summaryrefslogtreecommitdiff
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/fault.c56
-rw-r--r--arch/x86/mm/gup.c8
-rw-r--r--arch/x86/mm/hugetlbpage.c2
-rw-r--r--arch/x86/mm/init.c41
-rw-r--r--arch/x86/mm/init_64.c10
-rw-r--r--arch/x86/mm/kasan_init_64.c1
-rw-r--r--arch/x86/mm/kaslr.c4
-rw-r--r--arch/x86/mm/mpx.c12
-rw-r--r--arch/x86/mm/numa_32.c1
-rw-r--r--arch/x86/mm/pat.c28
-rw-r--r--arch/x86/mm/tlb.c4
11 files changed, 94 insertions, 73 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9f72ca3b2669..8b5ff88aa4f8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -191,8 +191,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
* 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
* faulted on a pte with its pkey=4.
*/
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
- struct vm_area_struct *vma)
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
{
/* This is effectively an #ifdef */
if (!boot_cpu_has(X86_FEATURE_OSPKE))
@@ -208,7 +207,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
* valid VMA, so we should never reach this without a
* valid VMA.
*/
- if (!vma) {
+ if (!pkey) {
WARN_ONCE(1, "PKU fault with no VMA passed in");
info->si_pkey = 0;
return;
@@ -218,13 +217,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
* absolutely guranteed to be 100% accurate because of
* the race explained above.
*/
- info->si_pkey = vma_pkey(vma);
+ info->si_pkey = *pkey;
}
static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
- struct task_struct *tsk, struct vm_area_struct *vma,
- int fault)
+ struct task_struct *tsk, u32 *pkey, int fault)
{
unsigned lsb = 0;
siginfo_t info;
@@ -239,7 +237,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
lsb = PAGE_SHIFT;
info.si_addr_lsb = lsb;
- fill_sig_info_pkey(si_code, &info, vma);
+ fill_sig_info_pkey(si_code, &info, pkey);
force_sig_info(si_signo, &info, tsk);
}
@@ -718,8 +716,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
struct task_struct *tsk = current;
unsigned long flags;
int sig;
- /* No context means no VMA to pass down */
- struct vm_area_struct *vma = NULL;
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs, X86_TRAP_PF)) {
@@ -744,7 +740,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
/* XXX: hwpoison faults will set the wrong code. */
force_sig_info_fault(signal, si_code, address,
- tsk, vma, 0);
+ tsk, NULL, 0);
}
/*
@@ -853,8 +849,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
static void
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma,
- int si_code)
+ unsigned long address, u32 *pkey, int si_code)
{
struct task_struct *tsk = current;
@@ -902,7 +897,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_PF;
- force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+ force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
return;
}
@@ -915,9 +910,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
static noinline void
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma)
+ unsigned long address, u32 *pkey)
{
- __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+ __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
}
static void
@@ -925,6 +920,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
unsigned long address, struct vm_area_struct *vma, int si_code)
{
struct mm_struct *mm = current->mm;
+ u32 pkey;
+
+ if (vma)
+ pkey = vma_pkey(vma);
/*
* Something tried to access memory that isn't in our memory map..
@@ -932,7 +931,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
*/
up_read(&mm->mmap_sem);
- __bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+ __bad_area_nosemaphore(regs, error_code, address,
+ (vma) ? &pkey : NULL, si_code);
}
static noinline void
@@ -975,7 +975,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
- struct vm_area_struct *vma, unsigned int fault)
+ u32 *pkey, unsigned int fault)
{
struct task_struct *tsk = current;
int code = BUS_ADRERR;
@@ -1002,13 +1002,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
code = BUS_MCEERR_AR;
}
#endif
- force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+ force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
}
static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma,
- unsigned int fault)
+ unsigned long address, u32 *pkey, unsigned int fault)
{
if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
no_context(regs, error_code, address, 0, 0);
@@ -1032,9 +1031,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
- do_sigbus(regs, error_code, address, vma, fault);
+ do_sigbus(regs, error_code, address, pkey, fault);
else if (fault & VM_FAULT_SIGSEGV)
- bad_area_nosemaphore(regs, error_code, address, vma);
+ bad_area_nosemaphore(regs, error_code, address, pkey);
else
BUG();
}
@@ -1220,6 +1219,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
struct mm_struct *mm;
int fault, major = 0;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ u32 pkey;
tsk = current;
mm = tsk->mm;
@@ -1393,7 +1393,17 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if
* we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
+ *
+ * Note that handle_userfault() may also release and reacquire mmap_sem
+ * (and not return with VM_FAULT_RETRY), when returning to userland to
+ * repeat the page fault later with a VM_FAULT_NOPAGE retval
+ * (potentially after handling any pending signal during the return to
+ * userland). The return to userland is identified whenever
+ * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
+ * Thus we have to be careful about not touching vma after handling the
+ * fault, so we read the pkey beforehand.
