summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/boot.c13
-rw-r--r--arch/x86/kernel/apic/apic_common.c2
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/apic/x2apic.h2
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/cpu/common.c32
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c2
-rw-r--r--arch/x86/kernel/crash.c334
-rw-r--r--arch/x86/kernel/espfix_64.c4
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/head_64.S11
-rw-r--r--arch/x86/kernel/kexec-bzimage64.c10
-rw-r--r--arch/x86/kernel/ldt.c6
-rw-r--r--arch/x86/kernel/machine_kexec_64.c111
-rw-r--r--arch/x86/kernel/signal_compat.c2
16 files changed, 151 insertions, 386 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7a37d9357bc4..dde444f932c1 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
{
struct acpi_madt_local_x2apic *processor = NULL;
#ifdef CONFIG_X86_X2APIC
- int apic_id;
+ u32 apic_id;
u8 enabled;
#endif
@@ -222,10 +222,13 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
* to not preallocating memory for all NR_CPUS
* when we use CPU hotplug.
*/
- if (!apic->apic_id_valid(apic_id) && enabled)
- printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
- else
- acpi_register_lapic(apic_id, processor->uid, enabled);
+ if (!apic->apic_id_valid(apic_id)) {
+ if (enabled)
+ pr_warn(PREFIX "x2apic entry ignored\n");
+ return 0;
+ }
+
+ acpi_register_lapic(apic_id, processor->uid, enabled);
#else
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
#endif
diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c
index a360801779ae..02b4839478b1 100644
--- a/arch/x86/kernel/apic/apic_common.c
+++ b/arch/x86/kernel/apic/apic_common.c
@@ -40,7 +40,7 @@ int default_check_phys_apicid_present(int phys_apicid)
return physid_isset(phys_apicid, phys_cpu_present_map);
}
-int default_apic_id_valid(int apicid)
+int default_apic_id_valid(u32 apicid)
{
return (apicid < 255);
}
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 134e04506ab4..78778b54f904 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigned int id)
return id << 24;
}
-static int numachip_apic_id_valid(int apicid)
+static int numachip_apic_id_valid(u32 apicid)
{
/* Trust what bootloader passes in MADT */
return 1;
diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h
index b107de381cb5..a49b3604027f 100644
--- a/arch/x86/kernel/apic/x2apic.h
+++ b/arch/x86/kernel/apic/x2apic.h
@@ -1,6 +1,6 @@
/* Common bits for X2APIC cluster/physical modes. */
-int x2apic_apic_id_valid(int apicid);
+int x2apic_apic_id_valid(u32 apicid);
int x2apic_apic_id_registered(void);
void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
unsigned int x2apic_get_apic_id(unsigned long id);
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index e2829bf40e4a..b5cf9e7b3830 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -101,7 +101,7 @@ static int x2apic_phys_probe(void)
}
/* Common x2apic functions, also used by x2apic_cluster */
-int x2apic_apic_id_valid(int apicid)
+int x2apic_apic_id_valid(u32 apicid)
{
return 1;
}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f11910b44638..efaf2d4f9c3c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -557,7 +557,7 @@ static void uv_send_IPI_all(int vector)
uv_send_IPI_mask(cpu_online_mask, vector);
}
-static int uv_apic_id_valid(int apicid)
+static int uv_apic_id_valid(u32 apicid)
{
return 1;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4702fbd98f92..8a5b185735e1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -848,18 +848,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_power = edx;
}
- if (c->extended_cpuid_level >= 0x80000008) {
- cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
-
- c->x86_virt_bits = (eax >> 8) & 0xff;
- c->x86_phys_bits = eax & 0xff;
- c->x86_capability[CPUID_8000_0008_EBX] = ebx;
- }
-#ifdef CONFIG_X86_32
- else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
- c->x86_phys_bits = 36;
-#endif
-
if (c->extended_cpuid_level >= 0x8000000a)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
@@ -874,6 +862,23 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
apply_forced_caps(c);
}
+static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
+{
+ u32 eax, ebx, ecx, edx;
+
+ if (c->extended_cpuid_level >= 0x80000008) {
+ cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+
+ c->x86_virt_bits = (eax >> 8) & 0xff;
+ c->x86_phys_bits = eax & 0xff;
+ c->x86_capability[CPUID_8000_0008_EBX] = ebx;
+ }
+#ifdef CONFIG_X86_32
+ else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
+ c->x86_phys_bits = 36;
+#endif
+}
+
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
@@ -965,6 +970,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
+ get_cpu_address_sizes(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
if (this_cpu->c_early_init)
@@ -1097,6 +1103,8 @@ static void generic_identify(struct cpuinfo_x86 *c)
get_cpu_cap(c);
+ get_cpu_address_sizes(c);
+
if (c->cpuid_level >= 0x00000001) {
c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 904b0a3c4e53..2c0bd38a44ab 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -19,7 +19,7 @@ struct cpuid_dep {
* called from cpu hotplug. It shouldn't do anything in this case,
* but it's difficult to tell that to the init reference checker.
*/
-const static struct cpuid_dep cpuid_deps[] = {
+static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
{ X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
{ X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 1f6680427ff0..f631a3f15587 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -38,37 +38,6 @@
#include <asm/virtext.h>
#include <asm/intel_pt.h>
-/* Alignment required for elf header segment */
-#define ELF_CORE_HEADER_ALIGN 4096
-
-/* This primarily represents number of split ranges due to exclusion */
-#define CRASH_MAX_RANGES 16
-
-struct crash_mem_range {
- u64 start, end;
-};
-
-struct crash_mem {
- unsigned int nr_ranges;
- struct crash_mem_range ranges[CRASH_MAX_RANGES];
-};
-
-/* Misc data about ram ranges needed to prepare elf headers */
-struct crash_elf_data {
- struct kimage *image;
- /*
- * Total number of ram ranges we have after various adjustments for
- * crash reserved region, etc.
- */
- unsigned int max_nr_ranges;
-
- /* Pointer to elf header */
- void *ehdr;
- /* Pointer to next phdr */
- void *bufp;
- struct crash_mem mem;
-};
-
/* Used while preparing memory map entries for second kernel */
struct crash_memmap_data {
struct boot_params *params;
@@ -218,124 +187,49 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
return 0;
}
-
/* Gather all the required information to prepare elf headers for ram regions */
-static void fill_up_crash_elf_data(struct crash_elf_data *ced,
- struct kimage *image)
+static struct crash_mem *fill_up_crash_elf_data(void)
{
unsigned int nr_ranges = 0;
-
- ced->image = image;
+ struct crash_mem *cmem;
walk_system_ram_res(0, -1, &nr_ranges,
get_nr_ram_ranges_callback);
+ if (!nr_ranges)
+ return NULL;
- ced->max_nr_ranges = nr_ranges;
-
- /* Exclusion of crash region could split memory ranges */
- ced->max_nr_ranges++;
-
- /* If crashk_low_res is not 0, another range split possible */
- if (crashk_low_res.end)
- ced->max_nr_ranges++;
-}
-
-static int exclude_mem_range(struct crash_mem *mem,
- unsigned long long mstart, unsigned long long mend)
-{
- int i, j;
- unsigned long long start, end;
- struct crash_mem_range temp_range = {0, 0};
-
- for (i = 0; i < mem->nr_ranges; i++) {
- start = mem->ranges[i].start;
- end = mem->ranges[i].end;
-
- if (mstart > end || mend < start)
- continue;
-
- /* Truncate any area outside of range */
- if (mstart < start)
- mstart = start;
- if (mend > end)
- mend = end;
-
- /* Found completely overlapping range */
- if (mstart == start && mend == end) {
- mem->ranges[i].start = 0;
- mem->ranges[i].end = 0;
- if (i < mem->nr_ranges - 1) {
- /* Shift rest of the ranges to left */
- for (j = i; j < mem->nr_ranges - 1; j++) {
- mem->ranges[j].start =
- mem->ranges[j+1].start;
- mem->ranges[j].end =
- mem->ranges[j+1].end;
- }
- }
- mem->nr_ranges--;
- return 0;
- }
-
- if (mstart > start && mend < end) {
- /* Split original range */
- mem->ranges[i].end = mstart - 1;
- temp_range.start = mend + 1;
- temp_range.end = end;
- } else if (mstart != start)
- mem->ranges[i].end = mstart - 1;
- else
- mem->ranges[i].start = mend + 1;
- break;
- }
+ /*
+ * Exclusion of crash region and/or crashk_low_res may cause
+ * another range split. So add extra two slots here.
+ */
+ nr_ranges += 2;
+ cmem = vzalloc(sizeof(struct crash_mem) +
+ sizeof(struct crash_mem_range) * nr_ranges);
+ if (!cmem)
+ return NULL;
- /* If a split happend, add the split to array */
- if (!temp_range.end)
- return 0;
+ cmem->max_nr_ranges = nr_ranges;
+ cmem->nr_ranges = 0;
- /* Split happened */
- if (i == CRASH_MAX_RANGES - 1) {
- pr_err("Too many crash ranges after split\n");
- return -ENOMEM;
- }
-
- /* Location where new range should go */
- j = i + 1;
- if (j < mem->nr_ranges) {
- /* Move over all ranges one slot towards the end */
- for (i = mem->nr_ranges - 1; i >= j; i--)
- mem->ranges[i + 1] = mem->ranges[i];
- }
-
- mem->ranges[j].start = temp_range.start;
- mem->ranges[j].end = temp_range.end;
- mem->nr_ranges++;
- return 0;
+ return cmem;
}
/*
* Look for any unwanted ranges between mstart, mend and remove them. This
- * might lead to split and split ranges are put in ced->mem.ranges[] array
+ * might lead to split and split ranges are put in cmem->ranges[] array
*/
-static int elf_header_exclude_ranges(struct crash_elf_data *ced,
- unsigned long long mstart, unsigned long long mend)
+static int elf_header_exclude_ranges(struct crash_mem *cmem)
{
- struct crash_mem *cmem = &ced->mem;
int ret = 0;
- memset(cmem->ranges, 0, sizeof(cmem->ranges));
-
- cmem->ranges[0].start = mstart;
- cmem->ranges[0].end = mend;
- cmem->nr_ranges = 1;
-
/* Exclude crashkernel region */
- ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
if (ret)
return ret;
if (crashk_low_res.end) {
- ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+ ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
+ crashk_low_res.end);
if (ret)
return ret;
}
@@ -345,144 +239,12 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
{
- struct crash_elf_data *ced = arg;
- Elf64_Ehdr *ehdr;
- Elf64_Phdr *phdr;
- unsigned long mstart, mend;
- struct kimage *image = ced->image;
- struct crash_mem *cmem;
- int ret, i;
-
- ehdr = ced->ehdr;
-
- /* Exclude unwanted mem ranges */
- ret = elf_header_exclude_ranges(ced, res->start, res->end);
- if (ret)
- return ret;
-
- /* Go through all the ranges in ced->mem.ranges[] and prepare phdr */
- cmem = &ced->mem;
-
- for (i = 0; i < cmem->nr_ranges; i++) {
- mstart = cmem->ranges[i].start;
- mend = cmem->ranges[i].end;
-
- phdr = ced->bufp;
- ced->bufp += sizeof(Elf64_Phdr);
-
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_offset = mstart;
-
- /*
- * If a range matches backup region, adjust offset to backup
- * segment.
- */
- if (mstart == image->arch.backup_src_start &&
- (mend - mstart + 1) == image->arch.backup_src_sz)
- phdr->p_offset = image->arch.backup_load_addr;
-
- phdr->p_paddr = mstart;
- phdr->p_vaddr = (unsigned long long) __va(mstart);
- phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
- phdr->p_align = 0;
- ehdr->e_phnum++;
- pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
- phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
- ehdr->e_phnum, phdr->p_offset);
- }
-
- return ret;
-}
-
-static int prepare_elf64_headers(struct crash_elf_data *ced,
- void **addr, unsigned long *sz)
-{
- Elf64_Ehdr *ehdr;
- Elf64_Phdr *phdr;
- unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
- unsigned char *buf, *bufp;
- unsigned int cpu;
- unsigned long long notes_addr;
- int ret;
+ struct crash_mem *cmem = arg;
- /* extra phdr for vmcoreinfo elf note */
- nr_phdr = nr_cpus + 1;
- nr_phdr += ced->max_nr_ranges;
-
- /*
- * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
- * area on x86_64 (ffffffff80000000 - ffffffffa0000000).
- * I think this is required by tools like gdb. So same physical
- * memory will be mapped in two elf headers. One will contain kernel
- * text virtual addresses and other will have __va(physical) addresses.
- */
+ cmem->ranges[cmem->nr_ranges].start = res->start;
+ cmem->ranges[cmem->nr_ranges].end = res->end;
+ cmem->nr_ranges++;
- nr_phdr++;
- elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
- elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
-
- buf = vzalloc(elf_sz);
- if (!buf)
- return -ENOMEM;
-
- bufp = buf;
- ehdr = (Elf64_Ehdr *)bufp;
- bufp += sizeof(Elf64_Ehdr);
- memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
- ehdr->e_ident[EI_CLASS] = ELFCLASS64;
- ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
- ehdr->e_ident[EI_VERSION] = EV_CURRENT;
- ehdr->e_ident[EI_OSABI] = ELF_OSABI;
- memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
- ehdr->e_type = ET_CORE;
- ehdr->e_machine = ELF_ARCH;
- ehdr->e_version = EV_CURRENT;
- ehdr->e_phoff = sizeof(Elf64_Ehdr);
- ehdr->e_ehsize = sizeof(Elf64_Ehdr);
- ehdr->e_phentsize = sizeof(Elf64_Phdr);
-
- /* Prepare one phdr of type PT_NOTE for each present cpu */
- for_each_present_cpu(cpu) {
- phdr = (Elf64_Phdr *)bufp;
- bufp += sizeof(Elf64_Phdr);
- phdr->p_type = PT_NOTE;
- notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
- phdr->p_offset = phdr->p_paddr = notes_addr;
- phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
- (ehdr->e_phnum)++;
- }
-
- /* Prepare one PT_NOTE header for vmcoreinfo */
- phdr = (Elf64_Phdr *)bufp;
- bufp += sizeof(Elf64_Phdr);
- phdr->p_type = PT_NOTE;
- phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
- phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
- (ehdr->e_phnum)++;
-
-#ifdef CONFIG_X86_64
- /* Prepare PT_LOAD type program header for kernel text region */
- phdr = (Elf64_Phdr *)bufp;
- bufp += sizeof(Elf64_Phdr);
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_vaddr = (Elf64_Addr)_text;
- phdr->p_filesz = phdr->p_memsz = _end - _text;
- phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
- (ehdr->e_phnum)++;
-#endif
-
- /* Prepare PT_LOAD headers for system ram chunks. */
- ced->ehdr = ehdr;
- ced->bufp = bufp;
- ret = walk_system_ram_res(0, -1, ced,
- prepare_elf64_ram_headers_callback);
- if (ret < 0)
- return ret;
-
- *addr = buf;
- *sz = elf_sz;
return 0;
}
@@ -490,18 +252,46 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
static int prepare_elf_headers(struct kimage *image, void **addr,
unsigned long *sz)
{
- struct crash_elf_data *ced;
- int ret;
+ struct crash_mem *cmem;
+ Elf64_Ehdr *ehdr;
+ Elf64_Phdr *phdr;
+ int ret, i;
- ced = kzalloc(sizeof(*ced), GFP_KERNEL);
- if (!ced)
+ cmem = fill_up_crash_elf_data();
+ if (!cmem)
return -ENOMEM;
- fill_up_crash_elf_data(ced, image);
+ ret = walk_system_ram_res(0, -1, cmem,
+ prepare_elf64_ram_headers_callback);
+ if (ret)
+ goto out;
+
+ /* Exclude unwanted mem ranges */
+ ret = elf_header_exclude_ranges(cmem);
+ if (ret)
+ goto out;
/* By default prepare 64bit headers */
- ret = prepare_elf64_headers(ced, addr, sz);
- kfree(ced);
+ ret = crash_prepare_elf64_headers(cmem,
+ IS_ENABLED(CONFIG_X86_64), addr, sz);
+ if (ret)
+ goto out;
+
+ /*
+ * If a range matches backup region, adjust offset to backup
+ * segment.
+ */
+ ehdr = (Elf64_Ehdr *)*addr;
+ phdr = (Elf64_Phdr *)(ehdr + 1);
+ for (i = 0; i < ehdr->e_phnum; phdr++, i++)
+ if (phdr->p_type == PT_LOAD &&
+ phdr->p_paddr == image->arch.backup_src_start &&
+ phdr->p_memsz == image->arch.backup_src_sz) {
+ phdr->p_offset = image->arch.backup_load_addr;
+ break;
+ }
+out:
+ vfree(cmem);
return ret;
}
@@ -547,14 +337,14 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
/* Exclude Backup region */
start = image->arch.backup_load_addr;
end = start + image->arch.backup_src_sz - 1;
- ret = exclude_mem_range(cmem, start, end);
+ ret = crash_exclude_mem_range(cmem, start, end);
if (ret)
return ret;
/* Exclude elf header region */
start = image->arch.elf_load_addr;
end = start + image->arch.elf_headers_sz - 1;
- return exclude_mem_range(cmem, start, end);
+ return crash_exclude_mem_range(cmem, start, end);
}
/* Prepare memory map for crash dump kernel */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index e5ec3cafa72e..aebd0d5bc086 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -195,6 +195,10 @@ void init_espfix_ap(int cpu)
pte_p = pte_offset_kernel(&pmd, addr);
stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
+ /*
+ * __PAGE_KERNEL_* includes _PAGE_GLOBAL, which we want since
+ * this is mapped to userspace.
+ */
pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask));
for (n = 0; n < ESPFIX_PTE_CLONES; n++)
set_pte(&pte_p[n*PTE_STRIDE], pte);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 0c855deee165..0c408f8c4ed4 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -195,6 +195,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
pud[i + 1] = (pudval_t)pmd + pgtable_flags;
pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+ /* Filter out unsupported __PAGE_KERNEL_* bits: */
+ pmd_entry &= __supported_pte_mask;
pmd_entry += sme_get_me_mask();
pmd_entry += physaddr;
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 48385c1074a5..8344dd2f310a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -399,8 +399,13 @@ NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.fill 511, 8, 0
NEXT_PAGE(level2_ident_pgt)
- /* Since I easily can, map the first 1G.
+ /*
+ * Since I easily can, map the first 1G.
* Don't set NX because code runs from these pages.
+ *
+ * Note: This sets _PAGE_GLOBAL despite whether
+ * the CPU supports it or it is enabled. But,
+ * the CPU should ignore the bit.
*/
PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
#else
@@ -431,6 +436,10 @@ NEXT_PAGE(level2_kernel_pgt)
* (NOTE: at +512MB starts the module area, see MODULES_VADDR.
* If you want to increase this then increase MODULES_VADDR
* too.)
+ *
+ * This table is eventually used by the kernel during normal
+ * runtime. Care must be taken to clear out undesired bits
+ * later, like _PAGE_RW or _PAGE_GLOBAL in some cases.
*/
PMDS(0, __PAGE_KERNEL_LARGE_EXEC,
KERNEL_IMAGE_SIZE/PMD_SIZE)
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index fb095ba0c02f..3182908b7e6c 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -334,7 +334,6 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
unsigned long setup_header_size, params_cmdline_sz;
struct boot_params *params;
unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr;
- unsigned long purgatory_load_addr;
struct bzimage64_data *ldata;
struct kexec_entry64_regs regs64;
void *stack;
@@ -342,6 +341,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset;
struct kexec_buf kbuf = { .image = image, .buf_max = ULONG_MAX,
.top_down = true };
+ struct kexec_buf pbuf = { .image = image, .buf_min = MIN_PURGATORY_ADDR,
+ .buf_max = ULONG_MAX, .top_down = true };
header = (struct setup_header *)(kernel + setup_hdr_offset);
setup_sects = header->setup_sects;
@@ -379,14 +380,13 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
* Load purgatory. For 64bit entry point, purgatory code can be
* anywhere.
*/
- ret = kexec_load_purgatory(image, MIN_PURGATORY_ADDR, ULONG_MAX, 1,
- &purgatory_load_addr);
+ ret = kexec_load_purgatory(image, &pbuf);
if (ret) {
pr_err("Loading purgatory failed\n");
return ERR_PTR(ret);
}
- pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr);
+ pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
/*
@@ -538,7 +538,7 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
}
#endif
-struct kexec_file_ops kexec_bzImage64_ops = {
+const struct kexec_file_ops kexec_bzImage64_ops = {
.probe = bzImage64_probe,
.load = bzImage64_load,
.cleanup = bzImage64_cleanup,
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 26d713ecad34..c9b14020f4dd 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -145,6 +145,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
unsigned long offset = i << PAGE_SHIFT;
const void *src = (char *)ldt->entries + offset;
unsigned long pfn;
+ pgprot_t pte_prot;
pte_t pte, *ptep;
va = (unsigned long)ldt_slot_va(slot) + offset;
@@ -163,7 +164,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
* target via some kernel interface which misses a
* permission check.
*/
- pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+ pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL);
+ /* Filter out unsuppored __PAGE_KERNEL* bits: */
+ pgprot_val(pte_prot) &= __supported_pte_mask;
+ pte = pfn_pte(pfn, pte_prot);
set_pte_at(mm, va, ptep, pte);
pte_unmap_unlock(ptep, ptl);
}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 93bd4fb603d1..a5e55d832d0a 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -30,8 +30,9 @@
#include <asm/set_memory.h>
#ifdef CONFIG_KEXEC_FILE
-static struct kexec_file_ops *kexec_file_loaders[] = {
+const struct kexec_file_ops * const kexec_file_loaders[] = {
&kexec_bzImage64_ops,
+ NULL
};
#endif
@@ -364,27 +365,6 @@ void arch_crash_save_vmcoreinfo(void)
/* arch-dependent functionality related to kexec file-based syscall */
#ifdef CONFIG_KEXEC_FILE
-int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
- unsigned long buf_len)
-{
- int i, ret = -ENOEXEC;
- struct kexec_file_ops *fops;
-
- for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) {
- fops = kexec_file_loaders[i];
- if (!fops || !fops->probe)
- continue;
-
- ret = fops->probe(buf, buf_len);
- if (!ret) {
- image->fops = fops;
- return ret;
- }
- }
-
- return ret;
-}
-
void *arch_kexec_kernel_image_load(struct kimage *image)
{
vfree(image->arch.elf_headers);
@@ -399,88 +379,53 @@ void *arch_kexec_kernel_image_load(struct kimage *image)
image->cmdline_buf_len);
}
-int arch_kimage_file_post_load_cleanup(struct kimage *image)
-{
- if (!image->fops || !image->fops->cleanup)
- return 0;
-
- return image->fops->cleanup(image->image_loader_data);
-}
-
-#ifdef CONFIG_KEXEC_VERIFY_SIG
-int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel,
- unsigned long kernel_len)
-{
- if (!image->fops || !image->fops->verify_sig) {
- pr_debug("kernel loader does not support signature verification.");
- return -EKEYREJECTED;
- }
-
- return image->fops->verify_sig(kernel, kernel_len);
-}
-#endif
-
/*
* Apply purgatory relocations.
*
- * ehdr: Pointer to elf headers
- * sechdrs: Pointer to section headers.
- * relsec: section index of SHT_RELA section.
+ * @pi: Purgatory to be relocated.
+ * @section: Section relocations applying to.
+ * @relsec: Section containing RELAs.
+ * @symtabsec: Corresponding symtab.
