF))
return;
for_each_online_cpu(cpu)
if (!aperfmperf_snapshot_cpu(cpu, now, false))
wait = true;
if (wait)
msleep(APERFMPERF_REFRESH_DELAY_MS);
}
unsigned int arch_freq_get_on_cpu(int cpu)
{
if (!cpu_khz)
return 0;
if (!static_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
khz = per_cpu(samples.khz, cpu);
if (khz)
return khz;
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
return per_cpu(samples.khz, cpu);
msleep(APERFMPERF_REFRESH_DELAY_MS);
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
......
......@@ -900,7 +900,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
if (c->x86_vendor != X86_VENDOR_AMD)
setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
fpu__init_system(c);
......
......@@ -47,4 +47,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
extern void get_cpu_cap(struct cpuinfo_x86 *c);
extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
unsigned int aperfmperf_get_khz(int cpu);
#endif /* ARCH_X86_CPU_H */
......@@ -470,6 +470,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
#define F14H_MPB_MAX_SIZE 1824
#define F15H_MPB_MAX_SIZE 4096
#define F16H_MPB_MAX_SIZE 3458
#define F17H_MPB_MAX_SIZE 3200
switch (family) {
case 0x14:
......@@ -481,6 +482,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
case 0x16:
max_size = F16H_MPB_MAX_SIZE;
break;
case 0x17:
max_size = F17H_MPB_MAX_SIZE;
break;
default:
max_size = F1XH_MPB_MAX_SIZE;
break;
......
......@@ -5,6 +5,8 @@
#include <linux/seq_file.h>
#include <linux/cpufreq.h>
#include "cpu.h"
/*
* Get CPU information for use by the procfs.
*/
......@@ -78,8 +80,10 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
if (cpu_has(c, X86_FEATURE_TSC)) {
unsigned int freq = cpufreq_quick_get(cpu);
unsigned int freq = aperfmperf_get_khz(cpu);
if (!freq)
freq = cpufreq_quick_get(cpu);
if (!freq)
freq = cpu_khz;
seq_printf(m, "cpu MHz\t\t: %u.%03u\n",
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment