summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig12
-rw-r--r--arch/x86/Kconfig.debug19
-rw-r--r--arch/x86/boot/boot.h1
-rw-r--r--arch/x86/boot/compressed/eboot.c182
-rw-r--r--arch/x86/boot/compressed/head_32.S6
-rw-r--r--arch/x86/boot/compressed/head_64.S8
-rw-r--r--arch/x86/boot/compressed/kaslr.c140
-rw-r--r--arch/x86/boot/string.c13
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c8
-rw-r--r--arch/x86/events/Makefile13
-rw-r--r--arch/x86/events/amd/Makefile7
-rw-r--r--arch/x86/events/amd/uncore.c204
-rw-r--r--arch/x86/events/intel/cstate.c3
-rw-r--r--arch/x86/events/intel/pt.c6
-rw-r--r--arch/x86/events/intel/rapl.c63
-rw-r--r--arch/x86/events/intel/uncore.c234
-rw-r--r--arch/x86/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/apic.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h6
-rw-r--r--arch/x86/include/asm/div64.h11
-rw-r--r--arch/x86/include/asm/e820.h2
-rw-r--r--arch/x86/include/asm/efi.h5
-rw-r--r--arch/x86/include/asm/elf.h9
-rw-r--r--arch/x86/include/asm/fpu/internal.h10
-rw-r--r--arch/x86/include/asm/intel-mid.h5
-rw-r--r--arch/x86/include/asm/io.h46
-rw-r--r--arch/x86/include/asm/mce.h20
-rw-r--r--arch/x86/include/asm/microcode.h10
-rw-r--r--arch/x86/include/asm/microcode_amd.h2
-rw-r--r--arch/x86/include/asm/msr-index.h5
-rw-r--r--arch/x86/include/asm/msr.h51
-rw-r--r--arch/x86/include/asm/pgtable_32.h32
-rw-r--r--arch/x86/include/asm/processor.h1
-rw-r--r--arch/x86/include/asm/spinlock.h3
-rw-r--r--arch/x86/include/asm/uv/uv.h2
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h3
-rw-r--r--arch/x86/include/asm/xen/hypercall.h7
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h3
-rw-r--r--arch/x86/include/uapi/asm/hwcap2.h7
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/acpi/boot.c14
-rw-r--r--arch/x86/kernel/acpi/cstate.c9
-rw-r--r--arch/x86/kernel/apic/apic.c33
-rw-r--r--arch/x86/kernel/apic/io_apic.c6
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c548
-rw-r--r--arch/x86/kernel/apm_32.c6
-rw-r--r--arch/x86/kernel/asm-offsets.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c22
-rw-r--r--arch/x86/kernel/cpu/centaur.c6
-rw-r--r--arch/x86/kernel/cpu/common.c41
-rw-r--r--arch/x86/kernel/cpu/cyrix.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c50
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c5
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-genpool.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c5
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c88
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c9
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c30
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c500
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c101
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c9
-rw-r--r--arch/x86/kernel/cpu/transmeta.c3
-rw-r--r--arch/x86/kernel/e820.c22
-rw-r--r--arch/x86/kernel/fpu/core.c7
-rw-r--r--arch/x86/kernel/fpu/init.c29
-rw-r--r--arch/x86/kernel/fpu/xstate.c9
-rw-r--r--arch/x86/kernel/head32.c62
-rw-r--r--arch/x86/kernel/head_32.S121
-rw-r--r--arch/x86/kernel/hpet.c1
-rw-r--r--arch/x86/kernel/itmt.c6
-rw-r--r--arch/x86/kernel/jump_label.c3
-rw-r--r--arch/x86/kernel/kprobes/core.c2
-rw-r--r--arch/x86/kernel/kvm.c14
-rw-r--r--arch/x86/kernel/kvmclock.c2
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c3
-rw-r--r--arch/x86/kernel/pci-calgary_64.c2
-rw-r--r--arch/x86/kernel/setup.c14
-rw-r--r--arch/x86/kernel/smpboot.c15
-rw-r--r--arch/x86/kernel/test_nx.c173
-rw-r--r--arch/x86/kernel/traps.c5
-rw-r--r--arch/x86/kernel/tsc.c16
-rw-r--r--arch/x86/kernel/tsc_sync.c16
-rw-r--r--arch/x86/kernel/vm86_32.c5
-rw-r--r--arch/x86/kvm/hyperv.c5
-rw-r--r--arch/x86/kvm/x86.c1
-rw-r--r--arch/x86/lib/delay.c4
-rw-r--r--arch/x86/mm/dump_pagetables.c27
-rw-r--r--arch/x86/mm/pageattr.c13
-rw-r--r--arch/x86/mm/pat_rbtree.c12
-rw-r--r--arch/x86/net/bpf_jit_comp.c25
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c59
-rw-r--r--arch/x86/platform/efi/efi.c10
-rw-r--r--arch/x86/platform/efi/efi_64.c80
-rw-r--r--arch/x86/platform/intel-mid/device_libs/Makefile3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_ipc.c68
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_ipc.h18
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c48
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c12
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c3
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c54
-rw-r--r--arch/x86/platform/intel-mid/mrfld.c1
-rw-r--r--arch/x86/platform/intel-mid/sfi.c58
-rw-r--r--arch/x86/platform/uv/uv_nmi.c459
-rw-r--r--arch/x86/ras/Kconfig2
-rw-r--r--arch/x86/xen/Kconfig2
-rw-r--r--arch/x86/xen/Makefile1
-rw-r--r--arch/x86/xen/apic.c2
-rw-r--r--arch/x86/xen/enlighten.c279
-rw-r--r--arch/x86/xen/mmu.c21
-rw-r--r--arch/x86/xen/platform-pci-unplug.c4
-rw-r--r--arch/x86/xen/setup.c37
-rw-r--r--arch/x86/xen/smp.c78
-rw-r--r--arch/x86/xen/smp.h8
-rw-r--r--arch/x86/xen/spinlock.c19
-rw-r--r--arch/x86/xen/xen-head.S62
-rw-r--r--arch/x86/xen/xen-ops.h1
-rw-r--r--arch/x86/xen/xen-pvh.S161
124 files changed, 2500 insertions, 2337 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e487493bbd47..f793820cee4c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -53,7 +53,10 @@ config X86
select ARCH_HAS_KCOV if X86_64
select ARCH_HAS_MMIO_FLUSH
select ARCH_HAS_PMEM_API if X86_64
+ select ARCH_HAS_SET_MEMORY
select ARCH_HAS_SG_CHAIN
+ select ARCH_HAS_STRICT_KERNEL_RWX
+ select ARCH_HAS_STRICT_MODULE_RWX
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
@@ -309,9 +312,6 @@ config ARCH_SUPPORTS_UPROBES
config FIX_EARLYCON_MEM
def_bool y
-config DEBUG_RODATA
- def_bool y
-
config PGTABLE_LEVELS
int
default 4 if X86_64
@@ -1070,7 +1070,7 @@ config X86_MCE_THRESHOLD
def_bool y
config X86_MCE_INJECT
- depends on X86_MCE
+ depends on X86_MCE && X86_LOCAL_APIC
tristate "Machine check injector support"
---help---
Provide support for injecting machine checks for testing purposes.
@@ -1994,10 +1994,6 @@ config RANDOMIZE_BASE
theoretically possible, but the implementations are further
limited due to memory layouts.
- If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot
- time. To enable it, boot with "kaslr" on the kernel command
- line (which will also disable hibernation).
-
If unsure, say N.
# Relocation on x86 needs some additional build support
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 67eec55093a5..c4cba00dbdee 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -109,25 +109,6 @@ config DEBUG_WX
If in doubt, say "Y".
-config DEBUG_SET_MODULE_RONX
- bool "Set loadable kernel module data as NX and text as RO"
- depends on MODULES
- ---help---
- This option helps catch unintended modifications to loadable
- kernel module's text and read-only data. It also prevents execution
- of module data. Such protection may interfere with run-time code
- patching and dynamic kernel tracing - and they might also protect
- against certain classes of kernel exploits.
- If in doubt, say "N".
-
-config DEBUG_NX_TEST
- tristate "Testcase for the NX non-executable stack feature"
- depends on DEBUG_KERNEL && m
- ---help---
- This option enables a testcase for the CPU NX capability
- and the software setup of this feature.
- If in doubt, say "N"
-
config DOUBLEFAULT
default y
bool "Enable doublefault exception handler" if EXPERT
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index e5612f3e3b57..9b42b6d1e902 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -333,6 +333,7 @@ size_t strnlen(const char *s, size_t maxlen);
unsigned int atou(const char *s);
unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
size_t strlen(const char *s);
+char *strchr(const char *s, int c);
/* tty.c */
void puts(const char *);
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff01c8fc76f7..801c7a158e55 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -32,160 +32,13 @@ static void setup_boot_services##bits(struct efi_config *c) \
\
table = (typeof(table))sys_table; \
\
+ c->runtime_services = table->runtime; \
c->boot_services = table->boottime; \
c->text_output = table->con_out; \
}
BOOT_SERVICES(32);
BOOT_SERVICES(64);
-void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
-
-static efi_status_t
-__file_size32(void *__fh, efi_char16_t *filename_16,
- void **handle, u64 *file_sz)
-{
- efi_file_handle_32_t *h, *fh = __fh;
- efi_file_info_t *info;
- efi_status_t status;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- u32 info_sz;
-
- status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
- EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to open file: ");
- efi_char16_printk(sys_table, filename_16);
- efi_printk(sys_table, "\n");
- return status;
- }
-
- *handle = h;
-
- info_sz = 0;
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk(sys_table, "Failed to get file info size\n");
- return status;
- }
-
-grow:
- status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- info_sz, (void **)&info);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for file info\n");
- return status;
- }
-
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_early(free_pool, info);
- goto grow;
- }
-
- *file_sz = info->file_size;
- efi_call_early(free_pool, info);
-
- if (status != EFI_SUCCESS)
- efi_printk(sys_table, "Failed to get initrd info\n");
-
- return status;
-}
-
-static efi_status_t
-__file_size64(void *__fh, efi_char16_t *filename_16,
- void **handle, u64 *file_sz)
-{
- efi_file_handle_64_t *h, *fh = __fh;
- efi_file_info_t *info;
- efi_status_t status;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- u64 info_sz;
-
- status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
- EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to open file: ");
- efi_char16_printk(sys_table, filename_16);
- efi_printk(sys_table, "\n");
- return status;
- }
-
- *handle = h;
-
- info_sz = 0;
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk(sys_table, "Failed to get file info size\n");
- return status;
- }
-
-grow:
- status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- info_sz, (void **)&info);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for file info\n");
- return status;
- }
-
- status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
- &info_sz, info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_early(free_pool, info);
- goto grow;
- }
-
- *file_sz = info->file_size;
- efi_call_early(free_pool, info);
-
- if (status != EFI_SUCCESS)
- efi_printk(sys_table, "Failed to get initrd info\n");
-
- return status;
-}
-efi_status_t
-efi_file_size(efi_system_table_t *sys_table, void *__fh,
- efi_char16_t *filename_16, void **handle, u64 *file_sz)
-{
- if (efi_early->is64)
- return __file_size64(__fh, filename_16, handle, file_sz);
-
- return __file_size32(__fh, filename_16, handle, file_sz);
-}
-
-efi_status_t
-efi_file_read(void *handle, unsigned long *size, void *addr)
-{
- unsigned long func;
-
- if (efi_early->is64) {
- efi_file_handle_64_t *fh = handle;
-
- func = (unsigned long)fh->read;
- return efi_early->call(func, handle, size, addr);
- } else {
- efi_file_handle_32_t *fh = handle;
-
- func = (unsigned long)fh->read;
- return efi_early->call(func, handle, size, addr);
- }
-}
-
-efi_status_t efi_file_close(void *handle)
-{
- if (efi_early->is64) {
- efi_file_handle_64_t *fh = handle;
-
- return efi_early->call((unsigned long)fh->close, handle);
- } else {
- efi_file_handle_32_t *fh = handle;
-
- return efi_early->call((unsigned long)fh->close, handle);
- }
-}
-
static inline efi_status_t __open_volume32(void *__image, void **__fh)
{
efi_file_io_interface_t *io;
@@ -249,30 +102,8 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
{
- unsigned long output_string;
- size_t offset;
-
- if (efi_early->is64) {
- struct efi_simple_text_output_protocol_64 *out;
- u64 *func;
-
- offset = offsetof(typeof(*out), output_string);
- output_string = efi_early->text_output + offset;
- out = (typeof(out))(unsigned long)efi_early->text_output;
- func = (u64 *)output_string;
-
- efi_early->call(*func, out, str);
- } else {
- struct efi_simple_text_output_protocol_32 *out;
- u32 *func;
-
- offset = offsetof(typeof(*out), output_string);
- output_string = efi_early->text_output + offset;
- out = (typeof(out))(unsigned long)efi_early->text_output;
- func = (u32 *)output_string;
-
- efi_early->call(*func, out, str);
- }
+ efi_call_proto(efi_simple_text_output_protocol, output_string,
+ efi_early->text_output, str);
}
static efi_status_t
@@ -1157,6 +988,13 @@ struct boot_params *efi_main(struct efi_config *c,
else
setup_boot_services32(efi_early);
+ /*
+ * If the boot loader gave us a value for secure_boot then we use that,
+ * otherwise we ask the BIOS.
+ */
+ if (boot_params->secure_boot == efi_secureboot_mode_unset)
+ boot_params->secure_boot = efi_get_secureboot(sys_table);
+
setup_graphics(boot_params);
setup_efi_pci(boot_params);
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index fd0b6a272dd5..d85b9625e836 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -82,7 +82,7 @@ ENTRY(efi_pe_entry)
/* Relocate efi_config->call() */
leal efi32_config(%esi), %eax
- add %esi, 32(%eax)
+ add %esi, 40(%eax)
pushl %eax
call make_boot_params
@@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry)
/* Relocate efi_config->call() */
leal efi32_config(%esi), %eax
- add %esi, 32(%eax)
+ add %esi, 40(%eax)
pushl %eax
2:
call efi_main
@@ -264,7 +264,7 @@ relocated:
#ifdef CONFIG_EFI_STUB
.data
efi32_config:
- .fill 4,8,0
+ .fill 5,8,0
.long efi_call_phys
.long 0
.byte 0
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 4d85e600db78..d2ae1f821e0c 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -264,7 +264,7 @@ ENTRY(efi_pe_entry)
/*
* Relocate efi_config->call().
*/
- addq %rbp, efi64_config+32(%rip)
+ addq %rbp, efi64_config+40(%rip)
movq %rax, %rdi
call make_boot_params
@@ -284,7 +284,7 @@ handover_entry:
* Relocate efi_config->call().
*/
movq efi_config(%rip), %rax
- addq %rbp, 32(%rax)
+ addq %rbp, 40(%rax)
2:
movq efi_config(%rip), %rdi
call efi_main
@@ -456,14 +456,14 @@ efi_config:
#ifdef CONFIG_EFI_MIXED
.global efi32_config
efi32_config:
- .fill 4,8,0
+ .fill 5,8,0
.quad efi64_thunk
.byte 0
#endif
.global efi64_config
efi64_config:
- .fill 4,8,0
+ .fill 5,8,0
.quad efi_call
.byte 1
#endif /* CONFIG_EFI_STUB */
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a66854d99ee1..8b7c9e75edcb 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -11,6 +11,7 @@
*/
#include "misc.h"
#include "error.h"
+#include "../boot.h"
#include <generated/compile.h>
#include <linux/module.h>
@@ -52,15 +53,22 @@ static unsigned long get_boot_seed(void)
#include "../../lib/kaslr.c"
struct mem_vector {
- unsigned long start;
- unsigned long size;
+ unsigned long long start;
+ unsigned long long size;
};
+/* Only supporting at most 4 unusable memmap regions with kaslr */
+#define MAX_MEMMAP_REGIONS 4
+
+static bool memmap_too_large;
+
enum mem_avoid_index {
MEM_AVOID_ZO_RANGE = 0,
MEM_AVOID_INITRD,
MEM_AVOID_CMDLINE,
MEM_AVOID_BOOTPARAMS,
+ MEM_AVOID_MEMMAP_BEGIN,
+ MEM_AVOID_MEMMAP_END = MEM_AVOID_MEMMAP_BEGIN + MAX_MEMMAP_REGIONS - 1,
MEM_AVOID_MAX,
};
@@ -77,6 +85,123 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
return true;
}
+/**
+ * _memparse - Parse a string with mem suffixes into a number
+ * @ptr: Where parse begins
+ * @retptr: (output) Optional pointer to next char after parse completes
+ *
+ * Parses a string into a number. The number stored at @ptr is
+ * potentially suffixed with K, M, G, T, P, E.
+ */
+static unsigned long long _memparse(const char *ptr, char **retptr)
+{
+ char *endptr; /* Local pointer to end of parsed string */
+
+ unsigned long long ret = simple_strtoull(ptr, &endptr, 0);
+
+ switch (*endptr) {
+ case 'E':
+ case 'e':
+ ret <<= 10;
+ case 'P':
+ case 'p':
+ ret <<= 10;
+ case 'T':
+ case 't':
+ ret <<= 10;
+ case 'G':
+ case 'g':
+ ret <<= 10;
+ case 'M':
+ case 'm':
+ ret <<= 10;
+ case 'K':
+ case 'k':
+ ret <<= 10;
+ endptr++;
+ default:
+ break;
+ }
+
+ if (retptr)
+ *retptr = endptr;
+
+ return ret;
+}
+
+static int
+parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
+{
+ char *oldp;
+
+ if (!p)
+ return -EINVAL;
+
+ /* We don't care about this option here */
+ if (!strncmp(p, "exactmap", 8))
+ return -EINVAL;
+
+ oldp = p;
+ *size = _memparse(p, &p);
+ if (p == oldp)
+ return -EINVAL;
+
+ switch (*p) {
+ case '@':
+ /* Skip this region, usable */
+ *start = 0;
+ *size = 0;
+ return 0;
+ case '#':
+ case '$':
+ case '!':
+ *start = _memparse(p + 1, &p);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static void mem_avoid_memmap(void)
+{
+ char arg[128];
+ int rc;
+ int i;
+ char *str;
+
+ /* See if we have any memmap areas */
+ rc = cmdline_find_option("memmap", arg, sizeof(arg));
+ if (rc <= 0)
+ return;
+
+ i = 0;
+ str = arg;
+ while (str && (i < MAX_MEMMAP_REGIONS)) {
+ int rc;
+ unsigned long long start, size;
+ char *k = strchr(str, ',');
+
+ if (k)
+ *k++ = 0;
+
+ rc = parse_memmap(str, &start, &size);
+ if (rc < 0)
+ break;
+ str = k;
+ /* A usable region that should not be skipped */
+ if (size == 0)
+ continue;
+
+ mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start;
+ mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size;
+ i++;
+ }
+
+ /* More than 4 memmaps, fail kaslr */
+ if ((i >= MAX_MEMMAP_REGIONS) && str)
+ memmap_too_large = true;
+}
+
/*
* In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
* The mem_avoid array is used to store the ranges that need to be avoided
@@ -197,6 +322,9 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
/* We don't need to set a mapping for setup_data. */
+ /* Mark the memmap regions we need to avoid */
+ mem_avoid_memmap();
+
#ifdef CONFIG_X86_VERBOSE_BOOTUP
/* Make sure video RAM can be used. */
add_identity_map(0, PMD_SIZE);
@@ -379,6 +507,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
int i;
unsigned long addr;
+ /* Check if we had too many memmaps. */
+ if (memmap_too_large) {
+ debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n");
+ return 0;
+ }
+
/* Make sure minimum is aligned. */
minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
@@ -456,7 +590,7 @@ void choose_random_location(unsigned long input,
/* Walk e820 and find a random address. */
random_addr = find_random_phys_addr(min_addr, output_size);
if (!random_addr) {
- warn("KASLR disabled: could not find suitable E820 region!");
+ warn("Physical KASLR disabled: no suitable memory region!");
} else {
/* Update the new physical address location. */
if (*output != random_addr) {
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 9e240fcba784..5457b02fc050 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -156,3 +156,16 @@ char *strstr(const char *s1, const char *s2)
}
return NULL;
}
+
+/**
+ * strchr - Find the first occurrence of the character c in the string s.
+ * @s: the string to be searched
+ * @c: the character to search for
+ */
+char *strchr(const char *s, int c)
+{
+ while (*s != (char)c)
+ if (*s++ == '\0')
+ return NULL;
+ return (char *)s;
+}
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 6ef688a1ef3e..7ff1b0c86a8e 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1085,9 +1085,9 @@ static void aesni_free_simds(void)
aesni_simd_skciphers[i]; i++)
simd_skcipher_free(aesni_simd_skciphers[i]);
- for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) &&
- aesni_simd_skciphers2[i].simd; i++)
- simd_skcipher_free(aesni_simd_skciphers2[i].simd);
+ for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++)
+ if (aesni_simd_skciphers2[i].simd)
+ simd_skcipher_free(aesni_simd_skciphers2[i].simd);
}
static int __init aesni_init(void)
@@ -1168,7 +1168,7 @@ static int __init aesni_init(void)
simd = simd_skcipher_create_compat(algname, drvname, basename);
err = PTR_ERR(simd);
if (IS_ERR(simd))
- goto unregister_simds;
+ continue;
aesni_simd_skciphers2[i].simd = simd;
}
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 1d392c39fe56..b8ccdb5c9244 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,11 +1,4 @@
-obj-y += core.o
-
-obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o
-obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o
-obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o
-ifdef CONFIG_AMD_IOMMU
-obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o
-endif
-
-obj-$(CONFIG_CPU_SUP_INTEL) += msr.o
+obj-y += core.o
+obj-y += amd/
+obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile
new file mode 100644
index 000000000000..b1da46f396e0
--- /dev/null
+++ b/arch/x86/events/amd/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o
+obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o
+obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o
+ifdef CONFIG_AMD_IOMMU
+obj-$(CONFIG_CPU_SUP_AMD) += iommu.o
+endif
+
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a0b1bdb3ad42..4d1f7f2d9aff 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -22,13 +22,17 @@
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
-#define MAX_COUNTERS NUM_COUNTERS_NB
+#define NUM_COUNTERS_L3 6
+#define MAX_COUNTERS 6
#define RDPMC_BASE_NB 6
-#define RDPMC_BASE_L2 10
+#define RDPMC_BASE_LLC 10
#define COUNTER_SHIFT 16
+static int num_counters_llc;
+static int num_counters_nb;
+
static HLIST_HEAD(uncore_unused_list);
struct amd_uncore {
@@ -45,30 +49,30 @@ struct amd_uncore {
};
static struct amd_uncore * __percpu *amd_uncore_nb;
-static struct amd_uncore * __percpu *amd_uncore_l2;
+static struct amd_uncore * __percpu *amd_uncore_llc;
static struct pmu amd_nb_pmu;
-static struct pmu amd_l2_pmu;
+static struct pmu amd_llc_pmu;
static cpumask_t amd_nb_active_mask;
-static cpumask_t amd_l2_active_mask;
+static cpumask_t amd_llc_active_mask;
static bool is_nb_event(struct perf_event *event)
{
return event->pmu->type == amd_nb_pmu.type;
}
-static bool is_l2_event(struct perf_event *event)
+static bool is_llc_event(struct perf_event *event)
{
- return event->pmu->type == amd_l2_pmu.type;
+ return event->pmu->type == amd_llc_pmu.type;
}
static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
{
if (is_nb_event(event) && amd_uncore_nb)
return *per_cpu_ptr(amd_uncore_nb, event->cpu);
- else if (is_l2_event(event) && amd_uncore_l2)
- return *per_cpu_ptr(amd_uncore_l2, event->cpu);
+ else if (is_llc_event(event) && amd_uncore_llc)
+ return *per_cpu_ptr(amd_uncore_llc, event->cpu);
return NULL;
}
@@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event)
return -ENOENT;
/*
- * NB and L2 counters (MSRs) are shared across all cores that share the
- * same NB / L2 cache. Interrupts can be directed to a single target
- * core, however, event counts generated by processes running on other
- * cores cannot be masked out. So we do not support sampling and
- * per-thread events.
+ * NB and Last level cache counters (MSRs) are shared across all cores
+ * that share the same NB / Last level cache. Interrupts can be directed
+ * to a single target core, however, event counts generated by processes
+ * running on other cores cannot be masked out. So we do not support
+ * sampling and per-thread events.
*/
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
- /* NB and L2 counters do not have usr/os/guest/host bits */
+ /* NB and Last level cache counters do not have usr/os/guest/host bits */
if (event->attr.exclude_user || event->attr.exclude_kernel ||
event->attr.exclude_host || event->attr.exclude_guest)
return -EINVAL;
@@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
if (pmu->type == amd_nb_pmu.type)
active_mask = &amd_nb_active_mask;
- else if (pmu->type == amd_l2_pmu.type)
- active_mask = &amd_l2_active_mask;
+ else if (pmu->type == amd_llc_pmu.type)
+ active_mask = &amd_llc_active_mask;
else
return 0;
@@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = {
.attrs = amd_uncore_attrs,
};
-PMU_FORMAT_ATTR(event, "config:0-7,32-35");
-PMU_FORMAT_ATTR(umask, "config:8-15");
-
-static struct attribute *amd_uncore_format_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- NULL,
-};
-
-static struct attribute_group amd_uncore_format_group = {
- .name = "format",
- .attrs = amd_uncore_format_attr,
+/*
+ * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based
+ * on family
+ */
+#define AMD_FORMAT_ATTR(_dev, _name, _format) \
+static ssize_t \
+_dev##_show##_name(struct device *dev, \
+ struct device_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev);
+
+/* Used for each uncore counter type */
+#define AMD_ATTRIBUTE(_name) \
+static struct attribute *amd_uncore_format_attr_##_name[] = { \
+ &format_attr_event_##_name.attr, \
+ &format_attr_umask.attr, \
+ NULL, \
+}; \
+static struct attribute_group amd_uncore_format_group_##_name = { \
+ .name = "format", \
+ .attrs = amd_uncore_format_attr_##_name, \
+}; \
+static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \
+ &amd_uncore_attr_group, \
+ &amd_uncore_format_group_##_name, \
+ NULL, \
};
-static const struct attribute_group *amd_uncore_attr_groups[] = {
- &amd_uncore_attr_group,
- &amd_uncore_format_group,
- NULL,
-};
+AMD_FORMAT_ATTR(event, , "config:0-7,32-35");
+AMD_FORMAT_ATTR(umask, , "config:8-15");
+AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60");
+AMD_FORMAT_ATTR(event, _l3, "config:0-7");
+AMD_ATTRIBUTE(df);
+AMD_ATTRIBUTE(l3);
static struct pmu amd_nb_pmu = {
.task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_attr_groups,
- .name = "amd_nb",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = {
.read = amd_uncore_read,
};
-static struct pmu amd_l2_pmu = {
+static struct pmu amd_llc_pmu = {
.task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_attr_groups,
- .name = "amd_l2",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
static int amd_uncore_cpu_up_prepare(unsigned int cpu)
{
- struct amd_uncore *uncore_nb = NULL, *uncore_l2;
+ struct amd_uncore *uncore_nb = NULL, *uncore_llc;
if (amd_uncore_nb) {
uncore_nb = amd_uncore_alloc(cpu);
if (!uncore_nb)
goto fail;
uncore_nb->cpu = cpu;
- uncore_nb->num_counters = NUM_COUNTERS_NB;
+ uncore_nb->num_counters = num_counters_nb;
uncore_nb->rdpmc_base = RDPMC_BASE_NB;
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
@@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
- if (amd_uncore_l2) {
- uncore_l2 = amd_uncore_alloc(cpu);
- if (!uncore_l2)
+ if (amd_uncore_llc) {
+ uncore_llc = amd_uncore_alloc(cpu);
+ if (!uncore_llc)
goto fail;
- uncore_l2->cpu = cpu;
- uncore_l2->num_counters = NUM_COUNTERS_L2;
- uncore_l2->rdpmc_base = RDPMC_BASE_L2;
- uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
- uncore_l2->active_mask = &amd_l2_active_mask;
- uncore_l2->pmu = &amd_l2_pmu;
- uncore_l2->id = -1;
- *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
+ uncore_llc->cpu = cpu;
+ uncore_llc->num_counters = num_counters_llc;
+ uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
+ uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
+ uncore_llc->active_mask = &amd_llc_active_mask;
+ uncore_llc->pmu = &amd_llc_pmu;
+ uncore_llc->id = -1;
+ *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
}
return 0;
@@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
}
- if (amd_uncore_l2) {
+ if (amd_uncore_llc) {
unsigned int apicid = cpu_data(cpu).apicid;
unsigned int nshared;
- uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
+ uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
nshared = ((eax >> 14) & 0xfff) + 1;
uncore->id = apicid - (apicid % nshared);
- uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
- *per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+ uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
+ *per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
}
return 0;
@@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu)
if (amd_uncore_nb)
uncore_online(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_online(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_online(cpu, amd_uncore_llc);
return 0;
}
@@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu)
if (amd_uncore_nb)
uncore_down_prepare(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_down_prepare(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_down_prepare(cpu, amd_uncore_llc);
return 0;
}
@@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu)
if (amd_uncore_nb)
uncore_dead(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_dead(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_dead(cpu, amd_uncore_llc);
return 0;
}
@@ -492,6 +511,47 @@ static int __init amd_uncore_init(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
goto fail_nodev;
+ switch(boot_cpu_data.x86) {
+ case 23:
+ /* Family 17h: */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L3;
+ /*
+ * For Family17h, the NorthBridge counters are
+ * re-purposed as Data Fabric counters. Also, support is
+ * added for L3 counters. The pmus are exported based on
+ * family as either L2 or L3 and NB or DF.
+ */
+ amd_nb_pmu.name = "amd_df";
+ amd_llc_pmu.name = "amd_l3";
+ format_attr_event_df.show = &event_show_df;
+ format_attr_event_l3.show = &event_show_l3;
+ break;
+ case 22:
+ /* Family 16h - may change: */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ break;
+ default:
+ /*
+ * All prior families have the same number of
+ * NorthBridge and Last Level Cache counters
+ */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ break;
+ }
+ amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
+ amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
+
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
goto fail_nodev;
@@ -510,16 +570,16 @@ static int __init amd_uncore_init(void)
}
if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
- amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
- if (!amd_uncore_l2) {
+ amd_uncore_llc = alloc_percpu(struct amd_uncore *);
+ if (!amd_uncore_llc) {
ret = -ENOMEM;
- goto fail_l2;
+ goto fail_llc;
}
- ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+ ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
if (ret)
- goto fail_l2;
+ goto fail_llc;
- pr_info("perf: AMD L2I counters detected\n");
+ pr_info("perf: AMD LLC counters detected\n");
ret = 0;
}
@@ -529,7 +589,7 @@ static int __init amd_uncore_init(void)
if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
"perf/x86/amd/uncore:prepare",
amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
- goto fail_l2;
+ goto fail_llc;
if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
"perf/x86/amd/uncore:starting",
@@ -546,11 +606,11 @@ fail_start:
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
fail_prep:
cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
-fail_l2:
+fail_llc:
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
perf_pmu_unregister(&amd_nb_pmu);
- if (amd_uncore_l2)
- free_percpu(amd_uncore_l2);
+ if (amd_uncore_llc)
+ free_percpu(amd_uncore_llc);
fail_nb:
if (amd_uncore_nb)
free_percpu(amd_uncore_nb);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 1076c9a77292..aff4b5b69d40 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -541,6 +541,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
{ },
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 1c1b9fe705c8..5900471ee508 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = {
};
PMU_FORMAT_ATTR(cyc, "config:1" );
+PMU_FORMAT_ATTR(pwr_evt, "config:4" );
+PMU_FORMAT_ATTR(fup_on_ptw, "config:5" );
PMU_FORMAT_ATTR(mtc, "config:9" );
PMU_FORMAT_ATTR(tsc, "config:10" );
PMU_FORMAT_ATTR(noretcomp, "config:11" );
+PMU_FORMAT_ATTR(ptw, "config:12" );
PMU_FORMAT_ATTR(mtc_period, "config:14-17" );
PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" );
PMU_FORMAT_ATTR(psb_period, "config:24-27" );
static struct attribute *pt_formats_attr[] = {
&format_attr_cyc.attr,
+ &format_attr_pwr_evt.attr,
+ &format_attr_fup_on_ptw.attr,
&format_attr_mtc.attr,
&format_attr_tsc.attr,
&format_attr_noretcomp.attr,
+ &format_attr_ptw.attr,
&format_attr_mtc_period.attr,
&format_attr_cyc_thresh.attr,
&format_attr_psb_period.attr,
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 17c3564d087a..22054ca49026 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
- return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+ unsigned int pkgid = topology_logical_package_id(cpu);
+
+ /*
+ * The unsigned check also catches the '-1' return value for non
+ * existent mappings in the topology map.
+ */
+ return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
}
static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
/* must be done before validate_group */
pmu = cpu_to_rapl_pmu(event->cpu);
+ if (!pmu)
+ return -EINVAL;
event->cpu = pmu->cpu;
event->pmu_private = pmu;
event->hw.event_base = msr;
@@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu)
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
int target;
+ if (!pmu) {
+ pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+ if (!pmu)
+ return -ENOMEM;
+
+ raw_spin_lock_init(&pmu->lock);
+ INIT_LIST_HEAD(&pmu->active_list);
+ pmu->pmu = &rapl_pmus->pmu;
+ pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+ rapl_hrtimer_init(pmu);
+
+ rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+ }
+
/*
* Check if there is an online cpu in the package which collects rapl
* events already.
@@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu)
return 0;
}
-static int rapl_cpu_prepare(unsigned int cpu)
-{
- struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
- if (pmu)
- return 0;
-
- pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
- if (!pmu)
- return -ENOMEM;
-
- raw_spin_lock_init(&pmu->lock);
- INIT_LIST_HEAD(&pmu->active_list);
- pmu->pmu = &rapl_pmus->pmu;
- pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
- pmu->cpu = -1;
- rapl_hrtimer_init(pmu);
- rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
- return 0;
-}
-
static int rapl_check_hw_unit(bool apply_quirk)
{
u64 msr_rapl_power_unit_bits;
@@ -770,6 +771,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
+
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
{},
};
@@ -803,29 +807,21 @@ static int __init rapl_pmu_init(void)
/*
* Install callbacks. Core will call them for each online cpu.
*/
-
- ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
- rapl_cpu_prepare, NULL);
- if (ret)
- goto out;
-
ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
"perf/x86/rapl:online",
rapl_cpu_online, rapl_cpu_offline);
if (ret)
- goto out1;
+ goto out;
ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
if (ret)
- goto out2;
+ goto out1;
rapl_advertise();
return 0;
-out2:
- cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
out1:
- cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
out:
pr_warn("Initialization failed (%d), disabled\n", ret);
cleanup_rapl_pmus();
@@ -836,7 +832,6 @@ module_init(rapl_pmu_init);
static void __exit intel_rapl_exit(void)
{
cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
- cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
perf_pmu_unregister(&rapl_pmus->pmu);
cleanup_rapl_pmus();
}
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 8c4ccdc3a3f3..758c1aa5009d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
- return pmu->boxes[topology_logical_package_id(cpu)];
+ unsigned int pkgid = topology_logical_package_id(cpu);
+
+ /*
+ * The unsigned check also catches the '-1' return value for non
+ * existent mappings in the topology map.
+ */
+ return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
}
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -764,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
pmu->registered = false;
}
-static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
-{
- struct intel_uncore_pmu *pmu = type->pmus;
- struct intel_uncore_box *box;
- int i, pkg;
-
- if (pmu) {
- pkg = topology_physical_package_id(cpu);
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box)
- uncore_box_exit(box);
- }
- }
-}
-
-static void uncore_exit_boxes(void *dummy)
-{
- struct intel_uncore_type **types;
-
- for (types = uncore_msr_uncores; *types; types++)
- __uncore_exit_boxes(*types++, smp_processor_id());
-}
-
static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
{
int pkg;
@@ -1058,86 +1040,6 @@ static void uncore_pci_exit(void)
}
}
-static int uncore_cpu_dying(unsigned int cpu)
-{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- int i, pkg;
-
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box && atomic_dec_return(&box->refcnt) == 0)
- uncore_box_exit(box);
- }
- }
- return 0;
-}
-
-static int first_init;
-
-static int uncore_cpu_starting(unsigned int cpu)
-{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- int i, pkg, ncpus = 1;
-
- if (first_init) {
- /*
- * On init we get the number of online cpus in the package
- * and set refcount for all of them.
- */
- ncpus = cpumask_weight(topology_core_cpumask(cpu));
- }
-
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (!box)
- continue;
- /* The first cpu on a package activates the box */
- if (atomic_add_return(ncpus, &box->refcnt) == ncpus)
- uncore_box_init(box);
- }
- }
-
- return 0;
-}
-
-static int uncore_cpu_prepare(unsigned int cpu)
-{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- int i, pkg;
-
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- if (pmu->boxes[pkg])
- continue;
- /* First cpu of a package allocates the box */
- box = uncore_alloc_box(type, cpu_to_node(cpu));
- if (!box)
- return -ENOMEM;
- box->pmu = pmu;
- box->pkgid = pkg;
- pmu->boxes[pkg] = box;
- }
- }
- return 0;
-}
-
static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
int new_cpu)
{
@@ -1177,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
static int uncore_event_cpu_offline(unsigned int cpu)
{
- int target;
+ struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, pkg, target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
- return 0;
-
+ goto unref;
/* Find a new cpu to collect uncore events */
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
@@ -1194,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu)
uncore_change_context(uncore_msr_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
+
+unref:
+ /* Clear the references */
+ pkg = topology_logical_package_id(cpu);
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[pkg];
+ if (box && atomic_dec_return(&box->refcnt) == 0)
+ uncore_box_exit(box);
+ }
+ }
return 0;
}
+static int allocate_boxes(struct intel_uncore_type **types,
+ unsigned int pkg, unsigned int cpu)
+{
+ struct intel_uncore_box *box, *tmp;
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ LIST_HEAD(allocated);
+ int i;
+
+ /* Try to allocate all required boxes */
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ if (pmu->boxes[pkg])
+ continue;
+ box = uncore_alloc_box(type, cpu_to_node(cpu));
+ if (!box)
+ goto cleanup;
+ box->pmu = pmu;
+ box->pkgid = pkg;
+ list_add(&box->active_list, &allocated);
+ }
+ }
+ /* Install them in the pmus */
+ list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+ list_del_init(&box->active_list);
+ box->pmu->boxes[pkg] = box;
+ }
+ return 0;
+
+cleanup:
+ list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+ list_del_init(&box->active_list);
+ kfree(box);
+ }
+ return -ENOMEM;
+}
+
static int uncore_event_cpu_online(unsigned int cpu)
{
- int target;
+ struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, ret, pkg, target;
+
+ pkg = topology_logical_package_id(cpu);
+ ret = allocate_boxes(types, pkg, cpu);
+ if (ret)
+ return ret;
+
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[pkg];
+ if (!box && atomic_inc_return(&box->refcnt) == 1)
+ uncore_box_init(box);
+ }
+ }
/*
* Check if there is an online cpu in the package
@@ -1354,6 +1328,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
{},
};
@@ -1389,38 +1365,16 @@ static int __init intel_uncore_init(void)
if (cret && pret)
return -ENODEV;
- /*
- * Install callbacks. Core will call them for each online cpu.
- *
- * The first online cpu of each package allocates and takes
- * the refcounts for all other online cpus in that package.
- * If msrs are not enabled no allocation is required and
- * uncore_cpu_prepare() is not called for each online cpu.
- */
- if (!cret) {
- ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
- "perf/x86/intel/uncore:prepare",
- uncore_cpu_prepare, NULL);
- if (ret)
- goto err;
- } else {
- cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
- "perf/x86/intel/uncore:prepare",
- uncore_cpu_prepare, NULL);
- }
- first_init = 1;
- cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
- "perf/x86/uncore:starting",
- uncore_cpu_starting, uncore_cpu_dying);
- first_init = 0;
- cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
- "perf/x86/uncore:online",
- uncore_event_cpu_online, uncore_event_cpu_offline);
+ /* Install hotplug callbacks to setup the targets for each package */
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+ "perf/x86/intel/uncore:online",
+ uncore_event_cpu_online,
+ uncore_event_cpu_offline);
+ if (ret)
+ goto err;
return 0;
err:
- /* Undo box->init_box() */
- on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
uncore_types_exit(uncore_msr_uncores);
uncore_pci_exit();
return ret;
@@ -1429,9 +1383,7 @@ module_init(intel_uncore_init);
static void __exit intel_uncore_exit(void)
{
- cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
- cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
- cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
uncore_types_exit(uncore_msr_uncores);
uncore_pci_exit();
}
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 2b892e2313a9..5d6a53fd7521 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h
generated-y += xen-hypercalls.h
generic-y += clkdev.h
-generic-y += cputime.h
generic-y += dma-contiguous.h
generic-y += early_ioremap.h
generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 0c5fbc68e82d..eff8e36aaf72 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -195,7 +195,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
{
- wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+ __wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
}
static inline u32 native_apic_msr_read(u32 reg)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index eafee3161d1c..4e7772387c6e 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -100,7 +100,7 @@
#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */
#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */
#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */
#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
@@ -186,7 +186,7 @@
*
* Reuse free bits when adding new feature flags!
*/
-
+#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -288,6 +288,7 @@
#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
@@ -320,5 +321,4 @@
#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 */
-
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index ced283ac79df..af95c47d5c9e 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -59,6 +59,17 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
}
#define div_u64_rem div_u64_rem
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+ u32 high, low;
+
+ asm ("mull %[b]" : "=a" (low), "=d" (high)
+ : [a] "a" (a), [b] "rm" (b) );
+
+ return low | ((u64)high) << 32;
+}
+#define mul_u32_u32 mul_u32_u32
+
#else
# include <asm-generic/div64.h>
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index ec23d8e1297c..67313f3a9874 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -30,8 +30,6 @@ extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
int checktype);
extern void update_e820(void);
extern void e820_setup_gap(void);
-extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
- unsigned long start_addr, unsigned long long end_addr);
struct setup_data;
extern void parse_e820_ext(u64 phys_addr, u32 data_len);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index e99675b9c861..2f77bcefe6b4 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -191,6 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
struct efi_config {
u64 image_handle;
u64 table;
+ u64 runtime_services;
u64 boot_services;
u64 text_output;
efi_status_t (*call)(unsigned long, ...);
@@ -226,6 +227,10 @@ static inline bool efi_is_64bit(void)
#define __efi_call_early(f, ...) \
__efi_early()->call((unsigned long)f, __VA_ARGS__);
+#define efi_call_runtime(f, ...) \
+ __efi_early()->call(efi_table_attr(efi_runtime_services, f, \
+ __efi_early()->runtime_services), __VA_ARGS__)
+
extern bool efi_reboot_required(void);
#else
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index e7f155c3045e..9d49c18b5ea9 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -258,6 +258,15 @@ extern int force_personality32;
#define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX])
+extern u32 elf_hwcap2;
+
+/*
+ * HWCAP2 supplies mask with kernel enabled CPU features, so that
+ * the application can discover that it can safely use them.
+ * The bits are defined in uapi/asm/hwcap2.h.
+ */
+#define ELF_HWCAP2 (elf_hwcap2)
+
/* This yields a string that ld.so will use to load implementation
specific libraries for optimization. This is more specific in
intent than poking at uname or /proc/cpuinfo.
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index d4a684997497..255645f60ca2 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -87,6 +87,16 @@ extern void fpstate_init_soft(struct swregs_state *soft);
#else
static inline void fpstate_init_soft(struct swregs_state *soft) {}
#endif
+
+static inline void fpstate_init_xstate(struct xregs_state *xsave)
+{
+ /*
+ * XRSTORS requires these bits set in xcomp_bv, or it will
+ * trigger #GP:
+ */
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask;
+}
+
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
{
fx->cwd = 0x37f;
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 49da9f497b90..fe04491130ae 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -27,7 +27,6 @@ extern void intel_mid_pwr_power_off(void);
extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev);
extern int get_gpio_by_name(const char *name);
-extern void intel_scu_device_register(struct platform_device *pdev);
extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
extern int __init sfi_parse_mtmr(struct sfi_table_header *table);
extern int sfi_mrtc_num;
@@ -42,10 +41,8 @@ struct devs_id {
char name[SFI_NAME_LEN + 1];
u8 type;
u8 delay;
+ u8 msic;
void *(*get_platform_data)(void *info);
- /* Custom handler for devices */
- void (*device_handler)(struct sfi_device_table_entry *pentry,
- struct devs_id *dev);
};
#define sfi_device(i) \
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index d34bd370074b..7afb0e2f07f4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -164,6 +164,17 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
#define virt_to_bus virt_to_phys
#define bus_to_virt phys_to_virt
+/*
+ * The default ioremap() behavior is non-cached; if you need something
+ * else, you probably want one of the following.
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
+#define ioremap_uc ioremap_uc
+
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val);
+
/**
* ioremap - map bus memory into CPU space
* @offset: bus address of the memory
@@ -178,17 +189,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
* If the area you are trying to map is a PCI BAR you should have a
* look at pci_iomap().
*/
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
-#define ioremap_uc ioremap_uc
-
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
- unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
{
return ioremap_nocache(offset, size);
@@ -207,18 +207,42 @@ extern void set_iounmap_nonlazy(void);
*/
#define xlate_dev_kmem_ptr(p) p
+/**
+ * memset_io Set a range of I/O memory to a constant value
+ * @addr: The beginning of the I/O-memory range to set
+ * @val: The value to set the memory to
+ * @count: The number of bytes to set
+ *
+ * Set a range of I/O memory to a given value.
+ */
static inline void
memset_io(volatile void __iomem *addr, unsigned char val, size_t count)
{
memset((void __force *)addr, val, count);
}
+/**
+ * memcpy_fromio Copy a block of data from I/O memory
+ * @dst: The (RAM) destination for the copy
+ * @src: The (I/O memory) source for the data
+ * @count: The number of bytes to copy
+ *
+ * Copy a block of data from I/O memory.
+ */
static inline void
memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count)
{
memcpy(dst, (const void __force *)src, count);
}
+/**
+ * memcpy_toio Copy a block of data into I/O memory
+ * @dst: The (I/O memory) destination for the copy
+ * @src: The (RAM) source for the data
+ * @count: The number of bytes to copy
+ *
+ * Copy a block of data to I/O memory.
+ */
static inline void
memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
{
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 5132f2a6c0a2..e63873683d4a 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -97,10 +97,6 @@
#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */
-/* Software defined banks */
-#define MCE_EXTENDED_BANK 128
-#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0)
-
#define MCE_LOG_LEN 32
#define MCE_LOG_SIGNATURE "MACHINECHECK"
@@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags;
extern struct mca_config mca_cfg;
extern struct mca_msr_regs msr_ops;
+
+enum mce_notifier_prios {
+ MCE_PRIO_SRAO = INT_MAX,
+ MCE_PRIO_EXTLOG = INT_MAX - 1,
+ MCE_PRIO_NFIT = INT_MAX - 2,
+ MCE_PRIO_EDAC = INT_MAX - 3,
+ MCE_PRIO_LOWEST = 0,
+};
+
extern void mce_register_decode_chain(struct notifier_block *nb);
extern void mce_unregister_decode_chain(struct notifier_block *nb);
@@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void);
void intel_init_thermal(struct cpuinfo_x86 *c);
-void mce_log_therm_throt_event(__u64 status);
-
/* Interrupt Handler for core thermal thresholds */
extern int (*platform_thermal_notify)(__u64 msr_val);
@@ -362,12 +365,13 @@ struct smca_hwid {
unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */
u32 hwid_mcatype; /* (hwid,mcatype) tuple */
u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */
+ u8 count; /* Number of instances. */
};
struct smca_bank {
struct smca_hwid *hwid;
- /* Instance ID */
- u32 id;
+ u32 id; /* Value of MCA_IPID[InstanceId]. */
+ u8 sysfs_id; /* Value used for sysfs name. */
};
extern struct smca_bank smca_banks[MAX_NR_BANKS];
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 38711df3bcb5..daadeeea00b1 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -7,18 +7,17 @@
#define native_rdmsr(msr, val1, val2) \
do { \
- u64 __val = native_read_msr((msr)); \
+ u64 __val = __rdmsr((msr)); \
(void)((val1) = (u32)__val); \
(void)((val2) = (u32)(__val >> 32)); \
} while (0)
#define native_wrmsr(msr, low, high) \
- native_write_msr(msr, low, high)
+ __wrmsr(msr, low, high)
#define native_wrmsrl(msr, val) \
- native_write_msr((msr), \
- (u32)((u64)(val)), \
- (u32)((u64)(val) >> 32))
+ __wrmsr((msr), (u32)((u64)(val)), \
+ (u32)((u64)(val) >> 32))
struct ucode_patch {
struct list_head plist;
@@ -140,6 +139,7 @@ extern void __init load_ucode_bsp(void);
extern void load_ucode_ap(void);
void reload_early_microcode(void);
extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
+extern bool initrd_gone;
#else
static inline int __init microcode_init(void) { return 0; };
static inline void __init load_ucode_bsp(void) { }
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 3e3e20be829a..3d57009e168b 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -54,6 +54,4 @@ static inline int __init
save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
void reload_ucode_amd(void) {}
#endif
-
-extern bool check_current_patch_level(u32 *rev, bool early);
#endif /* _ASM_X86_MICROCODE_AMD_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 710273c617b8..00293a94ffaf 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -543,6 +543,11 @@
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
+/* MISC_FEATURE_ENABLES non-architectural features */
+#define MSR_MISC_FEATURE_ENABLES 0x00000140
+
+#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1
+
#define MSR_IA32_TSC_DEADLINE 0x000006E0
/* P4/Xeon+ specific */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index db0b90c3b03e..898dba2e2e2c 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -80,7 +80,14 @@ static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
#endif
-static inline unsigned long long native_read_msr(unsigned int msr)
+/*
+ * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR
+ * accessors and should not have any tracing or other functionality piggybacking
+ * on them - those are *purely* for accessing MSRs and nothing more. So don't even
+ * think of extending them - you will be slapped with a stinking trout or a frozen
+ * shark will reach you, wherever you are! You've been warned.
+ */
+static inline unsigned long long notrace __rdmsr(unsigned int msr)
{
DECLARE_ARGS(val, low, high);
@@ -88,11 +95,30 @@ static inline unsigned long long native_read_msr(unsigned int msr)
"2:\n"
_ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
: EAX_EDX_RET(val, low, high) : "c" (msr));
- if (msr_tracepoint_active(__tracepoint_read_msr))
- do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
+
return EAX_EDX_VAL(val, low, high);
}
+static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+{
+ asm volatile("1: wrmsr\n"
+ "2:\n"
+ _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+ : : "c" (msr), "a"(low), "d" (high) : "memory");
+}
+
+static inline unsigned long long native_read_msr(unsigned int msr)
+{
+ unsigned long long val;
+
+ val = __rdmsr(msr);
+
+ if (msr_tracepoint_active(__tracepoint_read_msr))
+ do_trace_read_msr(msr, val, 0);
+
+ return val;
+}
+
static inline unsigned long long native_read_msr_safe(unsigned int msr,
int *err)
{
@@ -116,29 +142,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
/* Can be uninlined because referenced by paravirt */
static inline void notrace
-__native_write_msr_notrace(unsigned int msr, u32 low, u32 high)
-{
- asm volatile("1: wrmsr\n"
- "2:\n"
- _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
- : : "c" (msr), "a"(low), "d" (high) : "memory");
-}
-
-/* Can be uninlined because referenced by paravirt */
-static inline void notrace
native_write_msr(unsigned int msr, u32 low, u32 high)
{
- __native_write_msr_notrace(msr, low, high);
+ __wrmsr(msr, low, high);
+
if (msr_tracepoint_active(__tracepoint_write_msr))
do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
}
-static inline void
-wrmsr_notrace(unsigned int msr, u32 low, u32 high)
-{
- __native_write_msr_notrace(msr, low, high);
-}
-
/* Can be uninlined because referenced by paravirt */
static inline int notrace
native_write_msr_safe(unsigned int msr, u32 low, u32 high)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index b6c0b404898a..fbc73360aea0 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -27,6 +27,7 @@ struct vm_area_struct;
extern pgd_t swapper_pg_dir[1024];
extern pgd_t initial_page_table[1024];
+extern pmd_t initial_pg_pmd[];
static inline void pgtable_cache_init(void) { }
static inline void check_pgt_cache(void) { }
@@ -75,4 +76,35 @@ do { \
#define kern_addr_valid(kaddr) (0)
#endif
+/*
+ * This is how much memory in addition to the memory covered up to
+ * and including _end we need mapped initially.
+ * We need:
+ * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
+ * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
+ *
+ * Modulo rounding, each megabyte assigned here requires a kilobyte of
+ * memory, which is currently unreclaimed.
+ *
+ * This should be a multiple of a page.
+ *
+ * KERNEL_IMAGE_SIZE should be greater than pa(_end)
+ * and small than max_low_pfn, otherwise will waste some page table entries
+ */
+#if PTRS_PER_PMD > 1
+#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
+#else
+#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
+#endif
+
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT))
+
#endif /* _ASM_X86_PGTABLE_32_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1be64da0384e..e6cfe7ba2d65 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
+ __u8 cu_id;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 921bea7a2708..6d391909e864 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -23,9 +23,6 @@
/* How long a lock should spin before we consider blocking */
#define SPIN_THRESHOLD (1 << 15)
-extern struct static_key paravirt_ticketlocks_enabled;
-static __always_inline bool static_key_false(struct static_key *key);
-
#include <asm/qspinlock.h>
/*
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 062921ef34e9..6686820feae9 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -10,6 +10,7 @@ struct mm_struct;
extern enum uv_system_type get_uv_system_type(void);
extern int is_uv_system(void);
+extern int is_uv_hubless(void);
extern void uv_cpu_init(void);
extern void uv_nmi_init(void);
extern void uv_system_init(void);
@@ -23,6 +24,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
static inline int is_uv_system(void) { return 0; }
+static inline int is_uv_hubless(void) { return 0; }
static inline void uv_cpu_init(void) { }
static inline void uv_system_init(void) { }
static inline const struct cpumask *
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 097b80c989c4..72e8300b1e8a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -772,6 +772,7 @@ static inline int uv_num_possible_blades(void)
/* Per Hub NMI support */
extern void uv_nmi_setup(void);
+extern void uv_nmi_setup_hubless(void);
/* BMC sets a bit this MMR non-zero before sending an NMI */
#define UVH_NMI_MMR UVH_SCRATCH5
@@ -799,6 +800,8 @@ struct uv_hub_nmi_s {
atomic_t read_mmr_count; /* count of MMR reads */
atomic_t nmi_count; /* count of true UV NMIs */
unsigned long nmi_value; /* last value read from NMI MMR */
+ bool hub_present; /* false means UV hubless system */
+ bool pch_owner; /* indicates this hub owns PCH */
};
struct uv_cpu_nmi_s {
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a12a047184ee..f6d20f6cca12 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -472,6 +472,13 @@ HYPERVISOR_xenpmu_op(unsigned int op, void *arg)
return _hypercall2(int, xenpmu_op, op, arg);
}
+static inline int
+HYPERVISOR_dm_op(
+ domid_t dom, unsigned int nr_bufs, void *bufs)
+{
+ return _hypercall3(int, dm_op, dom, nr_bufs, bufs);
+}
+
static inline void
MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
{
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index b10bf319ed20..5138dacf8bb8 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -135,7 +135,8 @@ struct boot_params {
__u8 eddbuf_entries; /* 0x1e9 */
__u8 edd_mbr_sig_buf_entries; /* 0x1ea */
__u8 kbd_status; /* 0x1eb */
- __u8 _pad5[3]; /* 0x1ec */
+ __u8 secure_boot; /* 0x1ec */
+ __u8 _pad5[2]; /* 0x1ed */
/*
* The sentinel is set to a nonzero value (0xff) in header.S.
*
diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h
new file mode 100644
index 000000000000..0bd2be5c7617
--- /dev/null
+++ b/arch/x86/include/uapi/asm/hwcap2.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_HWCAP2_H
+#define _ASM_X86_HWCAP2_H
+
+/* MONITOR/MWAIT enabled in Ring 3 */
+#define HWCAP2_RING3MWAIT (1 << 0)
+
+#endif
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 581386c7e429..bdcdb3b3a219 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -101,7 +101,6 @@ obj-$(CONFIG_APB_TIMER) += apb_timer.o
obj-$(CONFIG_AMD_NB) += amd_nb.o
obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
-obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 64422f850e95..ae32838cac5f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -35,6 +35,7 @@
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/pci.h>
+#include <linux/efi-bgrt.h>
#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
@@ -723,11 +724,12 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
return 0;
}
-int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
+int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
+ int *pcpu)
{
int cpu;
- cpu = acpi_register_lapic(physid, U32_MAX, ACPI_MADT_ENABLED);
+ cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED);
if (cpu < 0) {
pr_info(PREFIX "Unable to map lapic to logical cpu number\n");
return cpu;
@@ -1557,6 +1559,12 @@ int __init early_acpi_boot_init(void)
return 0;
}
+static int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+ efi_bgrt_init(table);
+ return 0;
+}
+
int __init acpi_boot_init(void)
{
/* those are executed after early-quirks are executed */
@@ -1581,6 +1589,8 @@ int __init acpi_boot_init(void)
acpi_process_madt();
acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet);
+ if (IS_ENABLED(CONFIG_ACPI_BGRT))
+ acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
if (!acpi_noirq)
x86_init.pci.init = pci_acpi_init;
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index af15f4444330..8233a630280f 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -12,7 +12,6 @@
#include <linux/sched.h>
#include <acpi/processor.h>
-#include <asm/acpi.h>
#include <asm/mwait.h>
#include <asm/special_insns.h>
@@ -89,7 +88,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
retval = 0;
/* If the HW does not support any sub-states in this C-state */
if (num_cstate_subtype == 0) {
- pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part);
+ pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n",
+ cx->address, edx_part);
retval = -1;
goto out;
}
@@ -104,8 +104,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
if (!mwait_supported[cstate_type]) {
mwait_supported[cstate_type] = 1;
printk(KERN_DEBUG
- "Monitor-Mwait will be used to enter C-%d "
- "state\n", cx->type);
+ "Monitor-Mwait will be used to enter C-%d state\n",
+ cx->type);
}
snprintf(cx->desc,
ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x",
@@ -166,6 +166,7 @@ EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter);
static int __init ffh_cstate_init(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
+
if (c->x86_vendor != X86_VENDOR_INTEL)
return -1;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 5b7e43eff139..8567c851172c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -529,18 +529,19 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
* The local apic timer can be used for any function which is CPU local.
*/
static struct clock_event_device lapic_clockevent = {
- .name = "lapic",
- .features = CLOCK_EVT_FEAT_PERIODIC |
- CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
- | CLOCK_EVT_FEAT_DUMMY,
- .shift = 32,
- .set_state_shutdown = lapic_timer_shutdown,
- .set_state_periodic = lapic_timer_set_periodic,
- .set_state_oneshot = lapic_timer_set_oneshot,
- .set_next_event = lapic_next_event,
- .broadcast = lapic_timer_broadcast,
- .rating = 100,
- .irq = -1,
+ .name = "lapic",
+ .features = CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
+ | CLOCK_EVT_FEAT_DUMMY,
+ .shift = 32,
+ .set_state_shutdown = lapic_timer_shutdown,
+ .set_state_periodic = lapic_timer_set_periodic,
+ .set_state_oneshot = lapic_timer_set_oneshot,
+ .set_state_oneshot_stopped = lapic_timer_shutdown,
+ .set_next_event = lapic_next_event,
+ .broadcast = lapic_timer_broadcast,
+ .rating = 100,
+ .irq = -1,
};
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
@@ -1245,7 +1246,7 @@ static void lapic_setup_esr(void)
/**
* setup_local_APIC - setup the local APIC
*
- * Used to setup local APIC while initializing BSP or bringin up APs.
+ * Used to setup local APIC while initializing BSP or bringing up APs.
* Always called with preemption disabled.
*/
void setup_local_APIC(void)
@@ -2028,8 +2029,8 @@ void disconnect_bsp_APIC(int virt_wire_setup)
/*
* The number of allocated logical CPU IDs. Since logical CPU IDs are allocated
* contiguously, it equals to current allocated max logical CPU ID plus 1.
- * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of
- * nr_logical_cpuids is nr_cpu_ids.
+ * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range,
+ * so the maximum of nr_logical_cpuids is nr_cpu_ids.
*
* NOTE: Reserve 0 for BSP.
*/
@@ -2094,7 +2095,7 @@ int __generic_processor_info(int apicid, int version, bool enabled)
* Since fixing handling of boot_cpu_physical_apicid requires
* another discussion and tests on each platform, we leave it
* for now and here we use read_apic_id() directly in this
- * function, generic_processor_info().
+ * function, __generic_processor_info().
*/
if (disabled_cpu_apicid != BAD_APICID &&
disabled_cpu_apicid != read_apic_id() &&
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1e35dd06b090..347bb9f65737 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1107,12 +1107,12 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
ioapic = mp_find_ioapic(gsi);
if (ioapic < 0)
- return -1;
+ return -ENODEV;
pin = mp_find_ioapic_pin(ioapic, gsi);
idx = find_irq_entry(ioapic, pin, mp_INT);
if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
- return -1;
+ return -ENODEV;
return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
}
@@ -2117,6 +2117,7 @@ static inline void __init check_timer(void)
if (idx != -1 && irq_trigger(idx))
unmask_ioapic_irq(irq_get_chip_data(0));
}
+ irq_domain_deactivate_irq(irq_data);
irq_domain_activate_irq(irq_data);
if (timer_irq_works()) {
if (disable_timer_pin_1 > 0)
@@ -2138,6 +2139,7 @@ static inline void __init check_timer(void)
* legacy devices should be connected to IO APIC #0
*/
replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+ irq_domain_deactivate_irq(irq_data);
irq_domain_activate_irq(irq_data);
legacy_pic->unmask(0);
if (timer_irq_works()) {
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 35690a168cf7..e9f8f8cdd570 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -41,40 +41,44 @@
DEFINE_PER_CPU(int, x2apic_extra_bits);
-#define PR_DEVEL(fmt, args...) pr_devel("%s: " fmt, __func__, args)
-
-static enum uv_system_type uv_system_type;
-static u64 gru_start_paddr, gru_end_paddr;
-static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
-static u64 gru_dist_lmask, gru_dist_umask;
-static union uvh_apicid uvh_apicid;
-
-/* info derived from CPUID */
+static enum uv_system_type uv_system_type;
+static bool uv_hubless_system;
+static u64 gru_start_paddr, gru_end_paddr;
+static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
+static u64 gru_dist_lmask, gru_dist_umask;
+static union uvh_apicid uvh_apicid;
+
+/* Information derived from CPUID: */
static struct {
unsigned int apicid_shift;
unsigned int apicid_mask;
unsigned int socketid_shift; /* aka pnode_shift for UV1/2/3 */
unsigned int pnode_mask;
unsigned int gpa_shift;
+ unsigned int gnode_shift;
} uv_cpuid;
int uv_min_hub_revision_id;
EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
+
unsigned int uv_apicid_hibits;
EXPORT_SYMBOL_GPL(uv_apicid_hibits);
static struct apic apic_x2apic_uv_x;
static struct uv_hub_info_s uv_hub_info_node0;
-/* Set this to use hardware error handler instead of kernel panic */
+/* Set this to use hardware error handler instead of kernel panic: */
static int disable_uv_undefined_panic = 1;
+
unsigned long uv_undefined(char *str)
{
if (likely(!disable_uv_undefined_panic))
panic("UV: error: undefined MMR: %s\n", str);
else
pr_crit("UV: error: undefined MMR: %s\n", str);
- return ~0ul; /* cause a machine fault */
+
+ /* Cause a machine fault: */
+ return ~0ul;
}
EXPORT_SYMBOL(uv_undefined);
@@ -85,18 +89,19 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr)
mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr));
val = *mmr;
early_iounmap(mmr, sizeof(*mmr));
+
return val;
}
static inline bool is_GRU_range(u64 start, u64 end)
{
if (gru_dist_base) {
- u64 su = start & gru_dist_umask; /* upper (incl pnode) bits */
- u64 sl = start & gru_dist_lmask; /* base offset bits */
+ u64 su = start & gru_dist_umask; /* Upper (incl pnode) bits */
+ u64 sl = start & gru_dist_lmask; /* Base offset bits */
u64 eu = end & gru_dist_umask;
u64 el = end & gru_dist_lmask;
- /* Must reside completely within a single GRU range */
+ /* Must reside completely within a single GRU range: */
return (sl == gru_dist_base && el == gru_dist_base &&
su >= gru_first_node_paddr &&
su <= gru_last_node_paddr &&
@@ -133,13 +138,14 @@ static int __init early_get_pnodeid(void)
break;
case UV4_HUB_PART_NUMBER:
uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
+ uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */
break;
}
uv_hub_info->hub_revision = uv_min_hub_revision_id;
uv_cpuid.pnode_mask = (1 << m_n_config.s.n_skt) - 1;
pnode = (node_id.s.node_id >> 1) & uv_cpuid.pnode_mask;
- uv_cpuid.gpa_shift = 46; /* default unless changed */
+ uv_cpuid.gpa_shift = 46; /* Default unless changed */
pr_info("UV: rev:%d part#:%x nodeid:%04x n_skt:%d pnmsk:%x pn:%x\n",
node_id.s.revision, node_id.s.part_number, node_id.s.node_id,
@@ -147,11 +153,12 @@ static int __init early_get_pnodeid(void)
return pnode;
}
-/* [copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
-#define SMT_LEVEL 0 /* leaf 0xb SMT level */
-#define INVALID_TYPE 0 /* leaf 0xb sub-leaf types */
-#define SMT_TYPE 1
-#define CORE_TYPE 2
+/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
+
+#define SMT_LEVEL 0 /* Leaf 0xb SMT level */
+#define INVALID_TYPE 0 /* Leaf 0xb sub-leaf types */
+#define SMT_TYPE 1
+#define CORE_TYPE 2
#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff)
#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f)
@@ -165,11 +172,13 @@ static void set_x2apic_bits(void)
pr_info("UV: CPU does not have CPUID.11\n");
return;
}
+
cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) {
pr_info("UV: CPUID.11 not implemented\n");
return;
}
+
sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
sub_index = 1;
do {
@@ -180,8 +189,9 @@ static void set_x2apic_bits(void)
}
sub_index++;
} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
- uv_cpuid.apicid_shift = 0;
- uv_cpuid.apicid_mask = (~(-1 << sid_shift));
+
+ uv_cpuid.apicid_shift = 0;
+ uv_cpuid.apicid_mask = (~(-1 << sid_shift));
uv_cpuid.socketid_shift = sid_shift;
}
@@ -192,10 +202,8 @@ static void __init early_get_apic_socketid_shift(void)
set_x2apic_bits();
- pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n",
- uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
- pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n",
- uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
+ pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
+ pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
}
/*
@@ -208,10 +216,8 @@ static void __init uv_set_apicid_hibit(void)
union uv1h_lb_target_physical_apic_id_mask_u apicid_mask;
if (is_uv1_hub()) {
- apicid_mask.v =
- uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
- uv_apicid_hibits =
- apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
+ apicid_mask.v = uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
+ uv_apicid_hibits = apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
}
}
@@ -220,20 +226,26 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
int pnodeid;
int uv_apic;
- if (strncmp(oem_id, "SGI", 3) != 0)
+ if (strncmp(oem_id, "SGI", 3) != 0) {
+ if (strncmp(oem_id, "NSGI", 4) == 0) {
+ uv_hubless_system = true;
+ pr_info("UV: OEM IDs %s/%s, HUBLESS\n",
+ oem_id, oem_table_id);
+ }
return 0;
+ }
if (numa_off) {
pr_err("UV: NUMA is off, disabling UV support\n");
return 0;
}
- /* Setup early hub type field in uv_hub_info for Node 0 */
+ /* Set up early hub type field in uv_hub_info for Node 0 */
uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
/*
* Determine UV arch type.
- * SGI: UV100/1000
+ * SGI: UV100/1000
* SGI2: UV2000/3000
* SGI3: UV300 (truncated to 4 chars because of different varieties)
* SGI4: UV400 (truncated to 4 chars because of different varieties)
@@ -249,31 +261,32 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
pnodeid = early_get_pnodeid();
early_get_apic_socketid_shift();
- x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
+
+ x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
x86_platform.nmi_init = uv_nmi_init;
- if (!strcmp(oem_table_id, "UVX")) { /* most common */
+ if (!strcmp(oem_table_id, "UVX")) {
+ /* This is the most common hardware variant: */
uv_system_type = UV_X2APIC;
uv_apic = 0;
- } else if (!strcmp(oem_table_id, "UVH")) { /* only UV1 systems */
+ } else if (!strcmp(oem_table_id, "UVH")) {
+ /* Only UV1 systems: */
uv_system_type = UV_NON_UNIQUE_APIC;
- __this_cpu_write(x2apic_extra_bits,
- pnodeid << uvh_apicid.s.pnode_shift);
+ __this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift);
uv_set_apicid_hibit();
uv_apic = 1;
- } else if (!strcmp(oem_table_id, "UVL")) { /* only used for */
- uv_system_type = UV_LEGACY_APIC; /* very small systems */
+ } else if (!strcmp(oem_table_id, "UVL")) {
+ /* Only used for very small systems: */
+ uv_system_type = UV_LEGACY_APIC;
uv_apic = 0;
} else {
goto badbios;
}
- pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n",
- oem_id, oem_table_id, uv_system_type,
- uv_min_hub_revision_id, uv_apic);
+ pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", oem_id, oem_table_id, uv_system_type, uv_min_hub_revision_id, uv_apic);
return uv_apic;
@@ -294,6 +307,12 @@ int is_uv_system(void)
}
EXPORT_SYMBOL_GPL(is_uv_system);
+int is_uv_hubless(void)
+{
+ return uv_hubless_system;
+}
+EXPORT_SYMBOL_GPL(is_uv_hubless);
+
void **__uv_hub_info_list;
EXPORT_SYMBOL_GPL(__uv_hub_info_list);
@@ -306,16 +325,18 @@ EXPORT_SYMBOL_GPL(uv_possible_blades);
unsigned long sn_rtc_cycles_per_second;
EXPORT_SYMBOL(sn_rtc_cycles_per_second);
-/* the following values are used for the per node hub info struct */
-static __initdata unsigned short *_node_to_pnode;
-static __initdata unsigned short _min_socket, _max_socket;
-static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len;
-static __initdata struct uv_gam_range_entry *uv_gre_table;
-static __initdata struct uv_gam_parameters *uv_gp_table;
-static __initdata unsigned short *_socket_to_node;
-static __initdata unsigned short *_socket_to_pnode;
-static __initdata unsigned short *_pnode_to_socket;
-static __initdata struct uv_gam_range_s *_gr_table;
+/* The following values are used for the per node hub info struct */
+static __initdata unsigned short *_node_to_pnode;
+static __initdata unsigned short _min_socket, _max_socket;
+static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len;
+static __initdata struct uv_gam_range_entry *uv_gre_table;
+static __initdata struct uv_gam_parameters *uv_gp_table;
+static __initdata unsigned short *_socket_to_node;
+static __initdata unsigned short *_socket_to_pnode;
+static __initdata unsigned short *_pnode_to_socket;
+
+static __initdata struct uv_gam_range_s *_gr_table;
+
#define SOCK_EMPTY ((unsigned short)~0)
extern int uv_hub_info_version(void)
@@ -324,7 +345,7 @@ extern int uv_hub_info_version(void)
}
EXPORT_SYMBOL(uv_hub_info_version);
-/* Build GAM range lookup table */
+/* Build GAM range lookup table: */
static __init void build_uv_gr_table(void)
{
struct uv_gam_range_entry *gre = uv_gre_table;
@@ -342,25 +363,24 @@ static __init void build_uv_gr_table(void)
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (gre->type == UV_GAM_RANGE_TYPE_HOLE) {
- if (!ram_limit) { /* mark hole between ram/non-ram */
+ if (!ram_limit) {
+ /* Mark hole between RAM/non-RAM: */
ram_limit = last_limit;
last_limit = gre->limit;
lsid++;
continue;
}
last_limit = gre->limit;
- pr_info("UV: extra hole in GAM RE table @%d\n",
- (int)(gre - uv_gre_table));
+ pr_info("UV: extra hole in GAM RE table @%d\n", (int)(gre - uv_gre_table));
continue;
}
if (_max_socket < gre->sockid) {
- pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n",
- gre->sockid, _max_socket,
- (int)(gre - uv_gre_table));
+ pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n", gre->sockid, _max_socket, (int)(gre - uv_gre_table));
continue;
}
sid = gre->sockid - _min_socket;
- if (lsid < sid) { /* new range */
+ if (lsid < sid) {
+ /* New range: */
grt = &_gr_table[indx];
grt->base = lindx;
grt->nasid = gre->nasid;
@@ -369,27 +389,32 @@ static __init void build_uv_gr_table(void)
lindx = indx++;
continue;
}
- if (lsid == sid && !ram_limit) { /* update range */
- if (grt->limit == last_limit) { /* .. if contiguous */
+ /* Update range: */
+ if (lsid == sid && !ram_limit) {
+ /* .. if contiguous: */
+ if (grt->limit == last_limit) {
grt->limit = last_limit = gre->limit;
continue;
}
}
- if (!ram_limit) { /* non-contiguous ram range */
+ /* Non-contiguous RAM range: */
+ if (!ram_limit) {
grt++;
grt->base = lindx;
grt->nasid = gre->nasid;
grt->limit = last_limit = gre->limit;
continue;
}
- grt++; /* non-contiguous/non-ram */
- grt->base = grt - _gr_table; /* base is this entry */
+ /* Non-contiguous/non-RAM: */
+ grt++;
+ /* base is this entry */
+ grt->base = grt - _gr_table;
grt->nasid = gre->nasid;
grt->limit = last_limit = gre->limit;
lsid++;
}
- /* shorten table if possible */
+ /* Shorten table if possible */
grt++;
i = grt - _gr_table;
if (i < _gr_table_len) {
@@ -403,16 +428,15 @@ static __init void build_uv_gr_table(void)
}
}
- /* display resultant gam range table */
+ /* Display resultant GAM range table: */
for (i = 0, grt = _gr_table; i < _gr_table_len; i++, grt++) {
+ unsigned long start, end;
int gb = grt->base;
- unsigned long start = gb < 0 ? 0 :
- (unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT;
- unsigned long end =
- (unsigned long)grt->limit << UV_GAM_RANGE_SHFT;
- pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n",
- i, grt->nasid, start, end, gb);
+ start = gb < 0 ? 0 : (unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT;
+ end = (unsigned long)grt->limit << UV_GAM_RANGE_SHFT;
+
+ pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n", i, grt->nasid, start, end, gb);
}
}
@@ -423,16 +447,19 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
pnode = uv_apicid_to_pnode(phys_apicid);
phys_apicid |= uv_apicid_hibits;
+
val = (1UL << UVH_IPI_INT_SEND_SHFT) |
(phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
APIC_DM_INIT;
+
uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
val = (1UL << UVH_IPI_INT_SEND_SHFT) |
(phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
APIC_DM_STARTUP;
+
uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
return 0;
@@ -566,7 +593,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = {
.apic_id_registered = uv_apic_id_registered,
.irq_delivery_mode = dest_Fixed,
- .irq_dest_mode = 0, /* physical */
+ .irq_dest_mode = 0, /* Physical */
.target_cpus = online_target_cpus,
.disable_esr = 0,
@@ -627,23 +654,22 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
switch (i) {
case 0:
m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR;
- m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR;
+ m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR;
break;
case 1:
m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR;
- m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR;
+ m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR;
break;
case 2:
m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR;
- m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR;
+ m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR;
break;
}
alias.v = uv_read_local_mmr(m_overlay);
if (alias.s.enable && alias.s.base == 0) {
*size = (1UL << alias.s.m_alias);
redirect.v = uv_read_local_mmr(m_redirect);
- *base = (unsigned long)redirect.s.dest_base
- << DEST_SHIFT;
+ *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
return;
}
}
@@ -652,8 +678,7 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
enum map_type {map_wb, map_uc};
-static __init void map_high(char *id, unsigned long base, int pshift,
- int bshift, int max_pnode, enum map_type map_type)
+static __init void map_high(char *id, unsigned long base, int pshift, int bshift, int max_pnode, enum map_type map_type)
{
unsigned long bytes, paddr;
@@ -678,16 +703,19 @@ static __init void map_gru_distributed(unsigned long c)
int nid;
gru.v = c;
- /* only base bits 42:28 relevant in dist mode */
+
+ /* Only base bits 42:28 relevant in dist mode */
gru_dist_base = gru.v & 0x000007fff0000000UL;
if (!gru_dist_base) {
pr_info("UV: Map GRU_DIST base address NULL\n");
return;
}
+
bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1);
gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1);
gru_dist_base &= gru_dist_lmask; /* Clear bits above M */
+
for_each_online_node(nid) {
paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) |
gru_dist_base;
@@ -695,11 +723,12 @@ static __init void map_gru_distributed(unsigned long c)
gru_first_node_paddr = min(paddr, gru_first_node_paddr);
gru_last_node_paddr = max(paddr, gru_last_node_paddr);
}
+
/* Save upper (63:M) bits of address only for is_GRU_range */
gru_first_node_paddr &= gru_dist_umask;
gru_last_node_paddr &= gru_dist_umask;
- pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n",
- gru_dist_base, gru_first_node_paddr, gru_last_node_paddr);
+
+ pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", gru_dist_base, gru_first_node_paddr, gru_last_node_paddr);
}
static __init void map_gru_high(int max_pnode)
@@ -719,6 +748,7 @@ static __init void map_gru_high(int max_pnode)
map_gru_distributed(gru.v);
return;
}
+
base = (gru.v & mask) >> shift;
map_high("GRU", base, shift, shift, max_pnode, map_wb);
gru_start_paddr = ((u64)base << shift);
@@ -772,8 +802,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
id = mmiohs[index].id;
overlay.v = uv_read_local_mmr(mmiohs[index].overlay);
- pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n",
- id, overlay.v, overlay.s3.base, overlay.s3.m_io);
+
+ pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io);
if (!overlay.s3.enable) {
pr_info("UV: %s disabled\n", id);
return;
@@ -784,7 +814,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
m_io = overlay.s3.m_io;
mmr = mmiohs[index].redirect;
n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
- min_pnode *= 2; /* convert to NASID */
+ /* Convert to NASID: */
+ min_pnode *= 2;
max_pnode *= 2;
max_io = lnasid = fi = li = -1;
@@ -793,16 +824,18 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
redirect.v = uv_read_local_mmr(mmr + i * 8);
nasid = redirect.s3.nasid;
+ /* Invalid NASID: */
if (nasid < min_pnode || max_pnode < nasid)
- nasid = -1; /* invalid NASID */
+ nasid = -1;
if (nasid == lnasid) {
li = i;
- if (i != n-1) /* last entry check */
+ /* Last entry check: */
+ if (i != n-1)
continue;
}
- /* check if we have a cached (or last) redirect to print */
+ /* Check if we have a cached (or last) redirect to print: */
if (lnasid != -1 || (i == n-1 && nasid != -1)) {
unsigned long addr1, addr2;
int f, l;
@@ -814,12 +847,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
f = fi;
l = li;
}
- addr1 = (base << shift) +
- f * (1ULL << m_io);
- addr2 = (base << shift) +
- (l + 1) * (1ULL << m_io);
- pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n",
- id, fi, li, lnasid, addr1, addr2);
+ addr1 = (base << shift) + f * (1ULL << m_io);
+ addr2 = (base << shift) + (l + 1) * (1ULL << m_io);
+ pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2);
if (max_io < l)
max_io = l;
}
@@ -827,8 +857,7 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
lnasid = nasid;
}
- pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n",
- id, base, shift, m_io, max_io);
+ pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", id, base, shift, m_io, max_io);
if (max_io >= 0)
map_high(id, base, shift, m_io, max_io, map_uc);
@@ -841,36 +870,35 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
int shift, enable, m_io, n_io;
if (is_uv3_hub() || is_uv4_hub()) {
- /* Map both MMIOH Regions */
+ /* Map both MMIOH regions: */
map_mmioh_high_uv3(0, min_pnode, max_pnode);
map_mmioh_high_uv3(1, min_pnode, max_pnode);
return;
}
if (is_uv1_hub()) {
- mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
- shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
- mmioh.v = uv_read_local_mmr(mmr);
- enable = !!mmioh.s1.enable;
- base = mmioh.s1.base;
- m_io = mmioh.s1.m_io;
- n_io = mmioh.s1.n_io;
+ mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
+ shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+ mmioh.v = uv_read_local_mmr(mmr);
+ enable = !!mmioh.s1.enable;
+ base = mmioh.s1.base;
+ m_io = mmioh.s1.m_io;
+ n_io = mmioh.s1.n_io;
} else if (is_uv2_hub()) {
- mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
- shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
- mmioh.v = uv_read_local_mmr(mmr);
- enable = !!mmioh.s2.enable;
- base = mmioh.s2.base;
- m_io = mmioh.s2.m_io;
- n_io = mmioh.s2.n_io;
- } else
+ mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
+ shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+ mmioh.v = uv_read_local_mmr(mmr);
+ enable = !!mmioh.s2.enable;
+ base = mmioh.s2.base;
+ m_io = mmioh.s2.m_io;
+ n_io = mmioh.s2.n_io;
+ } else {
return;
+ }
if (enable) {
max_pnode &= (1 << n_io) - 1;
- pr_info(
- "UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n",
- base, shift, m_io, n_io, max_pnode);
+ pr_info("UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", base, shift, m_io, n_io, max_pnode);
map_high("MMIOH", base, shift, m_io, max_pnode, map_uc);
} else {
pr_info("UV: MMIOH disabled\n");
@@ -888,16 +916,16 @@ static __init void uv_rtc_init(void)
long status;
u64 ticks_per_sec;
- status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK,
- &ticks_per_sec);
+ status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec);
+
if (status != BIOS_STATUS_SUCCESS || ticks_per_sec < 100000) {
- printk(KERN_WARNING
- "unable to determine platform RTC clock frequency, "
- "guessing.\n");
- /* BIOS gives wrong value for clock freq. so guess */
+ pr_warn("UV: unable to determine platform RTC clock frequency, guessing.\n");
+
+ /* BIOS gives wrong value for clock frequency, so guess: */
sn_rtc_cycles_per_second = 1000000000000UL / 30000UL;
- } else
+ } else {
sn_rtc_cycles_per_second = ticks_per_sec;
+ }
}
/*
@@ -908,19 +936,19 @@ static void uv_heartbeat(unsigned long ignored)
struct timer_list *timer = &uv_scir_info->timer;
unsigned char bits = uv_scir_info->state;
- /* flip heartbeat bit */
+ /* Flip heartbeat bit: */
bits ^= SCIR_CPU_HEARTBEAT;
- /* is this cpu idle? */
+ /* Is this CPU idle? */
if (idle_cpu(raw_smp_processor_id()))
bits &= ~SCIR_CPU_ACTIVITY;
else
bits |= SCIR_CPU_ACTIVITY;
- /* update system controller interface reg */
+ /* Update system controller interface reg: */
uv_set_scir_bits(bits);
- /* enable next timer period */
+ /* Enable next timer period: */
mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
}
@@ -935,7 +963,7 @@ static int uv_heartbeat_enable(unsigned int cpu)
add_timer_on(timer, cpu);
uv_cpu_scir_info(cpu)->enabled = 1;
- /* also ensure that boot cpu is enabled */
+ /* Also ensure that boot CPU is enabled: */
cpu = 0;
}
return 0;
@@ -968,9 +996,11 @@ static __init int uv_init_heartbeat(void)
{
int cpu;
- if (is_uv_system())
+ if (is_uv_system()) {
for_each_online_cpu(cpu)
uv_heartbeat_enable(cpu);
+ }
+
return 0;
}
@@ -979,14 +1009,10 @@ late_initcall(uv_init_heartbeat);
#endif /* !CONFIG_HOTPLUG_CPU */
/* Direct Legacy VGA I/O traffic to designated IOH */
-int uv_set_vga_state(struct pci_dev *pdev, bool decode,
- unsigned int command_bits, u32 flags)
+int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags)
{
int domain, bus, rc;
- PR_DEVEL("devfn %x decode %d cmd %x flags %d\n",
- pdev->devfn, decode, command_bits, flags);
-
if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
return 0;
@@ -997,13 +1023,12 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode,
bus = pdev->bus->number;
rc = uv_bios_set_legacy_vga_target(decode, domain, bus);
- PR_DEVEL("vga decode %d %x:%x, rc: %d\n", decode, domain, bus, rc);
return rc;
}
/*
- * Called on each cpu to initialize the per_cpu UV data area.
+ * Called on each CPU to initialize the per_cpu UV data area.
* FIXME: hotplug not supported yet
*/
void uv_cpu_init(void)
@@ -1030,90 +1055,79 @@ static void get_mn(struct mn *mnp)
union uvh_rh_gam_config_mmr_u m_n_config;
union uv3h_gr0_gam_gr_config_u m_gr_config;
- m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR);
- mnp->n_val = m_n_config.s.n_skt;
+ /* Make sure the whole structure is well initialized: */
+ memset(mnp, 0, sizeof(*mnp));
+
+ m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR);
+ mnp->n_val = m_n_config.s.n_skt;
+
if (is_uv4_hub()) {
- mnp->m_val = 0;
- mnp->n_lshift = 0;
+ mnp->m_val = 0;
+ mnp->n_lshift = 0;
} else if (is_uv3_hub()) {
- mnp->m_val = m_n_config.s3.m_skt;
- m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
- mnp->n_lshift = m_gr_config.s3.m_skt;
+ mnp->m_val = m_n_config.s3.m_skt;
+ m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
+ mnp->n_lshift = m_gr_config.s3.m_skt;
} else if (is_uv2_hub()) {
- mnp->m_val = m_n_config.s2.m_skt;
- mnp->n_lshift = mnp->m_val == 40 ? 40 : 39;
+ mnp->m_val = m_n_config.s2.m_skt;
+ mnp->n_lshift = mnp->m_val == 40 ? 40 : 39;
} else if (is_uv1_hub()) {
- mnp->m_val = m_n_config.s1.m_skt;
- mnp->n_lshift = mnp->m_val;
+ mnp->m_val = m_n_config.s1.m_skt;
+ mnp->n_lshift = mnp->m_val;
}
mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0;
}
-void __init uv_init_hub_info(struct uv_hub_info_s *hub_info)
+void __init uv_init_hub_info(struct uv_hub_info_s *hi)
{
- struct mn mn = {0}; /* avoid unitialized warnings */
union uvh_node_id_u node_id;
+ struct mn mn;
get_mn(&mn);
- hub_info->m_val = mn.m_val;
- hub_info->n_val = mn.n_val;
- hub_info->m_shift = mn.m_shift;
- hub_info->n_lshift = mn.n_lshift ? mn.n_lshift : 0;
-
- hub_info->hub_revision = uv_hub_info->hub_revision;
- hub_info->pnode_mask = uv_cpuid.pnode_mask;
- hub_info->min_pnode = _min_pnode;
- hub_info->min_socket = _min_socket;
- hub_info->pnode_to_socket = _pnode_to_socket;
- hub_info->socket_to_node = _socket_to_node;
- hub_info->socket_to_pnode = _socket_to_pnode;
- hub_info->gr_table_len = _gr_table_len;
- hub_info->gr_table = _gr_table;
- hub_info->gpa_mask = mn.m_val ?
+ hi->gpa_mask = mn.m_val ?
(1UL << (mn.m_val + mn.n_val)) - 1 :
(1UL << uv_cpuid.gpa_shift) - 1;
- node_id.v = uv_read_local_mmr(UVH_NODE_ID);
- hub_info->gnode_extra =
- (node_id.s.node_id & ~((1 << mn.n_val) - 1)) >> 1;
-
- hub_info->gnode_upper =
- ((unsigned long)hub_info->gnode_extra << mn.m_val);
+ hi->m_val = mn.m_val;
+ hi->n_val = mn.n_val;
+ hi->m_shift = mn.m_shift;
+ hi->n_lshift = mn.n_lshift ? mn.n_lshift : 0;
+ hi->hub_revision = uv_hub_info->hub_revision;
+ hi->pnode_mask = uv_cpuid.pnode_mask;
+ hi->min_pnode = _min_pnode;
+ hi->min_socket = _min_socket;
+ hi->pnode_to_socket = _pnode_to_socket;
+ hi->socket_to_node = _socket_to_node;
+ hi->socket_to_pnode = _socket_to_pnode;
+ hi->gr_table_len = _gr_table_len;
+ hi->gr_table = _gr_table;
+
+ node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+ uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val);
+ hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1;
+ hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val;
if (uv_gp_table) {
- hub_info->global_mmr_base = uv_gp_table->mmr_base;
- hub_info->global_mmr_shift = uv_gp_table->mmr_shift;
- hub_info->global_gru_base = uv_gp_table->gru_base;
- hub_info->global_gru_shift = uv_gp_table->gru_shift;
- hub_info->gpa_shift = uv_gp_table->gpa_shift;
- hub_info->gpa_mask = (1UL << hub_info->gpa_shift) - 1;
+ hi->global_mmr_base = uv_gp_table->mmr_base;
+ hi->global_mmr_shift = uv_gp_table->mmr_shift;
+ hi->global_gru_base = uv_gp_table->gru_base;
+ hi->global_gru_shift = uv_gp_table->gru_shift;
+ hi->gpa_shift = uv_gp_table->gpa_shift;
+ hi->gpa_mask = (1UL << hi->gpa_shift) - 1;
} else {
- hub_info->global_mmr_base =
- uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
- ~UV_MMR_ENABLE;
- hub_info->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT;
+ hi->global_mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE;
+ hi->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT;
}
- get_lowmem_redirect(
- &hub_info->lowmem_remap_base, &hub_info->lowmem_remap_top);
-
- hub_info->apic_pnode_shift = uv_cpuid.socketid_shift;
-
- /* show system specific info */
- pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n",
- hub_info->n_val, hub_info->m_val,
- hub_info->m_shift, hub_info->n_lshift);
-
- pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n",
- hub_info->gpa_mask, hub_info->gpa_shift,
- hub_info->pnode_mask, hub_info->apic_pnode_shift);
+ get_lowmem_redirect(&hi->lowmem_remap_base, &hi->lowmem_remap_top);
- pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n",
- hub_info->global_mmr_base, hub_info->global_mmr_shift,
- hub_info->global_gru_base, hub_info->global_gru_shift);
+ hi->apic_pnode_shift = uv_cpuid.socketid_shift;
- pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n",
- hub_info->gnode_upper, hub_info->gnode_extra);
+ /* Show system specific info: */
+ pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n", hi->n_val, hi->m_val, hi->m_shift, hi->n_lshift);
+ pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n", hi->gpa_mask, hi->gpa_shift, hi->pnode_mask, hi->apic_pnode_shift);
+ pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n", hi->global_mmr_base, hi->global_mmr_shift, hi->global_gru_base, hi->global_gru_shift);
+ pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n", hi->gnode_upper, hi->gnode_extra);
}
static void __init decode_gam_params(unsigned long ptr)
@@ -1139,12 +1153,9 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (!index) {
pr_info("UV: GAM Range Table...\n");
- pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n",
- "Range", "", "Size", "Type", "NASID",
- "SID", "PN");
+ pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
}
- pr_info(
- "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n",
+ pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n",
index++,
(unsigned long)lgre << UV_GAM_RANGE_SHFT,
(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
@@ -1162,29 +1173,32 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
if (pnode_max < gre->pnode)
pnode_max = gre->pnode;
}
- _min_socket = sock_min;
- _max_socket = sock_max;
- _min_pnode = pnode_min;
- _max_pnode = pnode_max;
- _gr_table_len = index;
- pr_info(
- "UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n",
- index, _min_socket, _max_socket, _min_pnode, _max_pnode);
+ _min_socket = sock_min;
+ _max_socket = sock_max;
+ _min_pnode = pnode_min;
+ _max_pnode = pnode_max;
+ _gr_table_len = index;
+
+ pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n", index, _min_socket, _max_socket, _min_pnode, _max_pnode);
}
-static void __init decode_uv_systab(void)
+static int __init decode_uv_systab(void)
{
struct uv_systab *st;
int i;
+ if (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE)
+ return 0; /* No extended UVsystab required */
+
st = uv_systab;
- if ((!st || st->revision < UV_SYSTAB_VERSION_UV4) && !is_uv4_hub())
- return;
- if (st->revision != UV_SYSTAB_VERSION_UV4_LATEST) {
- pr_crit(
- "UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n",
- st->revision, UV_SYSTAB_VERSION_UV4_LATEST);
- BUG();
+ if ((!st) || (st->revision < UV_SYSTAB_VERSION_UV4_LATEST)) {
+ int rev = st ? st->revision : 0;
+
+ pr_err("UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n", rev, UV_SYSTAB_VERSION_UV4_LATEST);
+ pr_err("UV: Cannot support UV operations, switching to generic PC\n");
+ uv_system_type = UV_NONE;
+
+ return -EINVAL;
}
for (i = 0; st->entry[i].type != UV_SYSTAB_TYPE_UNUSED; i++) {
@@ -1205,10 +1219,11 @@ static void __init decode_uv_systab(void)
break;
}
}
+ return 0;
}
/*
- * Setup physical blade translations from UVH_NODE_PRESENT_TABLE
+ * Set up physical blade translations from UVH_NODE_PRESENT_TABLE
* .. NB: UVH_NODE_PRESENT_TABLE is going away,
* .. being replaced by GAM Range Table
*/
@@ -1244,14 +1259,13 @@ static void __init build_socket_tables(void)
if (!gre) {
if (is_uv1_hub() || is_uv2_hub() || is_uv3_hub()) {
pr_info("UV: No UVsystab socket table, ignoring\n");
- return; /* not required */
+ return;
}
- pr_crit(
- "UV: Error: UVsystab address translations not available!\n");
+ pr_crit("UV: Error: UVsystab address translations not available!\n");
BUG();
}
- /* build socket id -> node id, pnode */
+ /* Build socket id -> node id, pnode */
num = maxsock - minsock + 1;
bytes = num * sizeof(_socket_to_node[0]);
_socket_to_node = kmalloc(bytes, GFP_KERNEL);
@@ -1268,27 +1282,27 @@ static void __init build_socket_tables(void)
for (i = 0; i < nump; i++)
_pnode_to_socket[i] = SOCK_EMPTY;
- /* fill in pnode/node/addr conversion list values */
+ /* Fill in pnode/node/addr conversion list values: */
pr_info("UV: GAM Building socket/pnode conversion tables\n");
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
continue;
i = gre->sockid - minsock;
+ /* Duplicate: */
if (_socket_to_pnode[i] != SOCK_EMPTY)
- continue; /* duplicate */
+ continue;
_socket_to_pnode[i] = gre->pnode;
i = gre->pnode - minpnode;
_pnode_to_socket[i] = gre->sockid;
- pr_info(
- "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
+ pr_info("UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
gre->sockid, gre->type, gre->nasid,
_socket_to_pnode[gre->sockid - minsock],
_pnode_to_socket[gre->pnode - minpnode]);
}
- /* Set socket -> node values */
+ /* Set socket -> node values: */
lnid = -1;
for_each_present_cpu(cpu) {
int nid = cpu_to_node(cpu);
@@ -1304,7 +1318,7 @@ static void __init build_socket_tables(void)
sockid, apicid, nid);
}
- /* Setup physical blade to pnode translation from GAM Range Table */
+ /* Set up physical blade to pnode translation from GAM Range Table: */
bytes = num_possible_nodes() * sizeof(_node_to_pnode[0]);
_node_to_pnode = kmalloc(bytes, GFP_KERNEL);
BUG_ON(!_node_to_pnode);
@@ -1314,8 +1328,7 @@ static void __init build_socket_tables(void)
for (sockid = minsock; sockid <= maxsock; sockid++) {
if (lnid == _socket_to_node[sockid - minsock]) {
- _node_to_pnode[lnid] =
- _socket_to_pnode[sockid - minsock];
+ _node_to_pnode[lnid] = _socket_to_pnode[sockid - minsock];
break;
}
}
@@ -1332,8 +1345,7 @@ static void __init build_socket_tables(void)
pr_info("UV: Checking socket->node/pnode for identity maps\n");
if (minsock == 0) {
for (i = 0; i < num; i++)
- if (_socket_to_node[i] == SOCK_EMPTY ||
- i != _socket_to_node[i])
+ if (_socket_to_node[i] == SOCK_EMPTY || i != _socket_to_node[i])
break;
if (i >= num) {
kfree(_socket_to_node);
@@ -1354,7 +1366,7 @@ static void __init build_socket_tables(void)
}
}
-void __init uv_system_init(void)
+static void __init uv_system_init_hub(void)
{
struct uv_hub_info_s hub_info = {0};
int bytes, cpu, nodeid;
@@ -1372,8 +1384,13 @@ void __init uv_system_init(void)
map_low_mmrs();
- uv_bios_init(); /* get uv_systab for decoding */
- decode_uv_systab();
+ /* Get uv_systab for decoding: */
+ uv_bios_init();
+
+ /* If there's an UVsystab problem then abort UV init: */
+ if (decode_uv_systab() < 0)
+ return;
+
build_socket_tables();
build_uv_gr_table();
uv_init_hub_info(&hub_info);
@@ -1381,14 +1398,10 @@ void __init uv_system_init(void)
if (!_node_to_pnode)
boot_init_possible_blades(&hub_info);
- /* uv_num_possible_blades() is really the hub count */
- pr_info("UV: Found %d hubs, %d nodes, %d cpus\n",
- uv_num_possible_blades(),
- num_possible_nodes(),
- num_possible_cpus());
+ /* uv_num_possible_blades() is really the hub count: */
+ pr_info("UV: Found %d hubs, %d nodes, %d CPUs\n", uv_num_possible_blades(), num_possible_nodes(), num_possible_cpus());
- uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id,
- &sn_region_size, &system_serial_number);
+ uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id, &sn_region_size, &system_serial_number);
hub_info.coherency_domain_number = sn_coherency_id;
uv_rtc_init();
@@ -1401,33 +1414,31 @@ void __init uv_system_init(void)
struct uv_hub_info_s *new_hub;
if (__uv_hub_info_list[nodeid]) {
- pr_err("UV: Node %d UV HUB already initialized!?\n",
- nodeid);
+ pr_err("UV: Node %d UV HUB already initialized!?\n", nodeid);
BUG();
}
/* Allocate new per hub info list */
- new_hub = (nodeid == 0) ?
- &uv_hub_info_node0 :
- kzalloc_node(bytes, GFP_KERNEL, nodeid);
+ new_hub = (nodeid == 0) ? &uv_hub_info_node0 : kzalloc_node(bytes, GFP_KERNEL, nodeid);
BUG_ON(!new_hub);
__uv_hub_info_list[nodeid] = new_hub;
new_hub = uv_hub_info_list(nodeid);
BUG_ON(!new_hub);
*new_hub = hub_info;
- /* Use information from GAM table if available */
+ /* Use information from GAM table if available: */
if (_node_to_pnode)
new_hub->pnode = _node_to_pnode[nodeid];
- else /* Fill in during cpu loop */
+ else /* Or fill in during CPU loop: */
new_hub->pnode = 0xffff;
+
new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
new_hub->memory_nid = -1;
new_hub->nr_possible_cpus = 0;
new_hub->nr_online_cpus = 0;
}
- /* Initialize per cpu info */
+ /* Initialize per CPU info: */
for_each_possible_cpu(cpu) {
int apicid = per_cpu(x86_cpu_to_apicid, cpu);
int numa_node_id;
@@ -1438,22 +1449,24 @@ void __init uv_system_init(void)
pnode = uv_apicid_to_pnode(apicid);
uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
- uv_cpu_info_per(cpu)->blade_cpu_id =
- uv_cpu_hub_info(cpu)->nr_possible_cpus++;
+ uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
if (uv_cpu_hub_info(cpu)->memory_nid == -1)
uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
- if (nodeid != numa_node_id && /* init memoryless node */
+
+ /* Init memoryless node: */
+ if (nodeid != numa_node_id &&
uv_hub_info_list(numa_node_id)->pnode == 0xffff)
uv_hub_info_list(numa_node_id)->pnode = pnode;
else if (uv_cpu_hub_info(cpu)->pnode == 0xffff)
uv_cpu_hub_info(cpu)->pnode = pnode;
+
uv_cpu_scir_info(cpu)->offset = uv_scir_offset(apicid);
}
for_each_node(nodeid) {
unsigned short pnode = uv_hub_info_list(nodeid)->pnode;
- /* Add pnode info for pre-GAM list nodes without cpus */
+ /* Add pnode info for pre-GAM list nodes without CPUs: */
if (pnode == 0xffff) {
unsigned long paddr;
@@ -1479,15 +1492,30 @@ void __init uv_system_init(void)
uv_scir_register_cpu_notifier();
proc_mkdir("sgi_uv", NULL);
- /* register Legacy VGA I/O redirection handler */
+ /* Register Legacy VGA I/O redirection handler: */
pci_register_set_vga_state(uv_set_vga_state);
/*
* For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
- * EFI is not enabled in the kdump kernel.
+ * EFI is not enabled in the kdump kernel:
*/
if (is_kdump_kernel())
reboot_type = BOOT_ACPI;
}
+/*
+ * There is a small amount of UV specific code needed to initialize a
+ * UV system that does not have a "UV HUB" (referred to as "hubless").
+ */
+void __init uv_system_init(void)
+{
+ if (likely(!is_uv_system() && !is_uv_hubless()))
+ return;
+
+ if (is_uv_system())
+ uv_system_init_hub();
+ else
+ uv_nmi_setup_hubless();
+}
+
apic_driver(apic_x2apic_uv_x);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 45d44c173cf9..4a7080c84a5a 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev,
{
static int use_apm_idle; /* = 0 */
static unsigned int last_jiffies; /* = 0 */
- static unsigned int last_stime; /* = 0 */
- cputime_t stime, utime;
+ static u64 last_stime; /* = 0 */
+ u64 stime, utime;
int apm_idle_done = 0;
unsigned int jiffies_since_last_check = jiffies - last_jiffies;
@@ -919,7 +919,7 @@ recalc:
} else if (jiffies_since_last_check > idle_period) {
unsigned int idle_percentage;
- idle_percentage = cputime_to_jiffies(stime - last_stime);
+ idle_percentage = nsecs_to_jiffies(stime - last_stime);
idle_percentage *= 100;
idle_percentage /= jiffies_since_last_check;
use_apm_idle = (idle_percentage > idle_threshold);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index c62e015b126c..de827d6ac8c2 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -81,6 +81,7 @@ void common(void) {
BLANK();
OFFSET(BP_scratch, boot_params, scratch);
+ OFFSET(BP_secure_boot, boot_params, secure_boot);
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..4e95b2e0d95f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ u32 eax, ebx, ecx, edx;
- node_id = cpuid_ecx(0x8000001e) & 7;
+ cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+ node_id = ecx & 0xff;
+ smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+ if (c->x86 == 0x15)
+ c->cu_id = ebx & 0xff;
+
+ if (c->x86 >= 0x17) {
+ c->cpu_core_id = ebx & 0xff;
+
+ if (smp_num_siblings > 1)
+ c->x86_max_cores /= smp_num_siblings;
+ }
/*
* We may have multiple LLCs if L3 caches exist, so check if we
@@ -541,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (!check_tsc_unstable())
- set_sched_clock_stable();
+ if (check_tsc_unstable())
+ clear_sched_clock_stable();
+ } else {
+ clear_sched_clock_stable();
}
/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 1661d8ec9280..2c234a6d94c4 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,5 +1,5 @@
-#include <linux/bitops.h>
-#include <linux/kernel.h>
+
+#include <linux/sched.h>
#include <asm/cpufeature.h>
#include <asm/e820.h>
@@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#endif
+
+ clear_sched_clock_stable();
}
static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bab7a8a4293..f07005e6f461 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -35,6 +35,7 @@
#include <asm/desc.h>
#include <asm/fpu/internal.h>
#include <asm/mtrr.h>
+#include <asm/hwcap2.h>
#include <linux/numa.h>
#include <asm/asm.h>
#include <asm/bugs.h>
@@ -51,6 +52,8 @@
#include "cpu.h"
+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;
@@ -83,6 +86,7 @@ static void default_init(struct cpuinfo_x86 *c)
strcpy(c->x86_model_id, "386");
}
#endif
+ clear_sched_clock_stable();
}
static const struct cpu_dev default_cpu = {
@@ -655,6 +659,16 @@ void cpu_detect(struct cpuinfo_x86 *c)
}
}
+static void apply_forced_caps(struct cpuinfo_x86 *c)
+{
+ int i;
+
+ for (i = 0; i < NCAPINTS; i++) {
+ c->x86_capability[i] &= ~cpu_caps_cleared[i];
+ c->x86_capability[i] |= cpu_caps_set[i];
+ }
+}
+
void get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
@@ -748,6 +762,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
init_scattered_cpuid_features(c);
+
+ /*
+ * Clear/Set all flags overridden by options, after probe.
+ * This needs to happen each time we re-probe, which may happen
+ * several times during CPU initialization.
+ */
+ apply_forced_caps(c);
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -801,14 +822,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
memset(&c->x86_capability, 0, sizeof c->x86_capability);
c->extended_cpuid_level = 0;
- if (!have_cpuid_p())
- identify_cpu_without_cpuid(c);
-
/* cyrix could have cpuid enabled via c_identify()*/
if (have_cpuid_p()) {
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
+ setup_force_cpu_cap(X86_FEATURE_CPUID);
if (this_cpu->c_early_init)
this_cpu->c_early_init(c);
@@ -818,6 +837,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
if (this_cpu->c_bsp_init)
this_cpu->c_bsp_init(c);
+ } else {
+ identify_cpu_without_cpuid(c);
+ setup_clear_cpu_cap(X86_FEATURE_CPUID);
}
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
@@ -1015,6 +1037,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
c->x86_coreid_bits = 0;
+ c->cu_id = 0xff;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
c->x86_phys_bits = 36;
@@ -1034,10 +1057,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
this_cpu->c_identify(c);
/* Clear/Set all flags overridden by options, after probe */
- for (i = 0; i < NCAPINTS; i++) {
- c->x86_capability[i] &= ~cpu_caps_cleared[i];
- c->x86_capability[i] |= cpu_caps_set[i];
- }
+ apply_forced_caps(c);
#ifdef CONFIG_X86_64
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
@@ -1055,6 +1075,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
*/
if (this_cpu->c_init)
this_cpu->c_init(c);
+ else
+ clear_sched_clock_stable();
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
@@ -1096,10 +1118,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
* Clear/Set all flags overridden by options, need do it
* before following smp all cpus cap AND.
*/
- for (i = 0; i < NCAPINTS; i++) {
- c->x86_capability[i] &= ~cpu_caps_cleared[i];
- c->x86_capability[i] |= cpu_caps_set[i];
- }
+ apply_forced_caps(c);
/*
* On SMP, boot_cpu_data holds the common feature set between
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index bd9dcd6b712d..47416f959a48 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -9,6 +9,7 @@
#include <asm/pci-direct.h>
#include <asm/tsc.h>
#include <asm/cpufeature.h>
+#include <linux/sched.h>
#include "cpu.h"
@@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
break;
}
+ clear_sched_clock_stable();
}
static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 203f860d2ab3..017ecd3bb553 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -15,6 +15,8 @@
#include <asm/cpu.h>
#include <asm/intel-family.h>
#include <asm/microcode_intel.h>
+#include <asm/hwcap2.h>
+#include <asm/elf.h>
#ifdef CONFIG_X86_64
#include <linux/topology.h>
@@ -62,6 +64,46 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
}
}
+static bool ring3mwait_disabled __read_mostly;
+
+static int __init ring3mwait_disable(char *__unused)
+{
+ ring3mwait_disabled = true;
+ return 0;
+}
+__setup("ring3mwait=disable", ring3mwait_disable);
+
+static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
+{
+ /*
+ * Ring 3 MONITOR/MWAIT feature cannot be detected without
+ * cpu model and family comparison.
+ */
+ if (c->x86 != 6)
+ return;
+ switch (c->x86_model) {
+ case INTEL_FAM6_XEON_PHI_KNL:
+ case INTEL_FAM6_XEON_PHI_KNM:
+ break;
+ default:
+ return;
+ }
+
+ if (ring3mwait_disabled) {
+ msr_clear_bit(MSR_MISC_FEATURE_ENABLES,
+ MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+ return;
+ }
+
+ msr_set_bit(MSR_MISC_FEATURE_ENABLES,
+ MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+
+ set_cpu_cap(c, X86_FEATURE_RING3MWAIT);
+
+ if (c == &boot_cpu_data)
+ ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
+}
+
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
@@ -119,8 +161,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (!check_tsc_unstable())
- set_sched_clock_stable();
+ if (check_tsc_unstable())
+ clear_sched_clock_stable();
+ } else {
+ clear_sched_clock_stable();
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
@@ -560,6 +604,8 @@ static void init_intel(struct cpuinfo_x86 *c)
detect_vmx_virtcap(c);
init_intel_energy_perf(c);
+
+ probe_xeon_phi_r3mwait(c);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 83f1a98d37db..2eee85379689 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
if (severity >= GHES_SEV_RECOVERABLE)
m.status |= MCI_STATUS_UC;
- if (severity >= GHES_SEV_PANIC)
+
+ if (severity >= GHES_SEV_PANIC) {
m.status |= MCI_STATUS_PCC;
+ m.tsc = rdtsc();
+ }
m.addr = mem_err->physical_addr;
mce_log(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 93d824ec3120..1e5a50c11d3c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void)
return new_head.first;
}
-void mce_gen_pool_process(void)
+void mce_gen_pool_process(struct work_struct *__unused)
{
struct llist_node *head;
struct mce_evt_llist *node, *tmp;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 517619ea6498..99165b206df3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -152,7 +152,6 @@ static void raise_mce(struct mce *m)
if (context == MCJ_CTX_RANDOM)
return;
-#ifdef CONFIG_X86_LOCAL_APIC
if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
unsigned long start;
int cpu;
@@ -192,9 +191,7 @@ static void raise_mce(struct mce *m)
raise_local();
put_cpu();
put_online_cpus();
- } else
-#endif
- {
+ } else {
preempt_disable();
raise_local();
preempt_enable();
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index cd74a3f00aea..903043e6a62b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -31,7 +31,7 @@ struct mce_evt_llist {
struct mce mce;
};
-void mce_gen_pool_process(void);
+void mce_gen_pool_process(struct work_struct *__unused);
bool mce_gen_pool_empty(void);
int mce_gen_pool_add(struct mce *mce);
int mce_gen_pool_init(void);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 00ef43233e03..8e9725c607ea 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -128,7 +128,6 @@ void mce_setup(struct mce *m)
{
memset(m, 0, sizeof(struct mce));
m->cpu = m->extcpu = smp_processor_id();
- m->tsc = rdtsc();
/* We hope get_seconds stays lockless */
m->time = get_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb)
{
atomic_inc(&num_notifiers);
- /* Ensure SRAO notifier has the highest priority in the decode chain. */
- if (nb != &mce_srao_nb && nb->priority == INT_MAX)
- nb->priority -= 1;
+ WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
@@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
}
static struct notifier_block mce_srao_nb = {
.notifier_call = srao_decode_notifier,
- .priority = INT_MAX,
+ .priority = MCE_PRIO_SRAO,
};
static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
@@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
static struct notifier_block mce_default_nb = {
.notifier_call = mce_default_notifier,
/* lowest prio, we want it to run last. */
- .priority = 0,
+ .priority = MCE_PRIO_LOWEST,
};
/*
@@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
mce_gather_info(&m, NULL);
- /*
- * m.tsc was set in mce_setup(). Clear it if not requested.
- *
- * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid
- * that dance.
- */
- if (!(flags & MCP_TIMESTAMP))
- m.tsc = 0;
+ if (flags & MCP_TIMESTAMP)
+ m.tsc = rdtsc();
for (i = 0; i < mca_cfg.banks; i++) {
if (!mce_banks[i].ctl || !test_bit(i, *b))
@@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
goto out;
mce_gather_info(&m, regs);
+ m.tsc = rdtsc();
final = this_cpu_ptr(&mces_seen);
*final = m;
@@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags)
#endif
/*
- * Action optional processing happens here (picking up
- * from the list of faulting pages that do_machine_check()
- * placed into the genpool).
- */
-static void mce_process_work(struct work_struct *dummy)
-{
- mce_gen_pool_process();
-}
-
-#ifdef CONFIG_X86_MCE_INTEL
-/***
- * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog
- * @cpu: The CPU on which the event occurred.
- * @status: Event status information
- *
- * This function should be called by the thermal interrupt after the
- * event has been processed and the decision was made to log the event
- * further.
- *
- * The status parameter will be saved to the 'status' field of 'struct mce'
- * and historically has been the register value of the
- * MSR_IA32_THERMAL_STATUS (Intel) msr.
- */
-void mce_log_therm_throt_event(__u64 status)
-{
- struct mce m;
-
- mce_setup(&m);
- m.bank = MCE_THERMAL_BANK;
- m.status = status;
- mce_log(&m);
-}
-#endif /* CONFIG_X86_MCE_INTEL */
-
-/*
* Periodic polling timer for "silent" machine check errors. If the
* poller finds an MCE, poll 2x faster. When the poller finds no more
* errors, poll 2x slower (up to check_interval seconds).
@@ -1373,20 +1330,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
-static void __restart_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct timer_list *t, unsigned long interval)
{
unsigned long when = jiffies + interval;
unsigned long flags;
local_irq_save(flags);
- if (timer_pending(t)) {
- if (time_before(when, t->expires))
- mod_timer(t, when);
- } else {
- t->expires = round_jiffies(when);
- add_timer_on(t, smp_processor_id());
- }
+ if (!timer_pending(t) || time_before(when, t->expires))
+ mod_timer(t, round_jiffies(when));
local_irq_restore(flags);
}
@@ -1421,7 +1373,7 @@ static void mce_timer_fn(unsigned long data)
done:
__this_cpu_write(mce_next_interval, iv);
- __restart_timer(t, iv);
+ __start_timer(t, iv);
}
/*
@@ -1432,7 +1384,7 @@ void mce_timer_kick(unsigned long interval)
struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned long iv = __this_cpu_read(mce_next_interval);
- __restart_timer(t, interval);
+ __start_timer(t, interval);
if (interval < iv)
__this_cpu_write(mce_next_interval, interval);
@@ -1779,17 +1731,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
}
}
-static void mce_start_timer(unsigned int cpu, struct timer_list *t)
+static void mce_start_timer(struct timer_list *t)
{
unsigned long iv = check_interval * HZ;
if (mca_cfg.ignore_ce || !iv)
return;
- per_cpu(mce_next_interval, cpu) = iv;
-
- t->expires = round_jiffies(jiffies + iv);
- add_timer_on(t, cpu);
+ this_cpu_write(mce_next_interval, iv);
+ __start_timer(t, iv);
}
static void __mcheck_cpu_setup_timer(void)
@@ -1806,7 +1756,7 @@ static void __mcheck_cpu_init_timer(void)
unsigned int cpu = smp_processor_id();
setup_pinned_timer(t, mce_timer_fn, cpu);
- mce_start_timer(cpu, t);
+ mce_start_timer(t);
}
/* Handle unconfigured int18 (should never happen) */
@@ -2196,7 +2146,7 @@ int __init mcheck_init(void)
mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity();
- INIT_WORK(&mce_work, mce_process_work);
+ INIT_WORK(&mce_work, mce_gen_pool_process);
init_irq_work(&mce_irq_work, mce_irq_work_cb);
return 0;
@@ -2566,7 +2516,7 @@ static int mce_cpu_dead(unsigned int cpu)
static int mce_cpu_online(unsigned int cpu)
{
- struct timer_list *t = &per_cpu(mce_timer, cpu);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
int ret;
mce_device_create(cpu);
@@ -2577,13 +2527,13 @@ static int mce_cpu_online(unsigned int cpu)
return ret;
}
mce_reenable_cpu();
- mce_start_timer(cpu, t);
+ mce_start_timer(t);
return 0;
}
static int mce_cpu_pre_down(unsigned int cpu)
{
- struct timer_list *t = &per_cpu(mce_timer, cpu);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
mce_disable_cpu();
del_timer_sync(t);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index a5fd137417a2..9e5427df3243 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank)
smca_banks[bank].hwid = s_hwid;
smca_banks[bank].id = instance_id;
+ smca_banks[bank].sysfs_id = s_hwid->count++;
break;
}
}
@@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
mce_setup(&m);
m.status = status;
- m.bank = bank;
+ m.bank = bank;
+ m.tsc = rdtsc();
if (threshold_err)
m.misc = misc;
@@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
return NULL;
}
+ if (smca_banks[bank].hwid->count == 1)
+ return smca_get_name(bank_type);
+
snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
"%s_%x", smca_get_name(bank_type),
- smca_banks[bank].id);
+ smca_banks[bank].sysfs_id);
return buf_mcatype;
}
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 465aca8be009..85469f84c921 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -6,7 +6,7 @@
*
* Maintains a counter in /sys that keeps track of the number of thermal
* events, such that the user knows how bad the thermal problem might be
- * (since the logging to syslog and mcelog is rate limited).
+ * (since the logging to syslog is rate limited).
*
* Author: Dmitriy Zavin (dmitriyz@google.com)
*
@@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = {
* IRQ has been acknowledged.
*
* It will take care of rate limiting and printing messages to the syslog.
- *
- * Returns: 0 : Event should NOT be further logged, i.e. still in
- * "timeout" from previous log message.
- * 1 : Event should be logged further, and a message has been
- * printed to the syslog.
*/
-static int therm_throt_process(bool new_event, int event, int level)
+static void therm_throt_process(bool new_event, int event, int level)
{
struct _thermal_state *state;
unsigned int this_cpu = smp_processor_id();
@@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level)
else if (event == POWER_LIMIT_EVENT)
state = &pstate->core_power_limit;
else
- return 0;
+ return;
} else if (level == PACKAGE_LEVEL) {
if (event == THERMAL_THROTTLING_EVENT)
state = &pstate->package_throttle;
else if (event == POWER_LIMIT_EVENT)
state = &pstate->package_power_limit;
else
- return 0;
+ return;
} else
- return 0;
+ return;
old_event = state->new_event;
state->new_event = new_event;
@@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level)
if (time_before64(now, state->next_check) &&
state->count != state->last_count)
- return 0;
+ return;
state->next_check = now + CHECK_INTERVAL;
state->last_count = state->count;
@@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level)
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
- return 1;
+ return;
}
if (old_event) {
if (event == THERMAL_THROTTLING_EVENT)
pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
level == CORE_LEVEL ? "Core" : "Package");
- return 1;
+ return;
}
-
- return 0;
}
static int thresh_event_valid(int level, int event)
@@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void)
/* Check for violation of core thermal thresholds*/
notify_thresholds(msr_val);
- if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
- THERMAL_THROTTLING_EVENT,
- CORE_LEVEL) != 0)
- mce_log_therm_throt_event(msr_val);
+ therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
+ THERMAL_THROTTLING_EVENT,
+ CORE_LEVEL);
if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable)
therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 6a31e2691f3a..7889ae492af0 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -42,16 +42,19 @@ static struct equiv_cpu_entry *equiv_cpu_table;
/*
* This points to the current valid container of microcode patches which we will
- * save from the initrd/builtin before jettisoning its contents.
+ * save from the initrd/builtin before jettisoning its contents. @mc is the
+ * microcode patch we found to match.
*/
-struct container {
- u8 *data;
- size_t size;
-} cont;
+struct cont_desc {
+ struct microcode_amd *mc;
+ u32 cpuid_1_eax;
+ u32 psize;
+ u8 *data;
+ size_t size;
+};
static u32 ucode_new_rev;
static u8 amd_ucode_patch[PATCH_MAX_SIZE];
-static u16 this_equiv_id;
/*
* Microcode patch container file is prepended to the initrd in cpio
@@ -60,57 +63,13 @@ static u16 this_equiv_id;
static const char
ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
-static size_t compute_container_size(u8 *data, u32 total_size)
+static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig)
{
- size_t size = 0;
- u32 *header = (u32 *)data;
-
- if (header[0] != UCODE_MAGIC ||
- header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
- header[2] == 0) /* size */
- return size;
-
- size = header[2] + CONTAINER_HDR_SZ;
- total_size -= size;
- data += size;
-
- while (total_size) {
- u16 patch_size;
-
- header = (u32 *)data;
-
- if (header[0] != UCODE_UCODE_TYPE)
- break;
-
- /*
- * Sanity-check patch size.
- */
- patch_size = header[1];
- if (patch_size > PATCH_MAX_SIZE)
- break;
-
- size += patch_size + SECTION_HDR_SIZE;
- data += patch_size + SECTION_HDR_SIZE;
- total_size -= patch_size + SECTION_HDR_SIZE;
+ for (; equiv_table && equiv_table->installed_cpu; equiv_table++) {
+ if (sig == equiv_table->installed_cpu)
+ return equiv_table->equiv_cpu;
}
- return size;
-}
-
-static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
- unsigned int sig)
-{
- int i = 0;
-
- if (!equiv_cpu_table)
- return 0;
-
- while (equiv_cpu_table[i].installed_cpu != 0) {
- if (sig == equiv_cpu_table[i].installed_cpu)
- return equiv_cpu_table[i].equiv_cpu;
-
- i++;
- }
return 0;
}
@@ -118,91 +77,109 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
* This scans the ucode blob for the proper container as we can have multiple
* containers glued together. Returns the equivalence ID from the equivalence
* table or 0 if none found.
+ * Returns the amount of bytes consumed while scanning. @desc contains all the
+ * data we're going to use in later stages of the application.
*/
-static u16
-find_proper_container(u8 *ucode, size_t size, struct container *ret_cont)
+static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
{
- struct container ret = { NULL, 0 };
- u32 eax, ebx, ecx, edx;
struct equiv_cpu_entry *eq;
- int offset, left;
- u16 eq_id = 0;
- u32 *header;
- u8 *data;
+ ssize_t orig_size = size;
+ u32 *hdr = (u32 *)ucode;
+ u16 eq_id;
+ u8 *buf;
- data = ucode;
- left = size;
- header = (u32 *)data;
+ /* Am I looking at an equivalence table header? */
+ if (hdr[0] != UCODE_MAGIC ||
+ hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE ||
+ hdr[2] == 0)
+ return CONTAINER_HDR_SZ;
+ buf = ucode;
- /* find equiv cpu table */
- if (header[0] != UCODE_MAGIC ||
- header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
- header[2] == 0) /* size */
- return eq_id;
+ eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ);
- eax = 0x00000001;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
+ /* Find the equivalence ID of our CPU in this table: */
+ eq_id = find_equiv_id(eq, desc->cpuid_1_eax);
- while (left > 0) {
- eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ);
+ buf += hdr[2] + CONTAINER_HDR_SZ;
+ size -= hdr[2] + CONTAINER_HDR_SZ;
+
+ /*
+ * Scan through the rest of the container to find where it ends. We do
+ * some basic sanity-checking too.
+ */
+ while (size > 0) {
+ struct microcode_amd *mc;
+ u32 patch_size;
- ret.data = data;
+ hdr = (u32 *)buf;
- /* Advance past the container header */
- offset = header[2] + CONTAINER_HDR_SZ;
- data += offset;
- left -= offset;
+ if (hdr[0] != UCODE_UCODE_TYPE)
+ break;
- eq_id = find_equiv_id(eq, eax);
- if (eq_id) {
- ret.size = compute_container_size(ret.data, left + offset);
+ /* Sanity-check patch size. */
+ patch_size = hdr[1];
+ if (patch_size > PATCH_MAX_SIZE)
+ break;
- /*
- * truncate how much we need to iterate over in the
- * ucode update loop below
- */
- left = ret.size - offset;
+ /* Skip patch section header: */
+ buf += SECTION_HDR_SIZE;
+ size -= SECTION_HDR_SIZE;
- *ret_cont = ret;
- return eq_id;
+ mc = (struct microcode_amd *)buf;
+ if (eq_id == mc->hdr.processor_rev_id) {
+ desc->psize = patch_size;
+ desc->mc = mc;
}
- /*
- * support multiple container files appended together. if this
- * one does not have a matching equivalent cpu entry, we fast
- * forward to the next container file.
- */
- while (left > 0) {
- header = (u32 *)data;
-
- if (header[0] == UCODE_MAGIC &&
- header[1] == UCODE_EQUIV_CPU_TABLE_TYPE)
- break;
-
- offset = header[1] + SECTION_HDR_SIZE;
- data += offset;
- left -= offset;
- }
+ buf += patch_size;
+ size -= patch_size;
+ }
- /* mark where the next microcode container file starts */
- offset = data - (u8 *)ucode;
- ucode = data;
+ /*
+ * If we have found a patch (desc->mc), it means we're looking at the
+ * container which has a patch for this CPU so return 0 to mean, @ucode
+ * already points to the proper container. Otherwise, we return the size
+ * we scanned so that we can advance to the next container in the
+ * buffer.
+ */
+ if (desc->mc) {
+ desc->data = ucode;
+ desc->size = orig_size - size;
+
+ return 0;
}
- return eq_id;
+ return orig_size - size;
}
-static int __apply_microcode_amd(struct microcode_amd *mc_amd)
+/*
+ * Scan the ucode blob for the proper container as we can have multiple
+ * containers glued together.
+ */
+static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
+{
+ ssize_t rem = size;
+
+ while (rem >= 0) {
+ ssize_t s = parse_container(ucode, rem, desc);
+ if (!s)
+ return;
+
+ ucode += s;
+ rem -= s;
+ }
+}
+
+static int __apply_microcode_amd(struct microcode_amd *mc)
{
u32 rev, dummy;
- native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
+ native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc->hdr.data_code);
/* verify patch application was successful */
native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- if (rev != mc_amd->hdr.patch_id)
+ if (rev != mc->hdr.patch_id)
return -1;
return 0;
@@ -217,17 +194,16 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd)
* load_microcode_amd() to save equivalent cpu table and microcode patches in
* kernel heap memory.
*
- * Returns true if container found (sets @ret_cont), false otherwise.
+ * Returns true if container found (sets @desc), false otherwise.
*/
-static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch,
- struct container *ret_cont)
+static bool
+apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch)
{
+ struct cont_desc desc = { 0 };
u8 (*patch)[PATCH_MAX_SIZE];
- u32 rev, *header, *new_rev;
- struct container ret;
- int offset, left;
- u16 eq_id = 0;
- u8 *data;
+ struct microcode_amd *mc;
+ u32 rev, dummy, *new_rev;
+ bool ret = false;
#ifdef CONFIG_X86_32
new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
@@ -237,50 +213,27 @@ static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch,
patch = &amd_ucode_patch;
#endif
- if (check_current_patch_level(&rev, true))
- return false;
-
- eq_id = find_proper_container(ucode, size, &ret);
- if (!eq_id)
- return false;
-
- this_equiv_id = eq_id;
- header = (u32 *)ret.data;
-
- /* We're pointing to an equiv table, skip over it. */
- data = ret.data + header[2] + CONTAINER_HDR_SZ;
- left = ret.size - (header[2] + CONTAINER_HDR_SZ);
-
- while (left > 0) {
- struct microcode_amd *mc;
-
- header = (u32 *)data;
- if (header[0] != UCODE_UCODE_TYPE || /* type */
- header[1] == 0) /* size */
- break;
+ desc.cpuid_1_eax = cpuid_1_eax;
- mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE);
+ scan_containers(ucode, size, &desc);
- if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) {
+ mc = desc.mc;
+ if (!mc)
+ return ret;
- if (!__apply_microcode_amd(mc)) {
- rev = mc->hdr.patch_id;
- *new_rev = rev;
+ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+ if (rev >= mc->hdr.patch_id)
+ return ret;
- if (save_patch)
- memcpy(patch, mc, min_t(u32, header[1], PATCH_MAX_SIZE));
- }
- }
+ if (!__apply_microcode_amd(mc)) {
+ *new_rev = mc->hdr.patch_id;
+ ret = true;
- offset = header[1] + SECTION_HDR_SIZE;
- data += offset;
- left -= offset;
+ if (save_patch)
+ memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE));
}
- if (ret_cont)
- *ret_cont = ret;
-
- return true;
+ return ret;
}
static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -298,10 +251,9 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
#endif
}
-void __init load_ucode_amd_bsp(unsigned int family)
+void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret)
{
struct ucode_cpu_info *uci;
- u32 eax, ebx, ecx, edx;
struct cpio_data cp;
const char *path;
bool use_pa;
@@ -316,183 +268,95 @@ void __init load_ucode_amd_bsp(unsigned int family)
use_pa = false;
}
- if (!get_builtin_microcode(&cp, family))
+ if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax)))
cp = find_microcode_in_initrd(path, use_pa);
- if (!(cp.data && cp.size))
- return;
-
- /* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */
- eax = 1;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- uci->cpu_sig.sig = eax;
+ /* Needed in load_microcode_amd() */
+ uci->cpu_sig.sig = cpuid_1_eax;
- apply_microcode_early_amd(cp.data, cp.size, true, NULL);
+ *ret = cp;
}
-#ifdef CONFIG_X86_32
-/*
- * On 32-bit, since AP's early load occurs before paging is turned on, we
- * cannot traverse cpu_equiv_table and microcode_cache in kernel heap memory.
- * So during cold boot, AP will apply_ucode_in_initrd() just like the BSP.
- * In save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch,
- * which is used upon resume from suspend.
- */
-void load_ucode_amd_ap(unsigned int family)
+void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
{
- struct microcode_amd *mc;
- struct cpio_data cp;
-
- mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
- if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
- __apply_microcode_amd(mc);
- return;
- }
-
- if (!get_builtin_microcode(&cp, family))
- cp = find_microcode_in_initrd((const char *)__pa_nodebug(ucode_path), true);
+ struct cpio_data cp = { };
+ __load_ucode_amd(cpuid_1_eax, &cp);
if (!(cp.data && cp.size))
return;
- /*
- * This would set amd_ucode_patch above so that the following APs can
- * use it directly instead of going down this path again.
- */
- apply_microcode_early_amd(cp.data, cp.size, true, NULL);
+ apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true);
}
-#else
-void load_ucode_amd_ap(unsigned int family)
+
+void load_ucode_amd_ap(unsigned int cpuid_1_eax)
{
- struct equiv_cpu_entry *eq;
struct microcode_amd *mc;
- u32 rev, eax;
- u16 eq_id;
-
- /* 64-bit runs with paging enabled, thus early==false. */
- if (check_current_patch_level(&rev, false))
- return;
-
- /* First AP hasn't cached it yet, go through the blob. */
- if (!cont.data) {
- struct cpio_data cp = { NULL, 0, "" };
+ struct cpio_data cp;
+ u32 *new_rev, rev, dummy;
- if (cont.size == -1)
- return;
+ if (IS_ENABLED(CONFIG_X86_32)) {
+ mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
+ new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
+ } else {
+ mc = (struct microcode_amd *)amd_ucode_patch;
+ new_rev = &ucode_new_rev;
+ }
-reget:
- if (!get_builtin_microcode(&cp, family)) {
-#ifdef CONFIG_BLK_DEV_INITRD
- cp = find_cpio_data(ucode_path, (void *)initrd_start,
- initrd_end - initrd_start, NULL);
-#endif
- if (!(cp.data && cp.size)) {
- /*
- * Mark it so that other APs do not scan again
- * for no real reason and slow down boot
- * needlessly.
- */
- cont.size = -1;
- return;
- }
- }
+ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) {
- cont.size = -1;
+ /* Check whether we have saved a new patch already: */
+ if (*new_rev && rev < mc->hdr.patch_id) {
+ if (!__apply_microcode_amd(mc)) {
+ *new_rev = mc->hdr.patch_id;
return;
}
}
- eax = cpuid_eax(0x00000001);
- eq = (struct equiv_cpu_entry *)(cont.data + CONTAINER_HDR_SZ);
-
- eq_id = find_equiv_id(eq, eax);
- if (!eq_id)
+ __load_ucode_amd(cpuid_1_eax, &cp);
+ if (!(cp.data && cp.size))
return;
- if (eq_id == this_equiv_id) {
- mc = (struct microcode_amd *)amd_ucode_patch;
-
- if (mc && rev < mc->hdr.patch_id) {
- if (!__apply_microcode_amd(mc))
- ucode_new_rev = mc->hdr.patch_id;
- }
-
- } else {
-
- /*
- * AP has a different equivalence ID than BSP, looks like
- * mixed-steppings silicon so go through the ucode blob anew.
- */
- goto reget;
- }
+ apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false);
}
-#endif /* CONFIG_X86_32 */
static enum ucode_state
load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
-int __init save_microcode_in_initrd_amd(unsigned int fam)
+int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
{
+ struct cont_desc desc = { 0 };
enum ucode_state ret;
- int retval = 0;
- u16 eq_id;
-
- if (!cont.data) {
- if (IS_ENABLED(CONFIG_X86_32) && (cont.size != -1)) {
- struct cpio_data cp = { NULL, 0, "" };
-
-#ifdef CONFIG_BLK_DEV_INITRD
- cp = find_cpio_data(ucode_path, (void *)initrd_start,
- initrd_end - initrd_start, NULL);
-#endif
+ struct cpio_data cp;
- if (!(cp.data && cp.size)) {
- cont.size = -1;
- return -EINVAL;
- }
+ cp = find_microcode_in_initrd(ucode_path, false);
+ if (!(cp.data && cp.size))
+ return -EINVAL;
- eq_id = find_proper_container(cp.data, cp.size, &cont);
- if (!eq_id) {
- cont.size = -1;
- return -EINVAL;
- }
+ desc.cpuid_1_eax = cpuid_1_eax;
- } else
- return -EINVAL;
- }
+ scan_containers(cp.data, cp.size, &desc);
+ if (!desc.mc)
+ return -EINVAL;
- ret = load_microcode_amd(smp_processor_id(), fam, cont.data, cont.size);
+ ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
+ desc.data, desc.size);
if (ret != UCODE_OK)
- retval = -EINVAL;
-
- /*
- * This will be freed any msec now, stash patches for the current
- * family and switch to patch cache for cpu hotplug, etc later.
- */
- cont.data = NULL;
- cont.size = 0;
+ return -EINVAL;
- return retval;
+ return 0;
}
void reload_ucode_amd(void)
{
struct microcode_amd *mc;
- u32 rev;
-
- /*
- * early==false because this is a syscore ->resume path and by
- * that time paging is long enabled.
- */
- if (check_current_patch_level(&rev, false))
- return;
+ u32 rev, dummy;
mc = (struct microcode_amd *)amd_ucode_patch;
if (!mc)
return;
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
if (rev < mc->hdr.patch_id) {
if (!__apply_microcode_amd(mc)) {
ucode_new_rev = mc->hdr.patch_id;
@@ -630,60 +494,13 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
return patch_size;
}
-/*
- * Those patch levels cannot be updated to newer ones and thus should be final.
- */
-static u32 final_levels[] = {
- 0x01000098,
- 0x0100009f,
- 0x010000af,
- 0, /* T-101 terminator */
-};
-
-/*
- * Check the current patch level on this CPU.
- *
- * @rev: Use it to return the patch level. It is set to 0 in the case of
- * error.
- *
- * Returns:
- * - true: if update should stop
- * - false: otherwise
- */
-bool check_current_patch_level(u32 *rev, bool early)
-{
- u32 lvl, dummy, i;
- bool ret = false;
- u32 *levels;
-
- native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
-
- if (IS_ENABLED(CONFIG_X86_32) && early)
- levels = (u32 *)__pa_nodebug(&final_levels);
- else
- levels = final_levels;
-
- for (i = 0; levels[i]; i++) {
- if (lvl == levels[i]) {
- lvl = 0;
- ret = true;
- break;
- }
- }
-
- if (rev)
- *rev = lvl;
-
- return ret;
-}
-
static int apply_microcode_amd(int cpu)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
struct microcode_amd *mc_amd;
struct ucode_cpu_info *uci;
struct ucode_patch *p;
- u32 rev;
+ u32 rev, dummy;
BUG_ON(raw_smp_processor_id() != cpu);
@@ -696,8 +513,7 @@ static int apply_microcode_amd(int cpu)
mc_amd = p->data;
uci->mc = p->data;
- if (check_current_patch_level(&rev, false))
- return -1;
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
/* need to apply patch? */
if (rev >= mc_amd->hdr.patch_id) {
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 2af69d27da62..b4a4cd39b358 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -46,6 +46,8 @@
static struct microcode_ops *microcode_ops;
static bool dis_ucode_ldr = true;
+bool initrd_gone;
+
LIST_HEAD(microcode_cache);
/*
@@ -64,19 +66,50 @@ static DEFINE_MUTEX(microcode_mutex);
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
-/*
- * Operations that are run on a target cpu:
- */
-
struct cpu_info_ctx {
struct cpu_signature *cpu_sig;
int err;
};
+/*
+ * Those patch levels cannot be updated to newer ones and thus should be final.
+ */
+static u32 final_levels[] = {
+ 0x01000098,
+ 0x0100009f,
+ 0x010000af,
+ 0, /* T-101 terminator */
+};
+
+/*
+ * Check the current patch level on this CPU.
+ *
+ * Returns:
+ * - true: if update should stop
+ * - false: otherwise
+ */
+static bool amd_check_current_patch_level(void)
+{
+ u32 lvl, dummy, i;
+ u32 *levels;
+
+ native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
+
+ if (IS_ENABLED(CONFIG_X86_32))
+ levels = (u32 *)__pa_nodebug(&final_levels);
+ else
+ levels = final_levels;
+
+ for (i = 0; levels[i]; i++) {
+ if (lvl == levels[i])
+ return true;
+ }
+ return false;
+}
+
static bool __init check_loader_disabled_bsp(void)
{
static const char *__dis_opt_str = "dis_ucode_ldr";
- u32 a, b, c, d;
#ifdef CONFIG_X86_32
const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
@@ -92,18 +125,19 @@ static bool __init check_loader_disabled_bsp(void)
if (!have_cpuid_p())
return *res;
- a = 1;
- c = 0;
- native_cpuid(&a, &b, &c, &d);
-
/*
* CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
* completely accurate as xen pv guests don't see that CPUID bit set but
* that's good enough as they don't land on the BSP path anyway.
*/
- if (c & BIT(31))
+ if (native_cpuid_ecx(1) & BIT(31))
return *res;
+ if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
+ if (amd_check_current_patch_level())
+ return *res;
+ }
+
if (cmdline_find_option_bool(cmdline, option) <= 0)
*res = false;
@@ -131,23 +165,21 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name)
void __init load_ucode_bsp(void)
{
- int vendor;
- unsigned int family;
+ unsigned int cpuid_1_eax;
if (check_loader_disabled_bsp())
return;
- vendor = x86_cpuid_vendor();
- family = x86_cpuid_family();
+ cpuid_1_eax = native_cpuid_eax(1);
- switch (vendor) {
+ switch (x86_cpuid_vendor()) {
case X86_VENDOR_INTEL:
- if (family >= 6)
+ if (x86_family(cpuid_1_eax) >= 6)
load_ucode_intel_bsp();
break;
case X86_VENDOR_AMD:
- if (family >= 0x10)
- load_ucode_amd_bsp(family);
+ if (x86_family(cpuid_1_eax) >= 0x10)
+ load_ucode_amd_bsp(cpuid_1_eax);
break;
default:
break;
@@ -165,22 +197,21 @@ static bool check_loader_disabled_ap(void)
void load_ucode_ap(void)
{
- int vendor, family;
+ unsigned int cpuid_1_eax;
if (check_loader_disabled_ap())
return;
- vendor = x86_cpuid_vendor();
- family = x86_cpuid_family();
+ cpuid_1_eax = native_cpuid_eax(1);
- switch (vendor) {
+ switch (x86_cpuid_vendor()) {
case X86_VENDOR_INTEL:
- if (family >= 6)
+ if (x86_family(cpuid_1_eax) >= 6)
load_ucode_intel_ap();
break;
case X86_VENDOR_AMD:
- if (family >= 0x10)
- load_ucode_amd_ap(family);
+ if (x86_family(cpuid_1_eax) >= 0x10)
+ load_ucode_amd_ap(cpuid_1_eax);
break;
default:
break;
@@ -190,21 +221,24 @@ void load_ucode_ap(void)
static int __init save_microcode_in_initrd(void)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
+ int ret = -EINVAL;
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
if (c->x86 >= 6)
- return save_microcode_in_initrd_intel();
+ ret = save_microcode_in_initrd_intel();
break;
case X86_VENDOR_AMD:
if (c->x86 >= 0x10)
- return save_microcode_in_initrd_amd(c->x86);
+ return save_microcode_in_initrd_amd(cpuid_eax(1));
break;
default:
break;
}
- return -EINVAL;
+ initrd_gone = true;
+
+ return ret;
}
struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
@@ -247,9 +281,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
* has the virtual address of the beginning of the initrd. It also
* possibly relocates the ramdisk. In either case, initrd_start contains
* the updated address so use that instead.
+ *
+ * initrd_gone is for the hotplug case where we've thrown out initrd
+ * already.
*/
- if (!use_pa && initrd_start)
- start = initrd_start;
+ if (!use_pa) {
+ if (initrd_gone)
+ return (struct cpio_data){ NULL, 0, "" };
+ if (initrd_start)
+ start = initrd_start;
+ }
return find_cpio_data(path, (void *)start, size, NULL);
#else /* !CONFIG_BLK_DEV_INITRD */
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 3f329b74e040..8325d8a09ab0 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -41,7 +41,7 @@
static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
-/* Current microcode patch used in early patching */
+/* Current microcode patch used in early patching on the APs. */
struct microcode_intel *intel_ucode_patch;
static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
@@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void)
struct ucode_cpu_info uci;
struct cpio_data cp;
- /*
- * AP loading didn't find any microcode patch, no need to save anything.
- */
- if (!intel_ucode_patch || IS_ERR(intel_ucode_patch))
- return 0;
-
if (!load_builtin_intel_microcode(&cp))
cp = find_microcode_in_initrd(ucode_path, false);
@@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void)
return 0;
}
-
/*
* @res_patch, output: a pointer to the patch we found.
*/
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 34178564be2a..c1ea5b999839 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,4 +1,5 @@
#include <linux/kernel.h>
+#include <linux/sched.h>
#include <linux/mm.h>
#include <asm/cpufeature.h>
#include <asm/msr.h>
@@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
if (xlvl >= 0x80860001)
c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
}
+
+ clear_sched_clock_stable();
}
static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 90e8dde3ec26..b2bbad6ebe4d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -580,24 +580,19 @@ static void __init update_e820_saved(void)
}
#define MAX_GAP_END 0x100000000ull
/*
- * Search for a gap in the e820 memory space from start_addr to end_addr.
+ * Search for a gap in the e820 memory space from 0 to MAX_GAP_END.
*/
-__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
- unsigned long start_addr, unsigned long long end_addr)
+static int __init e820_search_gap(unsigned long *gapstart,
+ unsigned long *gapsize)
{
- unsigned long long last;
+ unsigned long long last = MAX_GAP_END;
int i = e820->nr_map;
int found = 0;
- last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;
-
while (--i >= 0) {
unsigned long long start = e820->map[i].addr;
unsigned long long end = start + e820->map[i].size;
- if (end < start_addr)
- continue;
-
/*
* Since "last" is at most 4GB, we know we'll
* fit in 32 bits if this condition is true
@@ -628,18 +623,19 @@ __init void e820_setup_gap(void)
unsigned long gapstart, gapsize;
int found;
- gapstart = 0x10000000;
gapsize = 0x400000;
- found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);
+ found = e820_search_gap(&gapstart, &gapsize);
-#ifdef CONFIG_X86_64
if (!found) {
+#ifdef CONFIG_X86_64
gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
printk(KERN_ERR
"e820: cannot find a gap in the 32bit address range\n"
"e820: PCI devices with unassigned 32bit BARs may break!\n");
- }
+#else
+ gapstart = 0x10000000;
#endif
+ }
/*
* e820_reserve_resources_late protect stolen RAM already
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e4e97a5355ce..e1114f070c2d 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -178,13 +178,8 @@ void fpstate_init(union fpregs_state *state)
memset(state, 0, fpu_kernel_xstate_size);
- /*
- * XRSTORS requires that this bit is set in xcomp_bv, or
- * it will #GP. Make sure it is replaced after the memset().
- */
if (static_cpu_has(X86_FEATURE_XSAVES))
- state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT;
-
+ fpstate_init_xstate(&state->xsave);
if (static_cpu_has(X86_FEATURE_FXSR))
fpstate_init_fxstate(&state->fxsave);
else
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 60dece392b3a..19bdd1bf8160 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -48,13 +48,7 @@ void fpu__init_cpu(void)
fpu__init_cpu_xstate();
}
-/*
- * The earliest FPU detection code.
- *
- * Set the X86_FEATURE_FPU CPU-capability bit based on
- * trying to execute an actual sequence of FPU instructions:
- */
-static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+static bool fpu__probe_without_cpuid(void)
{
unsigned long cr0;
u16 fsw, fcw;
@@ -65,18 +59,25 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
write_cr0(cr0);
- if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
- asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
- : "+m" (fsw), "+m" (fcw));
+ asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw));
+
+ pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw);
- if (fsw == 0 && (fcw & 0x103f) == 0x003f)
- set_cpu_cap(c, X86_FEATURE_FPU);
+ return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+ if (!boot_cpu_has(X86_FEATURE_CPUID) &&
+ !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+ if (fpu__probe_without_cpuid())
+ setup_force_cpu_cap(X86_FEATURE_FPU);
else
- clear_cpu_cap(c, X86_FEATURE_FPU);
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
}
#ifndef CONFIG_MATH_EMULATION
- if (!boot_cpu_has(X86_FEATURE_FPU)) {
+ if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) {
pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
for (;;)
asm volatile("hlt");
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 1d7770447b3e..c24ac1efb12d 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -78,6 +78,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
setup_clear_cpu_cap(X86_FEATURE_PKU);
setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ);
}
/*
@@ -705,8 +706,14 @@ void __init fpu__init_system_xstate(void)
WARN_ON_FPU(!on_boot_cpu);
on_boot_cpu = 0;
+ if (!boot_cpu_has(X86_FEATURE_FPU)) {
+ pr_info("x86/fpu: No FPU detected\n");
+ return;
+ }
+
if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
- pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+ pr_info("x86/fpu: x87 FPU will use %s\n",
+ boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE");
return;
}
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index f16c55bfc090..e5fb436a6548 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -49,3 +49,65 @@ asmlinkage __visible void __init i386_start_kernel(void)
start_kernel();
}
+
+/*
+ * Initialize page tables. This creates a PDE and a set of page
+ * tables, which are located immediately beyond __brk_base. The variable
+ * _brk_end is set up to point to the first "safe" location.
+ * Mappings are created both at virtual address 0 (identity mapping)
+ * and PAGE_OFFSET for up to _end.
+ *
+ * In PAE mode initial_page_table is statically defined to contain
+ * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+ * entries). The identity mapping is handled by pointing two PGD entries
+ * to the first kernel PMD. Note the upper half of each PMD or PTE are
+ * always zero at this stage.
+ */
+void __init mk_early_pgtbl_32(void)
+{
+#ifdef __pa
+#undef __pa
+#endif
+#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET)
+ pte_t pte, *ptep;
+ int i;
+ unsigned long *ptr;
+ /* Enough space to fit pagetables for the low memory linear map */
+ const unsigned long limit = __pa(_end) +
+ (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT);
+#ifdef CONFIG_X86_PAE
+ pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd);
+#define SET_PL2(pl2, val) { (pl2).pmd = (val); }
+#else
+ pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table);
+#define SET_PL2(pl2, val) { (pl2).pgd = (val); }
+#endif
+
+ ptep = (pte_t *)__pa(__brk_base);
+ pte.pte = PTE_IDENT_ATTR;
+
+ while ((pte.pte & PTE_PFN_MASK) < limit) {
+
+ SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR);
+ *pl2p = pl2;
+#ifndef CONFIG_X86_PAE
+ /* Kernel PDE entry */
+ *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2;
+#endif
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ *ptep = pte;
+ pte.pte += PAGE_SIZE;
+ ptep++;
+ }
+
+ pl2p++;
+ }
+
+ ptr = (unsigned long *)__pa(&max_pfn_mapped);
+ /* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */
+ *ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+
+ ptr = (unsigned long *)__pa(&_brk_end);
+ *ptr = (unsigned long)ptep + PAGE_OFFSET;
+}
+
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 4e8577d03372..1f85ee8f9439 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -24,6 +24,7 @@
#include <asm/nops.h>
#include <asm/bootparam.h>
#include <asm/export.h>
+#include <asm/pgtable_32.h>
/* Physical address */
#define pa(X) ((X) - __PAGE_OFFSET)
@@ -41,44 +42,10 @@
#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability
#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id
-/*
- * This is how much memory in addition to the memory covered up to
- * and including _end we need mapped initially.
- * We need:
- * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
- * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
- *
- * Modulo rounding, each megabyte assigned here requires a kilobyte of
- * memory, which is currently unreclaimed.
- *
- * This should be a multiple of a page.
- *
- * KERNEL_IMAGE_SIZE should be greater than pa(_end)
- * and small than max_low_pfn, otherwise will waste some page table entries
- */
-
-#if PTRS_PER_PMD > 1
-#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
-#else
-#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
-#endif
#define SIZEOF_PTREGS 17*4
/*
- * Number of possible pages in the lowmem region.
- *
- * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
- * gas warning about overflowing shift count when gas has been compiled
- * with only a host target support using a 32-bit type for internal
- * representation.
- */
-LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
-
-/* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
-
-/*
* Worst-case size of the kernel mapping we need to make:
* a relocatable kernel can live anywhere in lowmem, so we need to be able
* to map all of lowmem.
@@ -160,90 +127,15 @@ ENTRY(startup_32)
call load_ucode_bsp
#endif
-/*
- * Initialize page tables. This creates a PDE and a set of page
- * tables, which are located immediately beyond __brk_base. The variable
- * _brk_end is set up to point to the first "safe" location.
- * Mappings are created both at virtual address 0 (identity mapping)
- * and PAGE_OFFSET for up to _end.
- */
-#ifdef CONFIG_X86_PAE
-
- /*
- * In PAE mode initial_page_table is statically defined to contain
- * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
- * entries). The identity mapping is handled by pointing two PGD entries
- * to the first kernel PMD.
- *
- * Note the upper half of each PMD or PTE are always zero at this stage.
- */
-
-#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
-
- xorl %ebx,%ebx /* %ebx is kept at zero */
-
- movl $pa(__brk_base), %edi
- movl $pa(initial_pg_pmd), %edx
- movl $PTE_IDENT_ATTR, %eax
-10:
- leal PDE_IDENT_ATTR(%edi),%ecx /* Create PMD entry */
- movl %ecx,(%edx) /* Store PMD entry */
- /* Upper half already zero */
- addl $8,%edx
- movl $512,%ecx
-11:
- stosl
- xchgl %eax,%ebx
- stosl
- xchgl %eax,%ebx
- addl $0x1000,%eax
- loop 11b
-
- /*
- * End condition: we must map up to the end + MAPPING_BEYOND_END.
- */
- movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
- cmpl %ebp,%eax
- jb 10b
-1:
- addl $__PAGE_OFFSET, %edi
- movl %edi, pa(_brk_end)
- shrl $12, %eax
- movl %eax, pa(max_pfn_mapped)
+ /* Create early pagetables. */
+ call mk_early_pgtbl_32
/* Do early initialization of the fixmap area */
movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+#ifdef CONFIG_X86_PAE
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
-#else /* Not PAE */
-
-page_pde_offset = (__PAGE_OFFSET >> 20);
-
- movl $pa(__brk_base), %edi
- movl $pa(initial_page_table), %edx
- movl $PTE_IDENT_ATTR, %eax
-10:
- leal PDE_IDENT_ATTR(%edi),%ecx /* Create PDE entry */
- movl %ecx,(%edx) /* Store identity PDE entry */
- movl %ecx,page_pde_offset(%edx) /* Store kernel PDE entry */
- addl $4,%edx
- movl $1024, %ecx
-11:
- stosl
- addl $0x1000,%eax
- loop 11b
- /*
- * End condition: we must map up to the end + MAPPING_BEYOND_END.
- */
- movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
- cmpl %ebp,%eax
- jb 10b
- addl $__PAGE_OFFSET, %edi
- movl %edi, pa(_brk_end)
- shrl $12, %eax
- movl %eax, pa(max_pfn_mapped)
-
- /* Do early initialization of the fixmap area */
- movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+#else
movl %eax,pa(initial_page_table+0xffc)
#endif
@@ -666,6 +558,7 @@ ENTRY(setup_once_ref)
__PAGE_ALIGNED_BSS
.align PAGE_SIZE
#ifdef CONFIG_X86_PAE
+.globl initial_pg_pmd
initial_pg_pmd:
.fill 1024*KPMDS,4,0
#else
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 85e87b46c318..dc6ba5bda9fc 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
} else {
struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+ irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
disable_irq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index cb9c1ed1d391..f73f475d0573 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -132,10 +132,8 @@ int sched_set_itmt_support(void)
sysctl_sched_itmt_enabled = 1;
- if (sysctl_sched_itmt_enabled) {
- x86_topology_update = true;
- rebuild_sched_domains();
- }
+ x86_topology_update = true;
+ rebuild_sched_domains();
mutex_unlock(&itmt_update_mutex);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index fc25f698d792..c37bd0f39c70 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line)
* Something went wrong. Crash the box, as something could be
* corrupting the kernel.
*/
- pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n",
- ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line);
+ pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line);
BUG();
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index eb3509338ae0..520b8dfe1640 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
* will be the real return address, and all the rest will
* point to kretprobe_trampoline.
*/
- hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ hlist_for_each_entry(ri, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 36bc66416021..099fcba4981d 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -620,18 +620,4 @@ void __init kvm_spinlock_init(void)
}
}
-static __init int kvm_spinlock_init_jump(void)
-{
- if (!kvm_para_available())
- return 0;
- if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
- return 0;
-
- static_key_slow_inc(&paravirt_ticketlocks_enabled);
- printk(KERN_INFO "KVM setup paravirtual spinlock\n");
-
- return 0;
-}
-early_initcall(kvm_spinlock_init_jump);
-
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2a5cafdf8808..542710b99f52 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable)
{
if (!stable) {
pv_time_ops.sched_clock = kvm_clock_read;
+ clear_sched_clock_stable();
return;
}
kvm_sched_clock_offset = kvm_clock_read();
pv_time_ops.sched_clock = kvm_sched_clock_read;
- set_sched_clock_stable();
printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 6d4bf812af45..6259327f3454 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = {
#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
-
-struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE;
-EXPORT_SYMBOL(paravirt_ticketlocks_enabled);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 5d400ba1349d..d47517941bbc 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
/* were we called with bad_dma_address? */
badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE);
- if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) {
+ if (unlikely(dma_addr < badend)) {
WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
"address 0x%Lx\n", dma_addr);
return;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4cfba947d774..69780edf0dde 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1176,6 +1176,20 @@ void __init setup_arch(char **cmdline_p)
/* Allocate bigger log buffer */
setup_log_buf(1);
+ if (efi_enabled(EFI_BOOT)) {
+ switch (boot_params.secure_boot) {
+ case efi_secureboot_mode_disabled:
+ pr_info("Secure boot disabled\n");
+ break;
+ case efi_secureboot_mode_enabled:
+ pr_info("Secure boot enabled\n");
+ break;
+ default:
+ pr_info("Secure boot could not be determined\n");
+ break;
+ }
+ }
+
reserve_initrd();
acpi_table_upgrade();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc3b73c..a0d38685f7df 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
if (c->phys_proc_id == o->phys_proc_id &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
- c->cpu_core_id == o->cpu_core_id)
- return topology_sane(c, o, "smt");
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+ if (c->cpu_core_id == o->cpu_core_id)
+ return topology_sane(c, o, "smt");
+
+ if ((c->cu_id != 0xff) &&
+ (o->cu_id != 0xff) &&
+ (c->cu_id == o->cu_id))
+ return topology_sane(c, o, "smt");
+ }
} else if (c->phys_proc_id == o->phys_proc_id &&
c->cpu_core_id == o->cpu_core_id) {
@@ -1341,8 +1347,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
pr_info("CPU0: ");
print_cpu_info(&cpu_data(0));
- if (is_uv_system())
- uv_system_init();
+ uv_system_init();
set_mtrr_aps_delayed_init();
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
deleted file mode 100644
index a3b875c9e6af..000000000000
--- a/arch/x86/kernel/test_nx.c
+++ /dev/null
@@ -1,173 +0,0 @@
-/*
- * test_nx.c: functional test for NX functionality
- *
- * (C) Copyright 2008 Intel Corporation
- * Author: Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#include <linux/module.h>
-#include <linux/sort.h>
-#include <linux/slab.h>
-
-#include <linux/uaccess.h>
-#include <asm/asm.h>
-
-extern int rodata_test_data;
-
-/*
- * This file checks 4 things:
- * 1) Check if the stack is not executable
- * 2) Check if kmalloc memory is not executable
- * 3) Check if the .rodata section is not executable
- * 4) Check if the .data section of a module is not executable
- *
- * To do this, the test code tries to execute memory in stack/kmalloc/etc,
- * and then checks if the expected trap happens.
- *
- * Sadly, this implies having a dynamic exception handling table entry.
- * ... which can be done (and will make Rusty cry)... but it can only
- * be done in a stand-alone module with only 1 entry total.
- * (otherwise we'd have to sort and that's just too messy)
- */
-
-
-
-/*
- * We want to set up an exception handling point on our stack,
- * which means a variable value. This function is rather dirty
- * and walks the exception table of the module, looking for a magic
- * marker and replaces it with a specific function.
- */
-static void fudze_exception_table(void *marker, void *new)
-{
- struct module *mod = THIS_MODULE;
- struct exception_table_entry *extable;
-
- /*
- * Note: This module has only 1 exception table entry,
- * so searching and sorting is not needed. If that changes,
- * this would be the place to search and re-sort the exception
- * table.
- */
- if (mod->num_exentries > 1) {
- printk(KERN_ERR "test_nx: too many exception table entries!\n");
- printk(KERN_ERR "test_nx: test results are not reliable.\n");
- return;
- }
- extable = (struct exception_table_entry *)mod->extable;
- extable[0].insn = (unsigned long)new;
-}
-
-
-/*
- * exception tables get their symbols translated so we need
- * to use a fake function to put in there, which we can then
- * replace at runtime.
- */
-void foo_label(void);
-
-/*
- * returns 0 for not-executable, negative for executable
- *
- * Note: we cannot allow this function to be inlined, because
- * that would give us more than 1 exception table entry.
- * This in turn would break the assumptions above.
- */
-static noinline int test_address(void *address)
-{
- unsigned long result;
-
- /* Set up an exception table entry for our address */
- fudze_exception_table(&foo_label, address);
- result = 1;
- asm volatile(
- "foo_label:\n"
- "0: call *%[fake_code]\n"
- "1:\n"
- ".section .fixup,\"ax\"\n"
- "2: mov %[zero], %[rslt]\n"
- " ret\n"
- ".previous\n"
- _ASM_EXTABLE(0b,2b)
- : [rslt] "=r" (result)
- : [fake_code] "r" (address), [zero] "r" (0UL), "0" (result)
- );
- /* change the exception table back for the next round */
- fudze_exception_table(address, &foo_label);
-
- if (result)
- return -ENODEV;
- return 0;
-}
-
-static unsigned char test_data = 0xC3; /* 0xC3 is the opcode for "ret" */
-
-static int test_NX(void)
-{
- int ret = 0;
- /* 0xC3 is the opcode for "ret" */
- char stackcode[] = {0xC3, 0x90, 0 };
- char *heap;
-
- test_data = 0xC3;
-
- printk(KERN_INFO "Testing NX protection\n");
-
- /* Test 1: check if the stack is not executable */
- if (test_address(&stackcode)) {
- printk(KERN_ERR "test_nx: stack was executable\n");
- ret = -ENODEV;
- }
-
-
- /* Test 2: Check if the heap is executable */
- heap = kmalloc(64, GFP_KERNEL);
- if (!heap)
- return -ENOMEM;
- heap[0] = 0xC3; /* opcode for "ret" */
-
- if (test_address(heap)) {
- printk(KERN_ERR "test_nx: heap was executable\n");
- ret = -ENODEV;
- }
- kfree(heap);
-
- /*
- * The following 2 tests currently fail, this needs to get fixed
- * Until then, don't run them to avoid too many people getting scared
- * by the error message
- */
-
- /* Test 3: Check if the .rodata section is executable */
- if (rodata_test_data != 0xC3) {
- printk(KERN_ERR "test_nx: .rodata marker has invalid value\n");
- ret = -ENODEV;
- } else if (test_address(&rodata_test_data)) {
- printk(KERN_ERR "test_nx: .rodata section is executable\n");
- ret = -ENODEV;
- }
-
-#if 0
- /* Test 4: Check if the .data section of a module is executable */
- if (test_address(&test_data)) {
- printk(KERN_ERR "test_nx: .data section is executable\n");
- ret = -ENODEV;
- }
-
-#endif
- return ret;
-}
-
-static void test_exit(void)
-{
-}
-
-module_init(test_NX);
-module_exit(test_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Testcase for the NX infrastructure");
-MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index bf0c6d049080..1dc86ee60a03 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -563,11 +563,9 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
* as we may switch to the interrupt stack.
*/
debug_stack_usage_inc();
- preempt_disable();
cond_local_irq_enable(regs);
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
cond_local_irq_disable(regs);
- preempt_enable_no_resched();
debug_stack_usage_dec();
exit:
ist_exit(regs);
@@ -742,14 +740,12 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
debug_stack_usage_inc();
/* It's safe to allow irq's after DR6 has been saved */
- preempt_disable();
cond_local_irq_enable(regs);
if (v8086_mode(regs)) {
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
X86_TRAP_DB);
cond_local_irq_disable(regs);
- preempt_enable_no_resched();
debug_stack_usage_dec();
goto exit;
}
@@ -769,7 +765,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
send_sigtrap(tsk, regs, error_code, si_code);
cond_local_irq_disable(regs);
- preempt_enable_no_resched();
debug_stack_usage_dec();
exit:
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e41af597aed8..2724dc82f992 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs)
return (u64)rdtsc_ordered();
}
+static void tsc_cs_mark_unstable(struct clocksource *cs)
+{
+ if (tsc_unstable)
+ return;
+ tsc_unstable = 1;
+ clear_sched_clock_stable();
+ disable_sched_clock_irqtime();
+ pr_info("Marking TSC unstable due to clocksource watchdog\n");
+}
+
/*
* .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
*/
@@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = {
CLOCK_SOURCE_MUST_VERIFY,
.archdata = { .vclock_mode = VCLOCK_TSC },
.resume = tsc_resume,
+ .mark_unstable = tsc_cs_mark_unstable,
};
void mark_tsc_unstable(char *reason)
@@ -1356,6 +1367,9 @@ void __init tsc_init(void)
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
+ /* Sanitize TSC ADJUST before cyc2ns gets initialized */
+ tsc_store_and_check_tsc_adjust(true);
+
/*
* Secondary CPUs do not run through tsc_init(), so set up
* all the scale factors for all CPUs, assuming the same
@@ -1386,8 +1400,6 @@ void __init tsc_init(void)
if (unsynchronized_tsc())
mark_tsc_unstable("TSCs unsynchronized");
- else
- tsc_store_and_check_tsc_adjust(true);
check_system_tsc_reliable();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index d0db011051a5..728f75378475 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu)
if (unsynchronized_tsc())
return;
- if (tsc_clocksource_reliable) {
- if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
- pr_info(
- "Skipped synchronization checks as TSC is reliable.\n");
- return;
- }
-
/*
* Set the maximum number of test runs to
* 1 if the CPU does not provide the TSC_ADJUST MSR
@@ -380,14 +373,19 @@ void check_tsc_sync_target(void)
int cpus = 2;
/* Also aborts if there is no TSC. */
- if (unsynchronized_tsc() || tsc_clocksource_reliable)
+ if (unsynchronized_tsc())
return;
/*
* Store, verify and sanitize the TSC adjust register. If
* successful skip the test.
+ *
+ * The test is also skipped when the TSC is marked reliable. This
+ * is true for SoCs which have no fallback clocksource. On these
+ * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
+ * register might have been wreckaged by the BIOS..
*/
- if (tsc_store_and_check_tsc_adjust(false)) {
+ if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
atomic_inc(&skip_test);
return;
}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index ec5d7545e6dc..0442d98367ae 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
static void mark_screen_rdonly(struct mm_struct *mm)
{
+ struct vm_area_struct *vma;
+ spinlock_t *ptl;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- spinlock_t *ptl;
int i;
down_write(&mm->mmap_sem);
@@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
pmd = pmd_offset(pud, 0xA0000);
if (pmd_trans_huge(*pmd)) {
- struct vm_area_struct *vma = find_vma(mm, 0xA0000);
+ vma = find_vma(mm, 0xA0000);
split_huge_pmd(vma, pmd, 0xA0000);
}
if (pmd_none_or_clear_bad(pmd))
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 1572c35b4f1a..2ecd7dab4631 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -964,10 +964,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
/* Calculate cpu time spent by current task in 100ns units */
static u64 current_task_runtime_100ns(void)
{
- cputime_t utime, stime;
+ u64 utime, stime;
task_cputime_adjusted(current, &utime, &stime);
- return div_u64(cputime_to_nsecs(utime + stime), 100);
+
+ return div_u64(utime + stime, 100);
}
static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d153be8929a6..e52c9088660f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3182,6 +3182,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
memcpy(dest, xsave, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV */
+ xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
/*
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 073d1f1a620b..a8e91ae89fb3 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -156,13 +156,13 @@ EXPORT_SYMBOL(__delay);
inline void __const_udelay(unsigned long xloops)
{
+ unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
int d0;
xloops *= 4;
asm("mull %%edx"
:"=d" (xloops), "=&a" (d0)
- :"1" (xloops), "0"
- (this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4)));
+ :"1" (xloops), "0" (lpj * (HZ / 4)));
__delay(++xloops);
}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..58b5bee7ea27 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,8 +15,10 @@
#include <linux/debugfs.h>
#include <linux/mm.h>
#include <linux/init.h>
+#include <linux/sched.h>
#include <linux/seq_file.h>
+#include <asm/kasan.h>
#include <asm/pgtable.h>
/*
@@ -50,6 +52,10 @@ enum address_markers_idx {
LOW_KERNEL_NR,
VMALLOC_START_NR,
VMEMMAP_START_NR,
+#ifdef CONFIG_KASAN
+ KASAN_SHADOW_START_NR,
+ KASAN_SHADOW_END_NR,
+#endif
# ifdef CONFIG_X86_ESPFIX64
ESPFIX_START_NR,
# endif
@@ -75,6 +81,10 @@ static struct addr_marker address_markers[] = {
{ 0/* PAGE_OFFSET */, "Low Kernel Mapping" },
{ 0/* VMALLOC_START */, "vmalloc() Area" },
{ 0/* VMEMMAP_START */, "Vmemmap" },
+#ifdef CONFIG_KASAN
+ { KASAN_SHADOW_START, "KASAN shadow" },
+ { KASAN_SHADOW_END, "KASAN shadow end" },
+#endif
# ifdef CONFIG_X86_ESPFIX64
{ ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
# endif
@@ -326,18 +336,31 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
#if PTRS_PER_PUD > 1
+/*
+ * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y
+ * KASAN fills page tables with the same values. Since there is no
+ * point in checking page table more than once we just skip repeated
+ * entries. This saves us dozens of seconds during boot.
+ */
+static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx)
+{
+ return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud));
+}
+
static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
unsigned long P)
{
int i;
pud_t *start;
pgprotval_t prot;
+ pud_t *prev_pud = NULL;
start = (pud_t *) pgd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PUD; i++) {
st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
- if (!pud_none(*start)) {
+ if (!pud_none(*start) &&
+ !pud_already_checked(prev_pud, start, st->check_wx)) {
if (pud_large(*start) || !pud_present(*start)) {
prot = pud_flags(*start);
note_page(m, st, __pgprot(prot), 2);
@@ -348,6 +371,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
} else
note_page(m, st, __pgprot(0), 2);
+ prev_pud = start;
start++;
}
}
@@ -406,6 +430,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
} else
note_page(m, &st, __pgprot(0), 1);
+ cond_resched();
start++;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 5a287e523eab..28d42130243c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -214,7 +214,20 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
int in_flags, struct page **pages)
{
unsigned int i, level;
+#ifdef CONFIG_PREEMPT
+ /*
+ * Avoid wbinvd() because it causes latencies on all CPUs,
+ * regardless of any CPU isolation that may be in effect.
+ *
+ * This should be extended for CAT enabled systems independent of
+ * PREEMPT because wbinvd() does not respect the CAT partitions and
+ * this is exposed to unpriviledged users through the graphics
+ * subsystem.
+ */
+ unsigned long do_wbinvd = 0;
+#else
unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
+#endif
BUG_ON(irqs_disabled());
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 159b52ccd600..d76485b22824 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -47,7 +47,7 @@ static u64 get_subtree_max_end(struct rb_node *node)
{
u64 ret = 0;
if (node) {
- struct memtype *data = container_of(node, struct memtype, rb);
+ struct memtype *data = rb_entry(node, struct memtype, rb);
ret = data->subtree_max_end;
}
return ret;
@@ -79,7 +79,7 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
struct memtype *last_lower = NULL;
while (node) {
- struct memtype *data = container_of(node, struct memtype, rb);
+ struct memtype *data = rb_entry(node, struct memtype, rb);
if (get_subtree_max_end(node->rb_left) > start) {
/* Lowest overlap if any must be on left side */
@@ -121,7 +121,7 @@ static struct memtype *memtype_rb_match(struct rb_root *root,
node = rb_next(&match->rb);
if (node)
- match = container_of(node, struct memtype, rb);
+ match = rb_entry(node, struct memtype, rb);
else
match = NULL;
}
@@ -150,7 +150,7 @@ static int memtype_rb_check_conflict(struct rb_root *root,
node = rb_next(&match->rb);
while (node) {
- match = container_of(node, struct memtype, rb);
+ match = rb_entry(node, struct memtype, rb);
if (match->start >= end) /* Checked all possible matches */
goto success;
@@ -181,7 +181,7 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
struct rb_node *parent = NULL;
while (*node) {
- struct memtype *data = container_of(*node, struct memtype, rb);
+ struct memtype *data = rb_entry(*node, struct memtype, rb);
parent = *node;
if (data->subtree_max_end < newdata->end)
@@ -270,7 +270,7 @@ int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
}
if (node) { /* pos == i */
- struct memtype *this = container_of(node, struct memtype, rb);
+ struct memtype *this = rb_entry(node, struct memtype, rb);
*out = *this;
return 0;
} else {
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index bb660e53cbd6..32322ce9b405 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1067,13 +1067,13 @@ common_load:
ilen = prog - temp;
if (ilen > BPF_MAX_INSN_SIZE) {
- pr_err("bpf_jit_compile fatal insn size error\n");
+ pr_err("bpf_jit: fatal insn size error\n");
return -EFAULT;
}
if (image) {
if (unlikely(proglen + ilen > oldproglen)) {
- pr_err("bpf_jit_compile fatal error\n");
+ pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
memcpy(image + proglen, temp, ilen);
@@ -1085,10 +1085,6 @@ common_load:
return proglen;
}
-void bpf_jit_compile(struct bpf_prog *prog)
-{
-}
-
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
struct bpf_binary_header *header = NULL;
@@ -1169,7 +1165,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
if (image) {
bpf_flush_icache(header, image + proglen);
- set_memory_ro((unsigned long)header, header->pages);
+ bpf_jit_binary_lock_ro(header);
prog->bpf_func = (void *)image;
prog->jited = 1;
} else {
@@ -1184,18 +1180,3 @@ out:
tmp : orig_prog);
return prog;
}
-
-void bpf_jit_free(struct bpf_prog *fp)
-{
- unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
- struct bpf_binary_header *header = (void *)addr;
-
- if (!fp->jited)
- goto free_filter;
-
- set_memory_rw(addr, header->pages);
- bpf_jit_binary_free(header);
-
-free_filter:
- bpf_prog_unlock_free(fp);
-}
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 6aad870e8962..04ca8764f0c0 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -19,8 +19,7 @@
#include <linux/efi.h>
#include <linux/efi-bgrt.h>
-struct acpi_table_bgrt *bgrt_tab;
-void *__initdata bgrt_image;
+struct acpi_table_bgrt bgrt_tab;
size_t __initdata bgrt_image_size;
struct bmp_header {
@@ -28,66 +27,58 @@ struct bmp_header {
u32 size;
} __packed;
-void __init efi_bgrt_init(void)
+void __init efi_bgrt_init(struct acpi_table_header *table)
{
- acpi_status status;
void *image;
struct bmp_header bmp_header;
+ struct acpi_table_bgrt *bgrt = &bgrt_tab;
if (acpi_disabled)
return;
- status = acpi_get_table("BGRT", 0,
- (struct acpi_table_header **)&bgrt_tab);
- if (ACPI_FAILURE(status))
- return;
-
- if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
+ if (table->length < sizeof(bgrt_tab)) {
pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n",
- bgrt_tab->header.length, sizeof(*bgrt_tab));
+ table->length, sizeof(bgrt_tab));
return;
}
- if (bgrt_tab->version != 1) {
+ *bgrt = *(struct acpi_table_bgrt *)table;
+ if (bgrt->version != 1) {
pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n",
- bgrt_tab->version);
- return;
+ bgrt->version);
+ goto out;
}
- if (bgrt_tab->status & 0xfe) {
+ if (bgrt->status & 0xfe) {
pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n",
- bgrt_tab->status);
- return;
+ bgrt->status);
+ goto out;
}
- if (bgrt_tab->image_type != 0) {
+ if (bgrt->image_type != 0) {
pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n",
- bgrt_tab->image_type);
- return;
+ bgrt->image_type);
+ goto out;
}
- if (!bgrt_tab->image_address) {
+ if (!bgrt->image_address) {
pr_notice("Ignoring BGRT: null image address\n");
- return;
+ goto out;
}
- image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB);
+ image = early_memremap(bgrt->image_address, sizeof(bmp_header));
if (!image) {
pr_notice("Ignoring BGRT: failed to map image header memory\n");
- return;
+ goto out;
}
memcpy(&bmp_header, image, sizeof(bmp_header));
- memunmap(image);
+ early_memunmap(image, sizeof(bmp_header));
if (bmp_header.id != 0x4d42) {
pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n",
bmp_header.id);
- return;
+ goto out;
}
bgrt_image_size = bmp_header.size;
+ efi_mem_reserve(bgrt->image_address, bgrt_image_size);
- bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
- if (!bgrt_image) {
- pr_notice("Ignoring BGRT: failed to map image memory\n");
- bgrt_image = NULL;
- return;
- }
-
- efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size);
+ return;
+out:
+ memset(bgrt, 0, sizeof(bgrt_tab));
}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 274dfc481849..565dff3c9a12 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -542,11 +542,6 @@ void __init efi_init(void)
efi_print_memmap();
}
-void __init efi_late_init(void)
-{
- efi_bgrt_init();
-}
-
void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
{
u64 addr, npages;
@@ -960,6 +955,11 @@ static void __init __efi_enter_virtual_mode(void)
return;
}
+ if (efi_enabled(EFI_DBG)) {
+ pr_info("EFI runtime memory map:\n");
+ efi_print_memmap();
+ }
+
BUG_ON(!efi.systab);
if (efi_setup_page_tables(pa, 1 << pg_shift)) {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 319148bd4b05..a4695da42d77 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -269,6 +269,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
efi_scratch.use_pgd = true;
/*
+ * Certain firmware versions are way too sentimential and still believe
+ * they are exclusive and unquestionable owners of the first physical page,
+ * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY
+ * (but then write-access it later during SetVirtualAddressMap()).
+ *
+ * Create a 1:1 mapping for this page, to avoid triple faults during early
+ * boot with such firmware. We are free to hand this page to the BIOS,
+ * as trim_bios_range() will reserve the first page and isolate it away
+ * from memory allocators anyway.
+ */
+ if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) {
+ pr_err("Failed to create 1:1 mapping for the first page!\n");
+ return 1;
+ }
+
+ /*
* When making calls to the firmware everything needs to be 1:1
* mapped and addressable with 32-bit pointers. Map the kernel
* text and allocate a new stack because we can't rely on the
@@ -398,10 +414,44 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
efi_setup = phys_addr + sizeof(struct setup_data);
}
-void __init efi_runtime_update_mappings(void)
+static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
{
unsigned long pfn;
pgd_t *pgd = efi_pgd;
+ int err1, err2;
+
+ /* Update the 1:1 mapping */
+ pfn = md->phys_addr >> PAGE_SHIFT;
+ err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf);
+ if (err1) {
+ pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n",
+ md->phys_addr, md->virt_addr);
+ }
+
+ err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf);
+ if (err2) {
+ pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n",
+ md->phys_addr, md->virt_addr);
+ }
+
+ return err1 || err2;
+}
+
+static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+ unsigned long pf = 0;
+
+ if (md->attribute & EFI_MEMORY_XP)
+ pf |= _PAGE_NX;
+
+ if (!(md->attribute & EFI_MEMORY_RO))
+ pf |= _PAGE_RW;
+
+ return efi_update_mappings(md, pf);
+}
+
+void __init efi_runtime_update_mappings(void)
+{
efi_memory_desc_t *md;
if (efi_enabled(EFI_OLD_MEMMAP)) {
@@ -410,6 +460,24 @@ void __init efi_runtime_update_mappings(void)
return;
}
+ /*
+ * Use the EFI Memory Attribute Table for mapping permissions if it
+ * exists, since it is intended to supersede EFI_PROPERTIES_TABLE.
+ */
+ if (efi_enabled(EFI_MEM_ATTR)) {
+ efi_memattr_apply_permissions(NULL, efi_update_mem_attr);
+ return;
+ }
+
+ /*
+ * EFI_MEMORY_ATTRIBUTES_TABLE is intended to replace
+ * EFI_PROPERTIES_TABLE. So, use EFI_PROPERTIES_TABLE to update
+ * permissions only if EFI_MEMORY_ATTRIBUTES_TABLE is not
+ * published by the firmware. Even if we find a buggy implementation of
+ * EFI_MEMORY_ATTRIBUTES_TABLE, don't fall back to
+ * EFI_PROPERTIES_TABLE, because of the same reason.
+ */
+
if (!efi_enabled(EFI_NX_PE_DATA))
return;
@@ -430,15 +498,7 @@ void __init efi_runtime_update_mappings(void)
(md->type != EFI_RUNTIME_SERVICES_CODE))
pf |= _PAGE_RW;
- /* Update the 1:1 mapping */
- pfn = md->phys_addr >> PAGE_SHIFT;
- if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf))
- pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
- md->phys_addr, md->virt_addr);
-
- if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf))
- pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
- md->phys_addr, md->virt_addr);
+ efi_update_mappings(md, pf);
}
}
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index 90e4f2a6625b..a7dbec4dce27 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -5,14 +5,12 @@ obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o
# WiFi
obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o
# IPC Devices
-obj-y += platform_ipc.o
obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o
obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o
obj-$(subst m,y,$(CONFIG_GPIO_MSIC)) += platform_msic_gpio.o
obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_ocd.o
obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_battery.o
obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o
-obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o
obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o
# SPI Devices
obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o
@@ -28,4 +26,5 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
# MISC Devices
obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
index 52534ec29765..74283875c7e8 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
@@ -32,6 +32,9 @@ static struct gpio_keys_button gpio_button[] = {
{SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20},
{KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20},
{KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20},
+ {KEY_MUTE, -1, 1, "mute_enable", EV_KEY, 0, 20},
+ {KEY_VOLUMEUP, -1, 1, "volume_up", EV_KEY, 0, 20},
+ {KEY_VOLUMEDOWN, -1, 1, "volume_down", EV_KEY, 0, 20},
{KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20},
{KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20},
{SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20},
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
deleted file mode 100644
index a84b73d6c4a0..000000000000
--- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * platform_ipc.c: IPC platform library file
- *
- * (C) Copyright 2013 Intel Corporation
- * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/sfi.h>
-#include <linux/gpio.h>
-#include <asm/intel-mid.h>
-#include "platform_ipc.h"
-
-void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
- struct devs_id *dev)
-{
- struct platform_device *pdev;
- void *pdata = NULL;
- static struct resource res __initdata = {
- .name = "IRQ",
- .flags = IORESOURCE_IRQ,
- };
-
- pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
- pentry->name, pentry->irq);
-
- /*
- * We need to call platform init of IPC devices to fill misc_pdata
- * structure. It will be used in msic_init for initialization.
- */
- if (dev != NULL)
- pdata = dev->get_platform_data(pentry);
-
- /*
- * On Medfield the platform device creation is handled by the MSIC
- * MFD driver so we don't need to do it here.
- */
- if (intel_mid_has_msic())
- return;
-
- pdev = platform_device_alloc(pentry->name, 0);
- if (pdev == NULL) {
- pr_err("out of memory for SFI platform device '%s'.\n",
- pentry->name);
- return;
- }
- res.start = pentry->irq;
- platform_device_add_resources(pdev, &res, 1);
-
- pdev->dev.platform_data = pdata;
- intel_scu_device_register(pdev);
-}
-
-static const struct devs_id pmic_audio_dev_id __initconst = {
- .name = "pmic_audio",
- .type = SFI_DEV_TYPE_IPC,
- .delay = 1,
- .device_handler = &ipc_device_handler,
-};
-
-sfi_device(pmic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
deleted file mode 100644
index 79bb09d4f718..000000000000
--- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * platform_ipc.h: IPC platform library header file
- *
- * (C) Copyright 2013 Intel Corporation
- * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#ifndef _PLATFORM_IPC_H_
-#define _PLATFORM_IPC_H_
-
-void __init
-ipc_device_handler(struct sfi_device_table_entry *pentry, struct devs_id *dev);
-
-#endif
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c
new file mode 100644
index 000000000000..3135416df037
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c
@@ -0,0 +1,48 @@
+/*
+ * Intel Merrifield legacy RTC initialization file
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+
+#include <asm/hw_irq.h>
+#include <asm/intel-mid.h>
+#include <asm/io_apic.h>
+#include <asm/time.h>
+#include <asm/x86_init.h>
+
+static int __init mrfld_legacy_rtc_alloc_irq(void)
+{
+ struct irq_alloc_info info;
+ int ret;
+
+ if (!x86_platform.legacy.rtc)
+ return -ENODEV;
+
+ ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, 0);
+ ret = mp_map_gsi_to_irq(RTC_IRQ, IOAPIC_MAP_ALLOC, &info);
+ if (ret < 0) {
+ pr_info("Failed to allocate RTC interrupt. Disabling RTC\n");
+ x86_platform.legacy.rtc = 0;
+ return ret;
+ }
+
+ return 0;
+}
+
+static int __init mrfld_legacy_rtc_init(void)
+{
+ if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+ return -ENODEV;
+
+ return mrfld_legacy_rtc_alloc_irq();
+}
+arch_initcall(mrfld_legacy_rtc_init);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 3f1f1c77d090..86edd1e941eb 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -28,9 +28,9 @@ static struct platform_device wdt_dev = {
static int tangier_probe(struct platform_device *pdev)
{
- int gsi;
struct irq_alloc_info info;
struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
+ int gsi, irq;
if (!pdata)
return -EINVAL;
@@ -38,10 +38,10 @@ static int tangier_probe(struct platform_device *pdev)
/* IOAPIC builds identity mapping between GSI and IRQ on MID */
gsi = pdata->irq;
ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
- if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
- dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
- gsi);
- return -EINVAL;
+ irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+ if (irq < 0) {
+ dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", gsi);
+ return irq;
}
return 0;
@@ -82,4 +82,4 @@ static int __init register_mid_wdt(void)
return 0;
}
-rootfs_initcall(register_mid_wdt);
+arch_initcall(register_mid_wdt);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
index cb3490ecb341..d4dc744dd5a5 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
@@ -20,7 +20,6 @@
#include <asm/intel-mid.h>
#include "platform_msic.h"
-#include "platform_ipc.h"
static void *msic_audio_platform_data(void *info)
{
@@ -40,8 +39,8 @@ static const struct devs_id msic_audio_dev_id __initconst = {
.name = "msic_audio",
.type = SFI_DEV_TYPE_IPC,
.delay = 1,
+ .msic = 1,
.get_platform_data = &msic_audio_platform_data,
- .device_handler = &ipc_device_handler,
};
sfi_device(msic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
index 4f72193939a6..5c3e9919633f 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
@@ -19,7 +19,6 @@
#include <asm/intel-mid.h>
#include "platform_msic.h"
-#include "platform_ipc.h"
static void __init *msic_battery_platform_data(void *info)
{
@@ -30,8 +29,8 @@ static const struct devs_id msic_battery_dev_id __initconst = {
.name = "msic_battery",
.type = SFI_DEV_TYPE_IPC,
.delay = 1,
+ .msic = 1,
.get_platform_data = &msic_battery_platform_data,
- .device_handler = &ipc_device_handler,
};
sfi_device(msic_battery_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
index 70de5b531ba0..9fdb88d460d7 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
@@ -20,7 +20,6 @@
#include <asm/intel-mid.h>
#include "platform_msic.h"
-#include "platform_ipc.h"
static void __init *msic_gpio_platform_data(void *info)
{
@@ -41,8 +40,8 @@ static const struct devs_id msic_gpio_dev_id __initconst = {
.name = "msic_gpio",
.type = SFI_DEV_TYPE_IPC,
.delay = 1,
+ .msic = 1,
.get_platform_data = &msic_gpio_platform_data,
- .device_handler = &ipc_device_handler,
};
sfi_device(msic_gpio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
index 3d7c2011b6cf..7ae37cdbf256 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
@@ -20,7 +20,6 @@
#include <asm/intel-mid.h>
#include "platform_msic.h"
-#include "platform_ipc.h"
static void __init *msic_ocd_platform_data(void *info)
{
@@ -42,8 +41,8 @@ static const struct devs_id msic_ocd_dev_id __initconst = {
.name = "msic_ocd",
.type = SFI_DEV_TYPE_IPC,
.delay = 1,
+ .msic = 1,
.get_platform_data = &msic_ocd_platform_data,
- .device_handler = &ipc_device_handler,
};
sfi_device(msic_ocd_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
index 038f618fbc52..96809b98cf69 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
@@ -18,7 +18,6 @@
#include <asm/intel-mid.h>
#include "platform_msic.h"
-#include "platform_ipc.h"
static void __init *msic_power_btn_platform_data(void *info)
{
@@ -29,8 +28,8 @@ static const struct devs_id msic_power_btn_dev_id __initconst = {
.name = "msic_power_btn",
.type = SFI_DEV_TYPE_IPC,
.delay = 1,
+ .msic = 1,
.get_platform_data = &msic_power_btn_platform_data,
- .device_handler = &ipc_device_handler,
};
sfi_device(msic_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
index 114a5755b1e4..3e4167d246cd 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
@@ -19,7 +19,6 @@
#include <asm/intel-mid.h>
#include "platform_msic.h"
-#include "platform_ipc.h"
static void __init *msic_thermal_platform_data(void *info)
{
@@ -30,8 +29,8 @@ static const struct devs_id msic_thermal_dev_id __initconst = {
.name = "msic_thermal",
.type = SFI_DEV_TYPE_IPC,
.delay = 1,
+ .msic = 1,
.get_platform_data = &msic_thermal_platform_data,
- .device_handler = &ipc_device_handler,
};
sfi_device(msic_thermal_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
deleted file mode 100644
index e30cb62e3300..000000000000
--- a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * platform_pmic_gpio.c: PMIC GPIO platform data initialization file
- *
- * (C) Copyright 2013 Intel Corporation
- * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/scatterlist.h>
-#include <linux/gpio.h>
-#include <linux/init.h>
-#include <linux/sfi.h>
-#include <linux/intel_pmic_gpio.h>
-#include <asm/intel-mid.h>
-
-#include "platform_ipc.h"
-
-static void __init *pmic_gpio_platform_data(void *info)
-{
- static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
- int gpio_base = get_gpio_by_name("pmic_gpio_base");
-
- if (gpio_base < 0)
- gpio_base = 64;
- pmic_gpio_pdata.gpio_base = gpio_base;
- pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
- pmic_gpio_pdata.gpiointr = 0xffffeff8;
-
- return &pmic_gpio_pdata;
-}
-
-static const struct devs_id pmic_gpio_spi_dev_id __initconst = {
- .name = "pmic_gpio",
- .type = SFI_DEV_TYPE_SPI,
- .delay = 1,
- .get_platform_data = &pmic_gpio_platform_data,
-};
-
-static const struct devs_id pmic_gpio_ipc_dev_id __initconst = {
- .name = "pmic_gpio",
- .type = SFI_DEV_TYPE_IPC,
- .delay = 1,
- .get_platform_data = &pmic_gpio_platform_data,
- .device_handler = &ipc_device_handler
-};
-
-sfi_device(pmic_gpio_spi_dev_id);
-sfi_device(pmic_gpio_ipc_dev_id);
diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c
index e0607c77a1bd..ae7bdeb0e507 100644
--- a/arch/x86/platform/intel-mid/mrfld.c
+++ b/arch/x86/platform/intel-mid/mrfld.c
@@ -91,6 +91,7 @@ static unsigned long __init tangier_calibrate_tsc(void)
static void __init tangier_arch_setup(void)
{
x86_platform.calibrate_tsc = tangier_calibrate_tsc;
+ x86_platform.legacy.rtc = 1;
}
/* tangier arch ops */
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 051d264fce2e..19b43e3a9f0f 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -15,7 +15,6 @@
#include <linux/interrupt.h>
#include <linux/scatterlist.h>
#include <linux/sfi.h>
-#include <linux/intel_pmic_gpio.h>
#include <linux/spi/spi.h>
#include <linux/i2c.h>
#include <linux/skbuff.h>
@@ -226,7 +225,7 @@ int get_gpio_by_name(const char *name)
return -EINVAL;
}
-void __init intel_scu_device_register(struct platform_device *pdev)
+static void __init intel_scu_ipc_device_register(struct platform_device *pdev)
{
if (ipc_next_dev == MAX_IPCDEVS)
pr_err("too many SCU IPC devices");
@@ -335,10 +334,22 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry,
pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
pentry->name, pentry->irq);
+
+ /*
+ * We need to call platform init of IPC devices to fill misc_pdata
+ * structure. It will be used in msic_init for initialization.
+ */
pdata = intel_mid_sfi_get_pdata(dev, pentry);
if (IS_ERR(pdata))
return;
+ /*
+ * On Medfield the platform device creation is handled by the MSIC
+ * MFD driver so we don't need to do it here.
+ */
+ if (dev->msic && intel_mid_has_msic())
+ return;
+
pdev = platform_device_alloc(pentry->name, 0);
if (pdev == NULL) {
pr_err("out of memory for SFI platform device '%s'.\n",
@@ -348,7 +359,10 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry,
install_irq_resource(pdev, pentry->irq);
pdev->dev.platform_data = pdata;
- platform_device_add(pdev);
+ if (dev->delay)
+ intel_scu_ipc_device_register(pdev);
+ else
+ platform_device_add(pdev);
}
static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry,
@@ -503,27 +517,23 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
if (!dev)
continue;
- if (dev->device_handler) {
- dev->device_handler(pentry, dev);
- } else {
- switch (pentry->type) {
- case SFI_DEV_TYPE_IPC:
- sfi_handle_ipc_dev(pentry, dev);
- break;
- case SFI_DEV_TYPE_SPI:
- sfi_handle_spi_dev(pentry, dev);
- break;
- case SFI_DEV_TYPE_I2C:
- sfi_handle_i2c_dev(pentry, dev);
- break;
- case SFI_DEV_TYPE_SD:
- sfi_handle_sd_dev(pentry, dev);
- break;
- case SFI_DEV_TYPE_UART:
- case SFI_DEV_TYPE_HSI:
- default:
- break;
- }
+ switch (pentry->type) {
+ case SFI_DEV_TYPE_IPC:
+ sfi_handle_ipc_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_SPI:
+ sfi_handle_spi_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_I2C:
+ sfi_handle_i2c_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_SD:
+ sfi_handle_sd_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_UART:
+ case SFI_DEV_TYPE_HSI:
+ default:
+ break;
}
}
return 0;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 8410e7d0a5b5..9743d0ccfec6 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -45,8 +45,8 @@
*
* Handle system-wide NMI events generated by the global 'power nmi' command.
*
- * Basic operation is to field the NMI interrupt on each cpu and wait
- * until all cpus have arrived into the nmi handler. If some cpus do not
+ * Basic operation is to field the NMI interrupt on each CPU and wait
+ * until all CPU's have arrived into the nmi handler. If some CPU's do not
* make it into the handler, try and force them in with the IPI(NMI) signal.
*
* We also have to lessen UV Hub MMR accesses as much as possible as this
@@ -56,7 +56,7 @@
* To do this we register our primary NMI notifier on the NMI_UNKNOWN
* chain. This reduces the number of false NMI calls when the perf
* tools are running which generate an enormous number of NMIs per
- * second (~4M/s for 1024 cpu threads). Our secondary NMI handler is
+ * second (~4M/s for 1024 CPU threads). Our secondary NMI handler is
* very short as it only checks that if it has been "pinged" with the
* IPI(NMI) signal as mentioned above, and does not read the UV Hub's MMR.
*
@@ -65,8 +65,20 @@
static struct uv_hub_nmi_s **uv_hub_nmi_list;
DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
-EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi);
+/* UV hubless values */
+#define NMI_CONTROL_PORT 0x70
+#define NMI_DUMMY_PORT 0x71
+#define PAD_OWN_GPP_D_0 0x2c
+#define GPI_NMI_STS_GPP_D_0 0x164
+#define GPI_NMI_ENA_GPP_D_0 0x174
+#define STS_GPP_D_0_MASK 0x1
+#define PAD_CFG_DW0_GPP_D_0 0x4c0
+#define GPIROUTNMI (1ul << 17)
+#define PCH_PCR_GPIO_1_BASE 0xfdae0000ul
+#define PCH_PCR_GPIO_ADDRESS(offset) (int *)((u64)(pch_base) | (u64)(offset))
+
+static u64 *pch_base;
static unsigned long nmi_mmr;
static unsigned long nmi_mmr_clear;
static unsigned long nmi_mmr_pending;
@@ -100,7 +112,7 @@ static int param_get_local64(char *buffer, const struct kernel_param *kp)
static int param_set_local64(const char *val, const struct kernel_param *kp)
{
- /* clear on any write */
+ /* Clear on any write */
local64_set((local64_t *)kp->arg, 0);
return 0;
}
@@ -144,16 +156,80 @@ module_param_named(wait_count, uv_nmi_wait_count, int, 0644);
static int uv_nmi_retry_count = 500;
module_param_named(retry_count, uv_nmi_retry_count, int, 0644);
-/*
- * Valid NMI Actions:
- * "dump" - dump process stack for each cpu
- * "ips" - dump IP info for each cpu
- * "kdump" - do crash dump
- * "kdb" - enter KDB (default)
- * "kgdb" - enter KGDB
- */
-static char uv_nmi_action[8] = "kdb";
-module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644);
+static bool uv_pch_intr_enable = true;
+static bool uv_pch_intr_now_enabled;
+module_param_named(pch_intr_enable, uv_pch_intr_enable, bool, 0644);
+
+static bool uv_pch_init_enable = true;
+module_param_named(pch_init_enable, uv_pch_init_enable, bool, 0644);
+
+static int uv_nmi_debug;
+module_param_named(debug, uv_nmi_debug, int, 0644);
+
+#define nmi_debug(fmt, ...) \
+ do { \
+ if (uv_nmi_debug) \
+ pr_info(fmt, ##__VA_ARGS__); \
+ } while (0)
+
+/* Valid NMI Actions */
+#define ACTION_LEN 16
+static struct nmi_action {
+ char *action;
+ char *desc;
+} valid_acts[] = {
+ { "kdump", "do kernel crash dump" },
+ { "dump", "dump process stack for each cpu" },
+ { "ips", "dump Inst Ptr info for each cpu" },
+ { "kdb", "enter KDB (needs kgdboc= assignment)" },
+ { "kgdb", "enter KGDB (needs gdb target remote)" },
+ { "health", "check if CPUs respond to NMI" },
+};
+typedef char action_t[ACTION_LEN];
+static action_t uv_nmi_action = { "dump" };
+
+static int param_get_action(char *buffer, const struct kernel_param *kp)
+{
+ return sprintf(buffer, "%s\n", uv_nmi_action);
+}
+
+static int param_set_action(const char *val, const struct kernel_param *kp)
+{
+ int i;
+ int n = ARRAY_SIZE(valid_acts);
+ char arg[ACTION_LEN], *p;
+
+ /* (remove possible '\n') */
+ strncpy(arg, val, ACTION_LEN - 1);
+ arg[ACTION_LEN - 1] = '\0';
+ p = strchr(arg, '\n');
+ if (p)
+ *p = '\0';
+
+ for (i = 0; i < n; i++)
+ if (!strcmp(arg, valid_acts[i].action))
+ break;
+
+ if (i < n) {
+ strcpy(uv_nmi_action, arg);
+ pr_info("UV: New NMI action:%s\n", uv_nmi_action);
+ return 0;
+ }
+
+ pr_err("UV: Invalid NMI action:%s, valid actions are:\n", arg);
+ for (i = 0; i < n; i++)
+ pr_err("UV: %-8s - %s\n",
+ valid_acts[i].action, valid_acts[i].desc);
+ return -EINVAL;
+}
+
+static const struct kernel_param_ops param_ops_action = {
+ .get = param_get_action,
+ .set = param_set_action,
+};
+#define param_check_action(name, p) __param_check(name, p, action_t)
+
+module_param_named(action, uv_nmi_action, action, 0644);
static inline bool uv_nmi_action_is(const char *action)
{
@@ -192,8 +268,200 @@ static inline void uv_local_mmr_clear_nmi(void)
}
/*
- * If first cpu in on this hub, set hub_nmi "in_nmi" and "owner" values and
- * return true. If first cpu in on the system, set global "in_nmi" flag.
+ * UV hubless NMI handler functions
+ */
+static inline void uv_reassert_nmi(void)
+{
+ /* (from arch/x86/include/asm/mach_traps.h) */
+ outb(0x8f, NMI_CONTROL_PORT);
+ inb(NMI_DUMMY_PORT); /* dummy read */
+ outb(0x0f, NMI_CONTROL_PORT);
+ inb(NMI_DUMMY_PORT); /* dummy read */
+}
+
+static void uv_init_hubless_pch_io(int offset, int mask, int data)
+{
+ int *addr = PCH_PCR_GPIO_ADDRESS(offset);
+ int readd = readl(addr);
+
+ if (mask) { /* OR in new data */
+ int writed = (readd & ~mask) | data;
+
+ nmi_debug("UV:PCH: %p = %x & %x | %x (%x)\n",
+ addr, readd, ~mask, data, writed);
+ writel(writed, addr);
+ } else if (readd & data) { /* clear status bit */
+ nmi_debug("UV:PCH: %p = %x\n", addr, data);
+ writel(data, addr);
+ }
+
+ (void)readl(addr); /* flush write data */
+}
+
+static void uv_nmi_setup_hubless_intr(void)
+{
+ uv_pch_intr_now_enabled = uv_pch_intr_enable;
+
+ uv_init_hubless_pch_io(
+ PAD_CFG_DW0_GPP_D_0, GPIROUTNMI,
+ uv_pch_intr_now_enabled ? GPIROUTNMI : 0);
+
+ nmi_debug("UV:NMI: GPP_D_0 interrupt %s\n",
+ uv_pch_intr_now_enabled ? "enabled" : "disabled");
+}
+
+static struct init_nmi {
+ unsigned int offset;
+ unsigned int mask;
+ unsigned int data;
+} init_nmi[] = {
+ { /* HOSTSW_OWN_GPP_D_0 */
+ .offset = 0x84,
+ .mask = 0x1,
+ .data = 0x0, /* ACPI Mode */
+ },
+
+/* Clear status: */
+ { /* GPI_INT_STS_GPP_D_0 */
+ .offset = 0x104,
+ .mask = 0x0,
+ .data = 0x1, /* Clear Status */
+ },
+ { /* GPI_GPE_STS_GPP_D_0 */
+ .offset = 0x124,
+ .mask = 0x0,
+ .data = 0x1, /* Clear Status */
+ },
+ { /* GPI_SMI_STS_GPP_D_0 */
+ .offset = 0x144,
+ .mask = 0x0,
+ .data = 0x1, /* Clear Status */
+ },
+ { /* GPI_NMI_STS_GPP_D_0 */
+ .offset = 0x164,
+ .mask = 0x0,
+ .data = 0x1, /* Clear Status */
+ },
+
+/* Disable interrupts: */
+ { /* GPI_INT_EN_GPP_D_0 */
+ .offset = 0x114,
+ .mask = 0x1,
+ .data = 0x0, /* Disable interrupt generation */
+ },
+ { /* GPI_GPE_EN_GPP_D_0 */
+ .offset = 0x134,
+ .mask = 0x1,
+ .data = 0x0, /* Disable interrupt generation */
+ },
+ { /* GPI_SMI_EN_GPP_D_0 */
+ .offset = 0x154,
+ .mask = 0x1,
+ .data = 0x0, /* Disable interrupt generation */
+ },
+ { /* GPI_NMI_EN_GPP_D_0 */
+ .offset = 0x174,
+ .mask = 0x1,
+ .data = 0x0, /* Disable interrupt generation */
+ },
+
+/* Setup GPP_D_0 Pad Config: */
+ { /* PAD_CFG_DW0_GPP_D_0 */
+ .offset = 0x4c0,
+ .mask = 0xffffffff,
+ .data = 0x82020100,
+/*
+ * 31:30 Pad Reset Config (PADRSTCFG): = 2h # PLTRST# (default)
+ *
+ * 29 RX Pad State Select (RXPADSTSEL): = 0 # Raw RX pad state directly
+ * from RX buffer (default)
+ *
+ * 28 RX Raw Override to '1' (RXRAW1): = 0 # No Override
+ *
+ * 26:25 RX Level/Edge Configuration (RXEVCFG):
+ * = 0h # Level
+ * = 1h # Edge
+ *
+ * 23 RX Invert (RXINV): = 0 # No Inversion (signal active high)
+ *
+ * 20 GPIO Input Route IOxAPIC (GPIROUTIOXAPIC):
+ * = 0 # Routing does not cause peripheral IRQ...
+ * # (we want an NMI not an IRQ)
+ *
+ * 19 GPIO Input Route SCI (GPIROUTSCI): = 0 # Routing does not cause SCI.
+ * 18 GPIO Input Route SMI (GPIROUTSMI): = 0 # Routing does not cause SMI.
+ * 17 GPIO Input Route NMI (GPIROUTNMI): = 1 # Routing can cause NMI.
+ *
+ * 11:10 Pad Mode (PMODE1/0): = 0h = GPIO control the Pad.
+ * 9 GPIO RX Disable (GPIORXDIS):
+ * = 0 # Enable the input buffer (active low enable)
+ *
+ * 8 GPIO TX Disable (GPIOTXDIS):
+ * = 1 # Disable the output buffer; i.e. Hi-Z
+ *
+ * 1 GPIO RX State (GPIORXSTATE): This is the current internal RX pad state..
+ * 0 GPIO TX State (GPIOTXSTATE):
+ * = 0 # (Leave at default)
+ */
+ },
+
+/* Pad Config DW1 */
+ { /* PAD_CFG_DW1_GPP_D_0 */
+ .offset = 0x4c4,
+ .mask = 0x3c00,
+ .data = 0, /* Termination = none (default) */
+ },
+};
+
+static void uv_init_hubless_pch_d0(void)
+{
+ int i, read;
+
+ read = *PCH_PCR_GPIO_ADDRESS(PAD_OWN_GPP_D_0);
+ if (read != 0) {
+ pr_info("UV: Hubless NMI already configured\n");
+ return;
+ }
+
+ nmi_debug("UV: Initializing UV Hubless NMI on PCH\n");
+ for (i = 0; i < ARRAY_SIZE(init_nmi); i++) {
+ uv_init_hubless_pch_io(init_nmi[i].offset,
+ init_nmi[i].mask,
+ init_nmi[i].data);
+ }
+}
+
+static int uv_nmi_test_hubless(struct uv_hub_nmi_s *hub_nmi)
+{
+ int *pstat = PCH_PCR_GPIO_ADDRESS(GPI_NMI_STS_GPP_D_0);
+ int status = *pstat;
+
+ hub_nmi->nmi_value = status;
+ atomic_inc(&hub_nmi->read_mmr_count);
+
+ if (!(status & STS_GPP_D_0_MASK)) /* Not a UV external NMI */
+ return 0;
+
+ *pstat = STS_GPP_D_0_MASK; /* Is a UV NMI: clear GPP_D_0 status */
+ (void)*pstat; /* Flush write */
+
+ return 1;
+}
+
+static int uv_test_nmi(struct uv_hub_nmi_s *hub_nmi)
+{
+ if (hub_nmi->hub_present)
+ return uv_nmi_test_mmr(hub_nmi);
+
+ if (hub_nmi->pch_owner) /* Only PCH owner can check status */
+ return uv_nmi_test_hubless(hub_nmi);
+
+ return -1;
+}
+
+/*
+ * If first CPU in on this hub, set hub_nmi "in_nmi" and "owner" values and
+ * return true. If first CPU in on the system, set global "in_nmi" flag.
*/
static int uv_set_in_nmi(int cpu, struct uv_hub_nmi_s *hub_nmi)
{
@@ -214,6 +482,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
{
int cpu = smp_processor_id();
int nmi = 0;
+ int nmi_detected = 0;
local64_inc(&uv_nmi_count);
this_cpu_inc(uv_cpu_nmi.queries);
@@ -224,35 +493,48 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
break;
if (raw_spin_trylock(&hub_nmi->nmi_lock)) {
+ nmi_detected = uv_test_nmi(hub_nmi);
- /* check hub MMR NMI flag */
- if (uv_nmi_test_mmr(hub_nmi)) {
+ /* Check flag for UV external NMI */
+ if (nmi_detected > 0) {
uv_set_in_nmi(cpu, hub_nmi);
nmi = 1;
break;
}
- /* MMR NMI flag is clear */
+ /* A non-PCH node in a hubless system waits for NMI */
+ else if (nmi_detected < 0)
+ goto slave_wait;
+
+ /* MMR/PCH NMI flag is clear */
raw_spin_unlock(&hub_nmi->nmi_lock);
} else {
- /* wait a moment for the hub nmi locker to set flag */
- cpu_relax();
+
+ /* Wait a moment for the HUB NMI locker to set flag */
+slave_wait: cpu_relax();
udelay(uv_nmi_slave_delay);
- /* re-check hub in_nmi flag */
+ /* Re-check hub in_nmi flag */
nmi = atomic_read(&hub_nmi->in_nmi);
if (nmi)
break;
}
- /* check if this BMC missed setting the MMR NMI flag */
+ /*
+ * Check if this BMC missed setting the MMR NMI flag (or)
+ * UV hubless system where only PCH owner can check flag
+ */
if (!nmi) {
nmi = atomic_read(&uv_in_nmi);
if (nmi)
uv_set_in_nmi(cpu, hub_nmi);
}
+ /* If we're holding the hub lock, release it now */
+ if (nmi_detected < 0)
+ raw_spin_unlock(&hub_nmi->nmi_lock);
+
} while (0);
if (!nmi)
@@ -269,12 +551,15 @@ static inline void uv_clear_nmi(int cpu)
if (cpu == atomic_read(&hub_nmi->cpu_owner)) {
atomic_set(&hub_nmi->cpu_owner, -1);
atomic_set(&hub_nmi->in_nmi, 0);
- uv_local_mmr_clear_nmi();
+ if (hub_nmi->hub_present)
+ uv_local_mmr_clear_nmi();
+ else
+ uv_reassert_nmi();
raw_spin_unlock(&hub_nmi->nmi_lock);
}
}
-/* Ping non-responding cpus attemping to force them into the NMI handler */
+/* Ping non-responding CPU's attemping to force them into the NMI handler */
static void uv_nmi_nr_cpus_ping(void)
{
int cpu;
@@ -285,7 +570,7 @@ static void uv_nmi_nr_cpus_ping(void)
apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI);
}
-/* Clean up flags for cpus that ignored both NMI and ping */
+/* Clean up flags for CPU's that ignored both NMI and ping */
static void uv_nmi_cleanup_mask(void)
{
int cpu;
@@ -297,11 +582,12 @@ static void uv_nmi_cleanup_mask(void)
}
}
-/* Loop waiting as cpus enter nmi handler */
+/* Loop waiting as CPU's enter NMI handler */
static int uv_nmi_wait_cpus(int first)
{
int i, j, k, n = num_online_cpus();
int last_k = 0, waiting = 0;
+ int cpu = smp_processor_id();
if (first) {
cpumask_copy(uv_nmi_cpu_mask, cpu_online_mask);
@@ -310,6 +596,12 @@ static int uv_nmi_wait_cpus(int first)
k = n - cpumask_weight(uv_nmi_cpu_mask);
}
+ /* PCH NMI causes only one CPU to respond */
+ if (first && uv_pch_intr_now_enabled) {
+ cpumask_clear_cpu(cpu, uv_nmi_cpu_mask);
+ return n - k - 1;
+ }
+
udelay(uv_nmi_initial_delay);
for (i = 0; i < uv_nmi_retry_count; i++) {
int loop_delay = uv_nmi_loop_delay;
@@ -325,13 +617,13 @@ static int uv_nmi_wait_cpus(int first)
k = n;
break;
}
- if (last_k != k) { /* abort if no new cpus coming in */
+ if (last_k != k) { /* abort if no new CPU's coming in */
last_k = k;
waiting = 0;
} else if (++waiting > uv_nmi_wait_count)
break;
- /* extend delay if waiting only for cpu 0 */
+ /* Extend delay if waiting only for CPU 0: */
if (waiting && (n - k) == 1 &&
cpumask_test_cpu(0, uv_nmi_cpu_mask))
loop_delay *= 100;
@@ -342,29 +634,29 @@ static int uv_nmi_wait_cpus(int first)
return n - k;
}
-/* Wait until all slave cpus have entered UV NMI handler */
+/* Wait until all slave CPU's have entered UV NMI handler */
static void uv_nmi_wait(int master)
{
- /* indicate this cpu is in */
+ /* Indicate this CPU is in: */
this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN);
- /* if not the first cpu in (the master), then we are a slave cpu */
+ /* If not the first CPU in (the master), then we are a slave CPU */
if (!master)
return;
do {
- /* wait for all other cpus to gather here */
+ /* Wait for all other CPU's to gather here */
if (!uv_nmi_wait_cpus(1))
break;
- /* if not all made it in, send IPI NMI to them */
- pr_alert("UV: Sending NMI IPI to %d non-responding CPUs: %*pbl\n",
+ /* If not all made it in, send IPI NMI to them */
+ pr_alert("UV: Sending NMI IPI to %d CPUs: %*pbl\n",
cpumask_weight(uv_nmi_cpu_mask),
cpumask_pr_args(uv_nmi_cpu_mask));
uv_nmi_nr_cpus_ping();
- /* if all cpus are in, then done */
+ /* If all CPU's are in, then done */
if (!uv_nmi_wait_cpus(0))
break;
@@ -416,7 +708,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
}
-/* Trigger a slave cpu to dump it's state */
+/* Trigger a slave CPU to dump it's state */
static void uv_nmi_trigger_dump(int cpu)
{
int retry = uv_nmi_trigger_delay;
@@ -437,7 +729,7 @@ static void uv_nmi_trigger_dump(int cpu)
uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE;
}
-/* Wait until all cpus ready to exit */
+/* Wait until all CPU's ready to exit */
static void uv_nmi_sync_exit(int master)
{
atomic_dec(&uv_nmi_cpus_in_nmi);
@@ -451,7 +743,23 @@ static void uv_nmi_sync_exit(int master)
}
}
-/* Walk through cpu list and dump state of each */
+/* Current "health" check is to check which CPU's are responsive */
+static void uv_nmi_action_health(int cpu, struct pt_regs *regs, int master)
+{
+ if (master) {
+ int in = atomic_read(&uv_nmi_cpus_in_nmi);
+ int out = num_online_cpus() - in;
+
+ pr_alert("UV: NMI CPU health check (non-responding:%d)\n", out);
+ atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT);
+ } else {
+ while (!atomic_read(&uv_nmi_slave_continue))
+ cpu_relax();
+ }
+ uv_nmi_sync_exit(master);
+}
+
+/* Walk through CPU list and dump state of each */
static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
{
if (master) {
@@ -538,7 +846,7 @@ static inline int uv_nmi_kdb_reason(void)
#else /* !CONFIG_KGDB_KDB */
static inline int uv_nmi_kdb_reason(void)
{
- /* Insure user is expecting to attach gdb remote */
+ /* Ensure user is expecting to attach gdb remote */
if (uv_nmi_action_is("kgdb"))
return 0;
@@ -563,7 +871,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
if (reason < 0)
return;
- /* call KGDB NMI handler as MASTER */
+ /* Call KGDB NMI handler as MASTER */
ret = kgdb_nmicallin(cpu, X86_TRAP_NMI, regs, reason,
&uv_nmi_slave_continue);
if (ret) {
@@ -571,7 +879,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT);
}
} else {
- /* wait for KGDB signal that it's ready for slaves to enter */
+ /* Wait for KGDB signal that it's ready for slaves to enter */
int sig;
do {
@@ -579,7 +887,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
sig = atomic_read(&uv_nmi_slave_continue);
} while (!sig);
- /* call KGDB as slave */
+ /* Call KGDB as slave */
if (sig == SLAVE_CONTINUE)
kgdb_nmicallback(cpu, regs);
}
@@ -623,18 +931,23 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
strncpy(uv_nmi_action, "dump", strlen(uv_nmi_action));
}
- /* Pause as all cpus enter the NMI handler */
+ /* Pause as all CPU's enter the NMI handler */
uv_nmi_wait(master);
- /* Dump state of each cpu */
- if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump"))
+ /* Process actions other than "kdump": */
+ if (uv_nmi_action_is("health")) {
+ uv_nmi_action_health(cpu, regs, master);
+ } else if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) {
uv_nmi_dump_state(cpu, regs, master);
-
- /* Call KGDB/KDB if enabled */
- else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb"))
+ } else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) {
uv_call_kgdb_kdb(cpu, regs, master);
+ } else {
+ if (master)
+ pr_alert("UV: unknown NMI action: %s\n", uv_nmi_action);
+ uv_nmi_sync_exit(master);
+ }
- /* Clear per_cpu "in nmi" flag */
+ /* Clear per_cpu "in_nmi" flag */
this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT);
/* Clear MMR NMI flag on each hub */
@@ -648,6 +961,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
atomic_set(&uv_nmi_cpu, -1);
atomic_set(&uv_in_nmi, 0);
atomic_set(&uv_nmi_kexec_failed, 0);
+ atomic_set(&uv_nmi_slave_continue, SLAVE_CLEAR);
}
uv_nmi_touch_watchdogs();
@@ -657,7 +971,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
}
/*
- * NMI handler for pulling in CPUs when perf events are grabbing our NMI
+ * NMI handler for pulling in CPU's when perf events are grabbing our NMI
*/
static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs)
{
@@ -690,35 +1004,62 @@ void uv_nmi_init(void)
unsigned int value;
/*
- * Unmask NMI on all cpus
+ * Unmask NMI on all CPU's
*/
value = apic_read(APIC_LVT1) | APIC_DM_NMI;
value &= ~APIC_LVT_MASKED;
apic_write(APIC_LVT1, value);
}
-void uv_nmi_setup(void)
+/* Setup HUB NMI info */
+void __init uv_nmi_setup_common(bool hubbed)
{
int size = sizeof(void *) * (1 << NODES_SHIFT);
- int cpu, nid;
+ int cpu;
- /* Setup hub nmi info */
- uv_nmi_setup_mmrs();
uv_hub_nmi_list = kzalloc(size, GFP_KERNEL);
- pr_info("UV: NMI hub list @ 0x%p (%d)\n", uv_hub_nmi_list, size);
+ nmi_debug("UV: NMI hub list @ 0x%p (%d)\n", uv_hub_nmi_list, size);
BUG_ON(!uv_hub_nmi_list);
size = sizeof(struct uv_hub_nmi_s);
for_each_present_cpu(cpu) {
- nid = cpu_to_node(cpu);
+ int nid = cpu_to_node(cpu);
if (uv_hub_nmi_list[nid] == NULL) {
uv_hub_nmi_list[nid] = kzalloc_node(size,
GFP_KERNEL, nid);
BUG_ON(!uv_hub_nmi_list[nid]);
raw_spin_lock_init(&(uv_hub_nmi_list[nid]->nmi_lock));
atomic_set(&uv_hub_nmi_list[nid]->cpu_owner, -1);
+ uv_hub_nmi_list[nid]->hub_present = hubbed;
+ uv_hub_nmi_list[nid]->pch_owner = (nid == 0);
}
uv_hub_nmi_per(cpu) = uv_hub_nmi_list[nid];
}
BUG_ON(!alloc_cpumask_var(&uv_nmi_cpu_mask, GFP_KERNEL));
+}
+
+/* Setup for UV Hub systems */
+void __init uv_nmi_setup(void)
+{
+ uv_nmi_setup_mmrs();
+ uv_nmi_setup_common(true);
+ uv_register_nmi_notifier();
+ pr_info("UV: Hub NMI enabled\n");
+}
+
+/* Setup for UV Hubless systems */
+void __init uv_nmi_setup_hubless(void)
+{
+ uv_nmi_setup_common(false);
+ pch_base = xlate_dev_mem_ptr(PCH_PCR_GPIO_1_BASE);
+ nmi_debug("UV: PCH base:%p from 0x%lx, GPP_D_0\n",
+ pch_base, PCH_PCR_GPIO_1_BASE);
+ if (uv_pch_init_enable)
+ uv_init_hubless_pch_d0();
+ uv_init_hubless_pch_io(GPI_NMI_ENA_GPP_D_0,
+ STS_GPP_D_0_MASK, STS_GPP_D_0_MASK);
+ uv_nmi_setup_hubless_intr();
+ /* Ensure NMI enabled in Processor Interface Reg: */
+ uv_reassert_nmi();
uv_register_nmi_notifier();
+ pr_info("UV: Hubless NMI enabled\n");
}
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index d957d5f21a86..0bc60a308730 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -1,6 +1,6 @@
config MCE_AMD_INJ
tristate "Simple MCE injection interface for AMD processors"
- depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB
+ depends on RAS && X86_MCE && DEBUG_FS && AMD_NB
default n
help
This is a simple debugfs interface to inject MCEs and test different
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index c7b15f3e2cf3..76b6dbd627df 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -53,5 +53,5 @@ config XEN_DEBUG_FS
config XEN_PVH
bool "Support for running as a PVH guest"
- depends on X86_64 && XEN && XEN_PVHVM
+ depends on XEN && XEN_PVHVM && ACPI
def_bool n
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index e47e52787d32..cb0164aee156 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -23,3 +23,4 @@ obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
obj-$(CONFIG_XEN_DOM0) += vga.o
obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o
obj-$(CONFIG_XEN_EFI) += efi.o
+obj-$(CONFIG_XEN_PVH) += xen-pvh.o
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 44c88ad1841a..bcea81f36fc5 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -145,7 +145,7 @@ static void xen_silent_inquire(int apicid)
static int xen_cpu_present_to_apicid(int cpu)
{
if (cpu_present(cpu))
- return xen_get_apic_id(xen_apic_read(APIC_ID));
+ return cpu_data(cpu).apicid;
else
return BAD_APICID;
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 51ef95232725..ec1d5c46e58f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -45,6 +45,7 @@
#include <xen/interface/memory.h>
#include <xen/interface/nmi.h>
#include <xen/interface/xen-mca.h>
+#include <xen/interface/hvm/start_info.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/hvm.h>
@@ -176,6 +177,20 @@ struct tls_descs {
*/
static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
+#ifdef CONFIG_XEN_PVH
+/*
+ * PVH variables.
+ *
+ * xen_pvh and pvh_bootparams need to live in data segment since they
+ * are used after startup_{32|64}, which clear .bss, are invoked.
+ */
+bool xen_pvh __attribute__((section(".data"))) = 0;
+struct boot_params pvh_bootparams __attribute__((section(".data")));
+
+struct hvm_start_info pvh_start_info;
+unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+#endif
+
static void clamp_max_cpus(void)
{
#ifdef CONFIG_SMP
@@ -1138,10 +1153,11 @@ void xen_setup_vcpu_info_placement(void)
xen_vcpu_setup(cpu);
}
- /* xen_vcpu_setup managed to place the vcpu_info within the
- * percpu area for all cpus, so make use of it. Note that for
- * PVH we want to use native IRQ mechanism. */
- if (have_vcpu_info_placement && !xen_pvh_domain()) {
+ /*
+ * xen_vcpu_setup managed to place the vcpu_info within the
+ * percpu area for all cpus, so make use of it.
+ */
+ if (have_vcpu_info_placement) {
pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
@@ -1413,49 +1429,9 @@ static void __init xen_boot_params_init_edd(void)
* Set up the GDT and segment registers for -fstack-protector. Until
* we do this, we have to be careful not to call any stack-protected
* function, which is most of the kernel.
- *
- * Note, that it is __ref because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
*/
-static void __ref xen_setup_gdt(int cpu)
+static void xen_setup_gdt(int cpu)
{
- if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_X86_64
- unsigned long dummy;
-
- load_percpu_segment(cpu); /* We need to access per-cpu area */
- switch_to_new_gdt(cpu); /* GDT and GS set */
-
- /* We are switching of the Xen provided GDT to our HVM mode
- * GDT. The new GDT has __KERNEL_CS with CS.L = 1
- * and we are jumping to reload it.
- */
- asm volatile ("pushq %0\n"
- "leaq 1f(%%rip),%0\n"
- "pushq %0\n"
- "lretq\n"
- "1:\n"
- : "=&r" (dummy) : "0" (__KERNEL_CS));
-
- /*
- * While not needed, we also set the %es, %ds, and %fs
- * to zero. We don't care about %ss as it is NULL.
- * Strictly speaking this is not needed as Xen zeros those
- * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE)
- *
- * Linux zeros them in cpu_init() and in secondary_startup_64
- * (for BSP).
- */
- loadsegment(es, 0);
- loadsegment(ds, 0);
- loadsegment(fs, 0);
-#else
- /* PVH: TODO Implement. */
- BUG();
-#endif
- return; /* PVH does not need any PV GDT ops. */
- }
pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
pv_cpu_ops.load_gdt = xen_load_gdt_boot;
@@ -1466,59 +1442,6 @@ static void __ref xen_setup_gdt(int cpu)
pv_cpu_ops.load_gdt = xen_load_gdt;
}
-#ifdef CONFIG_XEN_PVH
-/*
- * A PV guest starts with default flags that are not set for PVH, set them
- * here asap.
- */
-static void xen_pvh_set_cr_flags(int cpu)
-{
-
- /* Some of these are setup in 'secondary_startup_64'. The others:
- * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
- * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
- write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
-
- if (!cpu)
- return;
- /*
- * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
- * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
- */
- if (boot_cpu_has(X86_FEATURE_PSE))
- cr4_set_bits_and_update_boot(X86_CR4_PSE);
-
- if (boot_cpu_has(X86_FEATURE_PGE))
- cr4_set_bits_and_update_boot(X86_CR4_PGE);
-}
-
-/*
- * Note, that it is ref - because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
- */
-void __ref xen_pvh_secondary_vcpu_init(int cpu)
-{
- xen_setup_gdt(cpu);
- xen_pvh_set_cr_flags(cpu);
-}
-
-static void __init xen_pvh_early_guest_init(void)
-{
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
- BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
-
- xen_pvh_early_cpu_init(0, false);
- xen_pvh_set_cr_flags(0);
-
-#ifdef CONFIG_X86_32
- BUG(); /* PVH: Implement proper support. */
-#endif
-}
-#endif /* CONFIG_XEN_PVH */
-
static void __init xen_dom0_set_legacy_features(void)
{
x86_platform.legacy.rtc = 1;
@@ -1555,24 +1478,17 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_domain_type = XEN_PV_DOMAIN;
xen_setup_features();
-#ifdef CONFIG_XEN_PVH
- xen_pvh_early_guest_init();
-#endif
+
xen_setup_machphys_mapping();
/* Install Xen paravirt ops */
pv_info = xen_info;
pv_init_ops = xen_init_ops;
- if (!xen_pvh_domain()) {
- pv_cpu_ops = xen_cpu_ops;
+ pv_cpu_ops = xen_cpu_ops;
- x86_platform.get_nmi_reason = xen_get_nmi_reason;
- }
+ x86_platform.get_nmi_reason = xen_get_nmi_reason;
- if (xen_feature(XENFEAT_auto_translated_physmap))
- x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
- else
- x86_init.resources.memory_setup = xen_memory_setup;
+ x86_init.resources.memory_setup = xen_memory_setup;
x86_init.oem.arch_setup = xen_arch_setup;
x86_init.oem.banner = xen_banner;
@@ -1665,18 +1581,15 @@ asmlinkage __visible void __init xen_start_kernel(void)
/* set the limit of our address space */
xen_reserve_top();
- /* PVH: runs at default kernel iopl of 0 */
- if (!xen_pvh_domain()) {
- /*
- * We used to do this in xen_arch_setup, but that is too late
- * on AMD were early_cpu_init (run before ->arch_setup()) calls
- * early_amd_init which pokes 0xcf8 port.
- */
- set_iopl.iopl = 1;
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
- if (rc != 0)
- xen_raw_printk("physdev_op failed %d\n", rc);
- }
+ /*
+ * We used to do this in xen_arch_setup, but that is too late
+ * on AMD were early_cpu_init (run before ->arch_setup()) calls
+ * early_amd_init which pokes 0xcf8 port.
+ */
+ set_iopl.iopl = 1;
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+ if (rc != 0)
+ xen_raw_printk("physdev_op failed %d\n", rc);
#ifdef CONFIG_X86_32
/* set up basic CPUID stuff */
@@ -1758,6 +1671,102 @@ asmlinkage __visible void __init xen_start_kernel(void)
#endif
}
+#ifdef CONFIG_XEN_PVH
+
+static void xen_pvh_arch_setup(void)
+{
+#ifdef CONFIG_ACPI
+ /* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
+ if (nr_ioapics == 0)
+ acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
+#endif
+}
+
+static void __init init_pvh_bootparams(void)
+{
+ struct xen_memory_map memmap;
+ unsigned int i;
+ int rc;
+
+ memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
+ memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map);
+ set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map);
+ rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+ if (rc) {
+ xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
+ BUG();
+ }
+
+ if (memmap.nr_entries < E820MAX - 1) {
+ pvh_bootparams.e820_map[memmap.nr_entries].addr =
+ ISA_START_ADDRESS;
+ pvh_bootparams.e820_map[memmap.nr_entries].size =
+ ISA_END_ADDRESS - ISA_START_ADDRESS;
+ pvh_bootparams.e820_map[memmap.nr_entries].type =
+ E820_RESERVED;
+ memmap.nr_entries++;
+ } else
+ xen_raw_printk("Warning: Can fit ISA range into e820\n");
+
+ sanitize_e820_map(pvh_bootparams.e820_map,
+ ARRAY_SIZE(pvh_bootparams.e820_map),
+ &memmap.nr_entries);
+
+ pvh_bootparams.e820_entries = memmap.nr_entries;
+ for (i = 0; i < pvh_bootparams.e820_entries; i++)
+ e820_add_region(pvh_bootparams.e820_map[i].addr,
+ pvh_bootparams.e820_map[i].size,
+ pvh_bootparams.e820_map[i].type);
+
+ pvh_bootparams.hdr.cmd_line_ptr =
+ pvh_start_info.cmdline_paddr;
+
+ /* The first module is always ramdisk. */
+ if (pvh_start_info.nr_modules) {
+ struct hvm_modlist_entry *modaddr =
+ __va(pvh_start_info.modlist_paddr);
+ pvh_bootparams.hdr.ramdisk_image = modaddr->paddr;
+ pvh_bootparams.hdr.ramdisk_size = modaddr->size;
+ }
+
+ /*
+ * See Documentation/x86/boot.txt.
+ *
+ * Version 2.12 supports Xen entry point but we will use default x86/PC
+ * environment (i.e. hardware_subarch 0).
+ */
+ pvh_bootparams.hdr.version = 0x212;
+ pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
+}
+
+/*
+ * This routine (and those that it might call) should not use
+ * anything that lives in .bss since that segment will be cleared later.
+ */
+void __init xen_prepare_pvh(void)
+{
+ u32 msr;
+ u64 pfn;
+
+ if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) {
+ xen_raw_printk("Error: Unexpected magic value (0x%08x)\n",
+ pvh_start_info.magic);
+ BUG();
+ }
+
+ xen_pvh = 1;
+
+ msr = cpuid_ebx(xen_cpuid_base() + 2);
+ pfn = __pa(hypercall_page);
+ wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+ init_pvh_bootparams();
+
+ x86_init.oem.arch_setup = xen_pvh_arch_setup;
+}
+#endif
+
void __ref xen_hvm_init_shared_info(void)
{
int cpu;
@@ -1797,20 +1806,29 @@ void __ref xen_hvm_init_shared_info(void)
static void __init init_hvm_pv_info(void)
{
int major, minor;
- uint32_t eax, ebx, ecx, edx, pages, msr, base;
- u64 pfn;
+ uint32_t eax, ebx, ecx, edx, base;
base = xen_cpuid_base();
- cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+ eax = cpuid_eax(base + 1);
major = eax >> 16;
minor = eax & 0xffff;
printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
- cpuid(base + 2, &pages, &msr, &ecx, &edx);
+ xen_domain_type = XEN_HVM_DOMAIN;
- pfn = __pa(hypercall_page);
- wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+ /* PVH set up hypercall page in xen_prepare_pvh(). */
+ if (xen_pvh_domain())
+ pv_info.name = "Xen PVH";
+ else {
+ u64 pfn;
+ uint32_t msr;
+
+ pv_info.name = "Xen HVM";
+ msr = cpuid_ebx(base + 2);
+ pfn = __pa(hypercall_page);
+ wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+ }
xen_setup_features();
@@ -1819,10 +1837,6 @@ static void __init init_hvm_pv_info(void)
this_cpu_write(xen_vcpu_id, ebx);
else
this_cpu_write(xen_vcpu_id, smp_processor_id());
-
- pv_info.name = "Xen HVM";
-
- xen_domain_type = XEN_HVM_DOMAIN;
}
#endif
@@ -1910,6 +1924,9 @@ static void __init xen_hvm_guest_init(void)
x86_init.irqs.intr_init = xen_init_IRQ;
xen_hvm_init_time_ops();
xen_hvm_init_mmu_ops();
+
+ if (xen_pvh_domain())
+ machine_ops.emergency_restart = xen_emergency_restart;
#ifdef CONFIG_KEXEC_CORE
machine_ops.shutdown = xen_hvm_shutdown;
machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 7d5afdb417cc..f6740b5b1738 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1792,10 +1792,6 @@ static void __init set_page_prot_flags(void *addr, pgprot_t prot,
unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
pte_t pte = pfn_pte(pfn, prot);
- /* For PVH no need to set R/O or R/W to pin them or unpin them. */
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
BUG();
}
@@ -1902,8 +1898,7 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
* level2_ident_pgt, and level2_kernel_pgt. This means that only the
* kernel has a physical mapping to start with - but that's enough to
* get __va working. We need to fill in the rest of the physical
- * mapping once some sort of allocator has been set up. NOTE: for
- * PVH, the page tables are native.
+ * mapping once some sort of allocator has been set up.
*/
void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
@@ -2812,16 +2807,6 @@ static int do_remap_gfn(struct vm_area_struct *vma,
BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
- if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_XEN_PVH
- /* We need to update the local page tables and the xen HAP */
- return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
- prot, domid, pages);
-#else
- return -EINVAL;
-#endif
- }
-
rmd.mfn = gfn;
rmd.prot = prot;
/* We use the err_ptr to indicate if there we are doing a contiguous
@@ -2915,10 +2900,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
return 0;
-#ifdef CONFIG_XEN_PVH
- return xen_xlate_unmap_gfn_range(vma, numpgs, pages);
-#else
return -EINVAL;
-#endif
}
EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 90d1b83cf35f..33a783c77d96 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -73,8 +73,8 @@ bool xen_has_pv_devices(void)
if (!xen_domain())
return false;
- /* PV domains always have them. */
- if (xen_pv_domain())
+ /* PV and PVH domains always have them. */
+ if (xen_pv_domain() || xen_pvh_domain())
return true;
/* And user has xen_platform_pci=0 set in guest config as
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f3f7b41116f7..a8c306cf8868 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -915,39 +915,6 @@ char * __init xen_memory_setup(void)
}
/*
- * Machine specific memory setup for auto-translated guests.
- */
-char * __init xen_auto_xlated_memory_setup(void)
-{
- struct xen_memory_map memmap;
- int i;
- int rc;
-
- memmap.nr_entries = ARRAY_SIZE(xen_e820_map);
- set_xen_guest_handle(memmap.buffer, xen_e820_map);
-
- rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
- if (rc < 0)
- panic("No memory map (%d)\n", rc);
-
- xen_e820_map_entries = memmap.nr_entries;
-
- sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
- &xen_e820_map_entries);
-
- for (i = 0; i < xen_e820_map_entries; i++)
- e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size,
- xen_e820_map[i].type);
-
- /* Remove p2m info, it is not needed. */
- xen_start_info->mfn_list = 0;
- xen_start_info->first_p2m_pfn = 0;
- xen_start_info->nr_p2m_frames = 0;
-
- return "Xen";
-}
-
-/*
* Set the bit indicating "nosegneg" library variants should be used.
* We only need to bother in pure 32-bit mode; compat 32-bit processes
* can have un-truncated segments, so wrapping around is allowed.
@@ -1032,8 +999,8 @@ void __init xen_pvmmu_arch_setup(void)
void __init xen_arch_setup(void)
{
xen_panic_handler_init();
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- xen_pvmmu_arch_setup();
+
+ xen_pvmmu_arch_setup();
#ifdef CONFIG_ACPI
if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 311acad7dad2..0dee6f59ea82 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -99,18 +99,8 @@ static void cpu_bringup(void)
local_irq_enable();
}
-/*
- * Note: cpu parameter is only relevant for PVH. The reason for passing it
- * is we can't do smp_processor_id until the percpu segments are loaded, for
- * which we need the cpu number! So we pass it in rdi as first parameter.
- */
-asmlinkage __visible void cpu_bringup_and_idle(int cpu)
+asmlinkage __visible void cpu_bringup_and_idle(void)
{
-#ifdef CONFIG_XEN_PVH
- if (xen_feature(XENFEAT_auto_translated_physmap) &&
- xen_feature(XENFEAT_supervisor_mode_kernel))
- xen_pvh_secondary_vcpu_init(cpu);
-#endif
cpu_bringup();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
@@ -404,61 +394,47 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
gdt = get_cpu_gdt_table(cpu);
#ifdef CONFIG_X86_32
- /* Note: PVH is not yet supported on x86_32. */
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
- ctxt->flags = VGCF_IN_KERNEL;
- ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
- ctxt->user_regs.ds = __USER_DS;
- ctxt->user_regs.es = __USER_DS;
- ctxt->user_regs.ss = __KERNEL_DS;
+ ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
+ ctxt->flags = VGCF_IN_KERNEL;
+ ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
+ ctxt->user_regs.ds = __USER_DS;
+ ctxt->user_regs.es = __USER_DS;
+ ctxt->user_regs.ss = __KERNEL_DS;
- xen_copy_trap_info(ctxt->trap_ctxt);
+ xen_copy_trap_info(ctxt->trap_ctxt);
- ctxt->ldt_ents = 0;
+ ctxt->ldt_ents = 0;
- BUG_ON((unsigned long)gdt & ~PAGE_MASK);
+ BUG_ON((unsigned long)gdt & ~PAGE_MASK);
- gdt_mfn = arbitrary_virt_to_mfn(gdt);
- make_lowmem_page_readonly(gdt);
- make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
+ gdt_mfn = arbitrary_virt_to_mfn(gdt);
+ make_lowmem_page_readonly(gdt);
+ make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
- ctxt->gdt_frames[0] = gdt_mfn;
- ctxt->gdt_ents = GDT_ENTRIES;
+ ctxt->gdt_frames[0] = gdt_mfn;
+ ctxt->gdt_ents = GDT_ENTRIES;
- ctxt->kernel_ss = __KERNEL_DS;
- ctxt->kernel_sp = idle->thread.sp0;
+ ctxt->kernel_ss = __KERNEL_DS;
+ ctxt->kernel_sp = idle->thread.sp0;
#ifdef CONFIG_X86_32
- ctxt->event_callback_cs = __KERNEL_CS;
- ctxt->failsafe_callback_cs = __KERNEL_CS;
+ ctxt->event_callback_cs = __KERNEL_CS;
+ ctxt->failsafe_callback_cs = __KERNEL_CS;
#else
- ctxt->gs_base_kernel = per_cpu_offset(cpu);
-#endif
- ctxt->event_callback_eip =
- (unsigned long)xen_hypervisor_callback;
- ctxt->failsafe_callback_eip =
- (unsigned long)xen_failsafe_callback;
- ctxt->user_regs.cs = __KERNEL_CS;
- per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
- }
-#ifdef CONFIG_XEN_PVH
- else {
- /*
- * The vcpu comes on kernel page tables which have the NX pte
- * bit set. This means before DS/SS is touched, NX in
- * EFER must be set. Hence the following assembly glue code.
- */
- ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init;
- ctxt->user_regs.rdi = cpu;
- ctxt->user_regs.rsi = true; /* entry == true */
- }
+ ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
+ ctxt->event_callback_eip =
+ (unsigned long)xen_hypervisor_callback;
+ ctxt->failsafe_callback_eip =
+ (unsigned long)xen_failsafe_callback;
+ ctxt->user_regs.cs = __KERNEL_CS;
+ per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
+
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c5c16dc4f694..9beef333584a 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -21,12 +21,4 @@ static inline int xen_smp_intr_init(unsigned int cpu)
static inline void xen_smp_intr_free(unsigned int cpu) {}
#endif /* CONFIG_SMP */
-#ifdef CONFIG_XEN_PVH
-extern void xen_pvh_early_cpu_init(int cpu, bool entry);
-#else
-static inline void xen_pvh_early_cpu_init(int cpu, bool entry)
-{
-}
-#endif
-
#endif
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index e8a9ea7d7a21..25a7c4302ce7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -141,25 +141,6 @@ void __init xen_init_spinlocks(void)
pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
-/*
- * While the jump_label init code needs to happend _after_ the jump labels are
- * enabled and before SMP is started. Hence we use pre-SMP initcall level
- * init. We cannot do it in xen_init_spinlocks as that is done before
- * jump labels are activated.
- */
-static __init int xen_init_spinlocks_jump(void)
-{
- if (!xen_pvspin)
- return 0;
-
- if (!xen_domain())
- return 0;
-
- static_key_slow_inc(&paravirt_ticketlocks_enabled);
- return 0;
-}
-early_initcall(xen_init_spinlocks_jump);
-
static __init int xen_parse_nopvspin(char *arg)
{
xen_pvspin = false;
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 7f8d8abf4c1a..37794e42b67d 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -16,25 +16,6 @@
#include <xen/interface/xen-mca.h>
#include <asm/xen/interface.h>
-#ifdef CONFIG_XEN_PVH
-#define PVH_FEATURES_STR "|writable_descriptor_tables|auto_translated_physmap|supervisor_mode_kernel"
-/* Note the lack of 'hvm_callback_vector'. Older hypervisor will
- * balk at this being part of XEN_ELFNOTE_FEATURES, so we put it in
- * XEN_ELFNOTE_SUPPORTED_FEATURES which older hypervisors will ignore.
- */
-#define PVH_FEATURES ((1 << XENFEAT_writable_page_tables) | \
- (1 << XENFEAT_auto_translated_physmap) | \
- (1 << XENFEAT_supervisor_mode_kernel) | \
- (1 << XENFEAT_hvm_callback_vector))
-/* The XENFEAT_writable_page_tables is not stricly necessary as we set that
- * up regardless whether this CONFIG option is enabled or not, but it
- * clarifies what the right flags need to be.
- */
-#else
-#define PVH_FEATURES_STR ""
-#define PVH_FEATURES (0)
-#endif
-
__INIT
ENTRY(startup_xen)
cld
@@ -54,41 +35,6 @@ ENTRY(startup_xen)
__FINIT
-#ifdef CONFIG_XEN_PVH
-/*
- * xen_pvh_early_cpu_init() - early PVH VCPU initialization
- * @cpu: this cpu number (%rdi)
- * @entry: true if this is a secondary vcpu coming up on this entry
- * point, false if this is the boot CPU being initialized for
- * the first time (%rsi)
- *
- * Note: This is called as a function on the boot CPU, and is the entry point
- * on the secondary CPU.
- */
-ENTRY(xen_pvh_early_cpu_init)
- mov %rsi, %r11
-
- /* Gather features to see if NX implemented. */
- mov $0x80000001, %eax
- cpuid
- mov %edx, %esi
-
- mov $MSR_EFER, %ecx
- rdmsr
- bts $_EFER_SCE, %eax
-
- bt $20, %esi
- jnc 1f /* No NX, skip setting it */
- bts $_EFER_NX, %eax
-1: wrmsr
-#ifdef CONFIG_SMP
- cmp $0, %r11b
- jne cpu_bringup_and_idle
-#endif
- ret
-
-#endif /* CONFIG_XEN_PVH */
-
.pushsection .text
.balign PAGE_SIZE
ENTRY(hypercall_page)
@@ -114,10 +60,10 @@ ENTRY(hypercall_page)
#endif
ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen)
ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page)
- ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .ascii "!writable_page_tables|pae_pgdir_above_4gb"; .asciz PVH_FEATURES_STR)
- ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long (PVH_FEATURES) |
- (1 << XENFEAT_writable_page_tables) |
- (1 << XENFEAT_dom0))
+ ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,
+ .ascii "!writable_page_tables|pae_pgdir_above_4gb")
+ ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES,
+ .long (1 << XENFEAT_writable_page_tables) | (1 << XENFEAT_dom0))
ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "yes")
ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic")
ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ac0a2b0f9e62..f6a41c41ebc7 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -146,5 +146,4 @@ __visible void xen_adjust_exception_frame(void);
extern int xen_panic_handler_init(void);
-void xen_pvh_secondary_vcpu_init(int cpu);
#endif /* XEN_OPS_H */
diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S
new file mode 100644
index 000000000000..5e246716d58f
--- /dev/null
+++ b/arch/x86/xen/xen-pvh.S
@@ -0,0 +1,161 @@
+/*
+ * Copyright C 2016, Oracle and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+ .code32
+ .text
+#define _pa(x) ((x) - __START_KERNEL_map)
+
+#include <linux/elfnote.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/asm.h>
+#include <asm/boot.h>
+#include <asm/processor-flags.h>
+#include <asm/msr.h>
+#include <xen/interface/elfnote.h>
+
+ __HEAD
+
+/*
+ * Entry point for PVH guests.
+ *
+ * Xen ABI specifies the following register state when we come here:
+ *
+ * - `ebx`: contains the physical memory address where the loader has placed
+ * the boot start info structure.
+ * - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared.
+ * - `cr4`: all bits are cleared.
+ * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’
+ * and a limit of ‘0xFFFFFFFF’. The selector value is unspecified.
+ * - `ds`, `es`: must be a 32-bit read/write data segment with a base of
+ * ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all
+ * unspecified.
+ * - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit
+ * of '0x67'.
+ * - `eflags`: bit 17 (VM) must be cleared. Bit 9 (IF) must be cleared.
+ * Bit 8 (TF) must be cleared. Other bits are all unspecified.
+ *
+ * All other processor registers and flag bits are unspecified. The OS is in
+ * charge of setting up it's own stack, GDT and IDT.
+ */
+
+ENTRY(pvh_start_xen)
+ cld
+
+ lgdt (_pa(gdt))
+
+ mov $(__BOOT_DS),%eax
+ mov %eax,%ds
+ mov %eax,%es
+ mov %eax,%ss
+
+ /* Stash hvm_start_info. */
+ mov $_pa(pvh_start_info), %edi
+ mov %ebx, %esi
+ mov _pa(pvh_start_info_sz), %ecx
+ shr $2,%ecx
+ rep
+ movsl
+
+ mov $_pa(early_stack_end), %esp
+
+ /* Enable PAE mode. */
+ mov %cr4, %eax
+ orl $X86_CR4_PAE, %eax
+ mov %eax, %cr4
+
+#ifdef CONFIG_X86_64
+ /* Enable Long mode. */
+ mov $MSR_EFER, %ecx
+ rdmsr
+ btsl $_EFER_LME, %eax
+ wrmsr
+
+ /* Enable pre-constructed page tables. */
+ mov $_pa(init_level4_pgt), %eax
+ mov %eax, %cr3
+ mov $(X86_CR0_PG | X86_CR0_PE), %eax
+ mov %eax, %cr0
+
+ /* Jump to 64-bit mode. */
+ ljmp $__KERNEL_CS, $_pa(1f)
+
+ /* 64-bit entry point. */
+ .code64
+1:
+ call xen_prepare_pvh
+
+ /* startup_64 expects boot_params in %rsi. */
+ mov $_pa(pvh_bootparams), %rsi
+ mov $_pa(startup_64), %rax
+ jmp *%rax
+
+#else /* CONFIG_X86_64 */
+
+ call mk_early_pgtbl_32
+
+ mov $_pa(initial_page_table), %eax
+ mov %eax, %cr3
+
+ mov %cr0, %eax
+ or $(X86_CR0_PG | X86_CR0_PE), %eax
+ mov %eax, %cr0
+
+ ljmp $__BOOT_CS, $1f
+1:
+ call xen_prepare_pvh
+ mov $_pa(pvh_bootparams), %esi
+
+ /* startup_32 doesn't expect paging and PAE to be on. */
+ ljmp $__BOOT_CS, $_pa(2f)
+2:
+ mov %cr0, %eax
+ and $~X86_CR0_PG, %eax
+ mov %eax, %cr0
+ mov %cr4, %eax
+ and $~X86_CR4_PAE, %eax
+ mov %eax, %cr4
+
+ ljmp $__BOOT_CS, $_pa(startup_32)
+#endif
+END(pvh_start_xen)
+
+ .section ".init.data","aw"
+ .balign 8
+gdt:
+ .word gdt_end - gdt_start
+ .long _pa(gdt_start)
+ .word 0
+gdt_start:
+ .quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x0000000000000000 /* reserved */
+#ifdef CONFIG_X86_64
+ .quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* __KERNEL_CS */
+#else
+ .quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* __KERNEL_CS */
+#endif
+ .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* __KERNEL_DS */
+gdt_end:
+
+ .balign 4
+early_stack:
+ .fill 256, 1, 0
+early_stack_end:
+
+ ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
+ _ASM_PTR (pvh_start_xen - __START_KERNEL_map))