[PATCH v3 5/6] x86: Move the vvar and hpet mappings next to the 64-bit vDSO

From: Andy Lutomirski
Date: Fri May 02 2014 - 16:16:15 EST


This makes the 64-bit and x32 vdsos use the same mechanism as the
32-bit vdso. Most of the churn is deleting all the old fixmap code.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
---
arch/x86/include/asm/fixmap.h | 10 +++-------
arch/x86/include/asm/vvar.h | 20 +-------------------
arch/x86/include/uapi/asm/vsyscall.h | 7 +------
arch/x86/kernel/cpu/common.c | 1 +
arch/x86/kernel/hpet.c | 3 ---
arch/x86/kernel/vsyscall_64.c | 15 ++++-----------
arch/x86/mm/fault.c | 5 +++--
arch/x86/mm/init_64.c | 10 +++++-----
arch/x86/vdso/vclock_gettime.c | 22 +++++-----------------
arch/x86/vdso/vdso-layout.lds.S | 2 --
arch/x86/xen/mmu.c | 8 +++-----
11 files changed, 26 insertions(+), 77 deletions(-)

diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 43f482a..afdb93d 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -24,7 +24,7 @@
#include <linux/threads.h>
#include <asm/kmap_types.h>
#else
-#include <asm/vsyscall.h>
+#include <uapi/asm/vsyscall.h>
#endif

/*
@@ -41,7 +41,7 @@
extern unsigned long __FIXADDR_TOP;
#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP)
#else
-#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE)
+#define FIXADDR_TOP (VSYSCALL_ADDR)
#endif


@@ -68,11 +68,7 @@ enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_HOLE,
#else
- VSYSCALL_LAST_PAGE,
- VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
- + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
- VVAR_PAGE,
- VSYSCALL_HPET,
+ VSYSCALL_PAGE,
#ifdef CONFIG_PARAVIRT_CLOCK
PVCLOCK_FIXMAP_BEGIN,
PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 081d909..5d2b9ad 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -29,31 +29,13 @@

#else

-#ifdef BUILD_VDSO32
+extern char __vvar_page;

#define DECLARE_VVAR(offset, type, name) \
extern type vvar_ ## name __attribute__((visibility("hidden")));

#define VVAR(name) (vvar_ ## name)

-#else
-
-extern char __vvar_page;
-
-/* Base address of vvars. This is not ABI. */
-#ifdef CONFIG_X86_64
-#define VVAR_ADDRESS (-10*1024*1024 - 4096)
-#else
-#define VVAR_ADDRESS (&__vvar_page)
-#endif
-
-#define DECLARE_VVAR(offset, type, name) \
- static type const * const vvaraddr_ ## name = \
- (void *)(VVAR_ADDRESS + (offset));
-
-#define VVAR(name) (*vvaraddr_ ## name)
-#endif
-
#define DEFINE_VVAR(type, name) \
type name \
__attribute__((section(".vvar_" #name), aligned(16))) __visible
diff --git a/arch/x86/include/uapi/asm/vsyscall.h b/arch/x86/include/uapi/asm/vsyscall.h
index 85dc1b3..b97dd6e 100644
--- a/arch/x86/include/uapi/asm/vsyscall.h
+++ b/arch/x86/include/uapi/asm/vsyscall.h
@@ -7,11 +7,6 @@ enum vsyscall_num {
__NR_vgetcpu,
};

-#define VSYSCALL_START (-10UL << 20)
-#define VSYSCALL_SIZE 1024
-#define VSYSCALL_END (-2UL << 20)
-#define VSYSCALL_MAPPED_PAGES 1
-#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr))
-
+#define VSYSCALL_ADDR (-10UL << 20)

#endif /* _UAPI_ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7c65b46..2cbbf88 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -20,6 +20,7 @@
#include <asm/processor.h>
#include <asm/debugreg.h>
#include <asm/sections.h>
+#include <asm/vsyscall.h>
#include <linux/topology.h>
#include <linux/cpumask.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 8d80ae0..bbc15a0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -74,9 +74,6 @@ static inline void hpet_writel(unsigned int d, unsigned int a)
static inline void hpet_set_mapping(void)
{
hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
-#ifdef CONFIG_X86_64
- __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE);
-#endif
}

static inline void hpet_clear_mapping(void)
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 8b3b3eb..ea5b570 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -91,7 +91,7 @@ static int addr_to_vsyscall_nr(unsigned long addr)
{
int nr;