*/
+ pkey = vma_pkey(vma);
fault = handle_mm_fault(vma, address, flags);
major |= fault & VM_FAULT_MAJOR;
@@ -1422,7 +1432,7 @@ good_area:
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
- mm_fault_error(regs, error_code, address, vma, fault);
+ mm_fault_error(regs, error_code, address, &pkey, fault);
return;
}
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 0d4fb3ebbbac..1680768d392c 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -120,6 +120,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
return 0;
}
+ if (!pte_allows_gup(pte_val(pte), write)) {
+ pte_unmap(ptep);
+ return 0;
+ }
+
if (pte_devmap(pte)) {
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
@@ -127,8 +132,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
pte_unmap(ptep);
return 0;
}
- } else if (!pte_allows_gup(pte_val(pte), write) ||
- pte_special(pte)) {
+ } else if (pte_special(pte)) {
pte_unmap(ptep);
return 0;
}
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 2ae8584b44c7..fe342e8ed529 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -144,7 +144,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
if (mm->get_unmapped_area == arch_get_unmapped_area)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 22af912d66d2..889e7619a091 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -643,21 +643,40 @@ void __init init_mem_mapping(void)
* devmem_is_allowed() checks to see if /dev/mem access to a certain address
* is valid. The argument is a physical page number.
*
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
*/
int devmem_is_allowed(unsigned long pagenr)
{
- if (pagenr < 256)
- return 1;
- if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+ if (page_is_ram(pagenr)) {
+ /*
+ * For disallowed memory regions in the low 1MB range,
+ * request that the page be shown as all zeros.
+ */
+ if (pagenr < 256)
+ return 2;
+
+ return 0;
+ }
+
+ /*
+ * This must follow RAM test, since System RAM is considered a
+ * restricted resource under CONFIG_STRICT_IOMEM.
+ */
+ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+ /* Low 1MB bypasses iomem restrictions. */
+ if (pagenr < 256)
+ return 1;
+
return 0;
- if (!page_is_ram(pagenr))
- return 1;
- return 0;
+ }
+
+ return 1;
}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 14b9dd71d9e8..3e27ded6ac65 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -94,10 +94,10 @@ __setup("noexec32=", nonx32_setup);
*/
void sync_global_pgds(unsigned long start, unsigned long end, int removed)
{
- unsigned long address;
+ unsigned long addr;
- for (address = start; address <= end; address += PGDIR_SIZE) {
- const pgd_t *pgd_ref = pgd_offset_k(address);
+ for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+ const pgd_t *pgd_ref = pgd_offset_k(addr);
struct page *page;
/*
@@ -113,7 +113,7 @@ void sync_global_pgds(unsigned long start, unsigned long end, int removed)
pgd_t *pgd;
spinlock_t *pgt_lock;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ pgd = (pgd_t *)page_address(page) + pgd_index(addr);
/* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
@@ -689,7 +689,7 @@ static void __meminit free_pagetable(struct page *page, int order)
if (PageReserved(page)) {
__ClearPageReserved(page);
- magic = (unsigned long)page->lru.next;
+ magic = (unsigned long)page->freelist;
if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
while (nr_pages--)
put_page_bootmem(page++);
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 0493c17b8a51..333362f992e4 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
#define pr_fmt(fmt) "kasan: " fmt
#include <linux/bootmem.h>
#include <linux/kasan.h>
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 887e57182716..aed206475aa7 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
#if defined(CONFIG_X86_ESPFIX64)
static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
#elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_START;
+static const unsigned long vaddr_end = EFI_VA_END;
#else
static const unsigned long vaddr_end = __START_KERNEL_map;
#endif
@@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void)
*/
BUILD_BUG_ON(vaddr_start >= vaddr_end);
BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
- vaddr_end >= EFI_VA_START);
+ vaddr_end >= EFI_VA_END);
BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
IS_ENABLED(CONFIG_EFI)) &&
vaddr_end >= __START_KERNEL_map);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index e4f800999b32..a75103e7f963 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
* We were not able to extract an address from the instruction,
* probably because there was something invalid in it.
*/
- if (info->si_addr == (void *)-1) {
+ if (info->si_addr == (void __user *)-1) {
err = -EINVAL;
goto err_out;
}
@@ -525,15 +525,7 @@ int mpx_handle_bd_fault(void)
if (!kernel_managing_mpx_tables(current->mm))
return -EINVAL;
- if (do_mpx_bt_fault()) {
- force_sig(SIGSEGV, current);
- /*
- * The force_sig() is essentially "handling" this
- * exception, so we do not pass up the error
- * from do_mpx_bt_fault().
- */
- }
- return 0;
+ return do_mpx_bt_fault();
}
/*
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 6b7ce6279133..aca6295350f3 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -100,5 +100,6 @@ void __init initmem_init(void)
printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
(ulong) pfn_to_kaddr(highstart_pfn));
+ __vmalloc_start_set = true;
setup_bootmem_allocator();
}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 83e701f160a9..89d7907c4218 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -36,14 +36,14 @@
#undef pr_fmt
#define pr_fmt(fmt) "" fmt
-static bool boot_cpu_done;
-
-static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
-static void init_cache_modes(void);
+static bool __read_mostly boot_cpu_done;
+static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static bool __read_mostly pat_initialized;
+static bool __read_mostly init_cm_done;
void pat_disable(const char *reason)
{
- if (!__pat_enabled)
+ if (pat_disabled)
return;
if (boot_cpu_done) {
@@ -51,10 +51,8 @@ void pat_disable(const char *reason)
return;
}
- __pat_enabled = 0;
+ pat_disabled = true;
pr_info("x86/PAT: %s\n", reason);
-
- init_cache_modes();
}
static int __init nopat(char *str)
@@ -66,7 +64,7 @@ early_param("nopat", nopat);
bool pat_enabled(void)
{
- return !!__pat_enabled;
+ return pat_initialized;
}
EXPORT_SYMBOL_GPL(pat_enabled);
@@ -204,6 +202,8 @@ static void __init_cache_modes(u64 pat)
update_cache_mode_entry(i, cache);
}
pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
+
+ init_cm_done = true;
}
#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8))
@@ -224,6 +224,7 @@ static void pat_bsp_init(u64 pat)
}
wrmsrl(MSR_IA32_CR_PAT, pat);
+ pat_initialized = true;
__init_cache_modes(pat);
}
@@ -241,10 +242,9 @@ static void pat_ap_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-static void init_cache_modes(void)
+void init_cache_modes(void)
{
u64 pat = 0;
- static int init_cm_done;
if (init_cm_done)
return;
@@ -286,8 +286,6 @@ static void init_cache_modes(void)
}
__init_cache_modes(pat);
-
- init_cm_done = 1;
}
/**
@@ -305,10 +303,8 @@ void pat_init(void)
u64 pat;
struct cpuinfo_x86 *c = &boot_cpu_data;
- if (!pat_enabled()) {
- init_cache_modes();
+ if (pat_disabled)
return;
- }
if ((c->x86_vendor == X86_VENDOR_INTEL) &&
(((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a7655f6caf7d..75fb01109f94 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -263,8 +263,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
{
struct flush_tlb_info info;
- if (end == 0)
- end = start + PAGE_SIZE;
info.flush_mm = mm;
info.flush_start = start;
info.flush_end = end;
@@ -393,7 +391,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
}
if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
+ flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
preempt_enable();
}
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-26 02:46:30 +0000