*
* TODO: Some of the code belongs to generic code. Move that in kexec.c.
*/
-int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
- Elf64_Shdr *sechdrs, unsigned int relsec)
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+ Elf_Shdr *section, const Elf_Shdr *relsec,
+ const Elf_Shdr *symtabsec)
{
unsigned int i;
Elf64_Rela *rel;
Elf64_Sym *sym;
void *location;
- Elf64_Shdr *section, *symtabsec;
unsigned long address, sec_base, value;
const char *strtab, *name, *shstrtab;
+ const Elf_Shdr *sechdrs;
- /*
- * ->sh_offset has been modified to keep the pointer to section
- * contents in memory
- */
- rel = (void *)sechdrs[relsec].sh_offset;
-
- /* Section to which relocations apply */
- section = &sechdrs[sechdrs[relsec].sh_info];
-
- pr_debug("Applying relocate section %u to %u\n", relsec,
- sechdrs[relsec].sh_info);
-
- /* Associated symbol table */
- symtabsec = &sechdrs[sechdrs[relsec].sh_link];
-
- /* String table */
- if (symtabsec->sh_link >= ehdr->e_shnum) {
- /* Invalid strtab section number */
- pr_err("Invalid string table section index %d\n",
- symtabsec->sh_link);
- return -ENOEXEC;
- }
+ /* String & section header string table */
+ sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
+ strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset;
+ shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;
- strtab = (char *)sechdrs[symtabsec->sh_link].sh_offset;
+ rel = (void *)pi->ehdr + relsec->sh_offset;
- /* section header string table */
- shstrtab = (char *)sechdrs[ehdr->e_shstrndx].sh_offset;
+ pr_debug("Applying relocate section %s to %u\n",
+ shstrtab + relsec->sh_name, relsec->sh_info);
- for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+ for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) {
/*
* rel[i].r_offset contains byte offset from beginning
* of section to the storage unit affected.
*
- * This is location to update (->sh_offset). This is temporary
- * buffer where section is currently loaded. This will finally
- * be loaded to a different address later, pointed to by
+ * This is location to update. This is temporary buffer
+ * where section is currently loaded. This will finally be
+ * loaded to a different address later, pointed to by
* ->sh_addr. kexec takes care of moving it
* (kexec_load_segment()).
*/
- location = (void *)(section->sh_offset + rel[i].r_offset);
+ location = pi->purgatory_buf;
+ location += section->sh_offset;
+ location += rel[i].r_offset;
/* Final address of the location */
address = section->sh_addr + rel[i].r_offset;
@@ -491,8 +436,8 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
* to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get
* these respectively.
*/
- sym = (Elf64_Sym *)symtabsec->sh_offset +
- ELF64_R_SYM(rel[i].r_info);
+ sym = (void *)pi->ehdr + symtabsec->sh_offset;
+ sym += ELF64_R_SYM(rel[i].r_info);
if (sym->st_name)
name = strtab + sym->st_name;
@@ -515,12 +460,12 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
if (sym->st_shndx == SHN_ABS)
sec_base = 0;
- else if (sym->st_shndx >= ehdr->e_shnum) {
+ else if (sym->st_shndx >= pi->ehdr->e_shnum) {
pr_err("Invalid section %d for symbol %s\n",
sym->st_shndx, name);
return -ENOEXEC;
} else
- sec_base = sechdrs[sym->st_shndx].sh_addr;
+ sec_base = pi->sechdrs[sym->st_shndx].sh_addr;
value = sym->st_value;
value += sec_base;
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index df92605d8724..14c057f29979 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -26,7 +26,7 @@ static inline void signal_compat_build_tests(void)
* new fields are handled in copy_siginfo_to_user32()!
*/
BUILD_BUG_ON(NSIGILL != 11);
- BUILD_BUG_ON(NSIGFPE != 14);
+ BUILD_BUG_ON(NSIGFPE != 15);
BUILD_BUG_ON(NSIGSEGV != 7);
BUILD_BUG_ON(NSIGBUS != 5);
BUILD_BUG_ON(NSIGTRAP != 4);