- if ((addr & ~0xC00UL) != VSYSCALL_START)
+ if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
return -EINVAL;

nr = (addr & 0xC00UL) >> 10;
@@ -330,24 +330,17 @@ void __init map_vsyscall(void)
{
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);

- __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+ __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
vsyscall_mode == NATIVE
? PAGE_KERNEL_VSYSCALL
: PAGE_KERNEL_VVAR);
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
- (unsigned long)VSYSCALL_START);
-
- __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
- (unsigned long)VVAR_ADDRESS);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
+ (unsigned long)VSYSCALL_ADDR);
}

static int __init vsyscall_init(void)
{
- BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
-
cpu_notifier_register_begin();

on_each_cpu(cpu_vsyscall_init, NULL, 1);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8e57229..858b47b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,7 +18,8 @@
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
-#include <asm/fixmap.h> /* VSYSCALL_START */
+#include <asm/fixmap.h> /* VSYSCALL_ADDR */
+#include <asm/vsyscall.h> /* emulate_vsyscall */

#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>
@@ -771,7 +772,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
* emulation.
*/
if (unlikely((error_code & PF_INSTR) &&
- ((address & ~0xfff) == VSYSCALL_START))) {
+ ((address & ~0xfff) == VSYSCALL_ADDR))) {
if (emulate_vsyscall(regs, address))
return;
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5638496..6f88184 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1055,8 +1055,8 @@ void __init mem_init(void)
after_bootmem = 1;

/* Register memory areas for /proc/kcore */
- kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
- VSYSCALL_END - VSYSCALL_START, KCORE_OTHER);
+ kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR,
+ PAGE_SIZE, KCORE_OTHER);

mem_init_print_info(NULL);
}
@@ -1186,8 +1186,8 @@ int kern_addr_valid(unsigned long addr)
* not need special handling anymore:
*/
static struct vm_area_struct gate_vma = {
- .vm_start = VSYSCALL_START,
- .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE),
+ .vm_start = VSYSCALL_ADDR,
+ .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
.vm_page_prot = PAGE_READONLY_EXEC,
.vm_flags = VM_READ | VM_EXEC
};
@@ -1218,7 +1218,7 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr)
*/
int in_gate_area_no_mm(unsigned long addr)
{
- return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
+ return (addr & PAGE_MASK) == VSYSCALL_ADDR;
}

const char *arch_vma_name(struct vm_area_struct *vma)
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 091554c..b2e4f49 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -30,9 +30,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
extern time_t __vdso_time(time_t *t);

#ifdef CONFIG_HPET_TIMER
-static inline u32 read_hpet_counter(const volatile void *addr)
+extern u8 hpet_page
+ __attribute__((visibility("hidden")));
+
+static notrace cycle_t vread_hpet(void)
{
- return *(const volatile u32 *) (addr + HPET_COUNTER);
+ return *(const volatile u32 *)(&hpet_page + HPET_COUNTER);
}
#endif

@@ -43,11 +46,6 @@ static inline u32 read_hpet_counter(const volatile void *addr)
#include <asm/fixmap.h>
#include <asm/pvclock.h>

-static notrace cycle_t vread_hpet(void)
-{
- return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET));
-}
-
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
@@ -137,16 +135,6 @@ static notrace cycle_t vread_pvclock(int *mode)

#else

-extern u8 hpet_page
- __attribute__((visibility("hidden")));
-
-#ifdef CONFIG_HPET_TIMER
-static notrace cycle_t vread_hpet(void)
-{
- return read_hpet_counter((const void *)(&hpet_page));
-}
-#endif
-
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index e177c08..2ec72f6 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -47,7 +47,6 @@ SECTIONS

.text : { *(.text*) } :text =0x90909090,

-#ifdef BUILD_VDSO32
/*
* The remainder of the vDSO consists of special pages that are
* shared between the kernel and userspace. It needs to be at the
@@ -69,7 +68,6 @@ SECTIONS

hpet_page = .;
. = . + PAGE_SIZE;
-#endif

. = ALIGN(PAGE_SIZE);
end_mapping = .;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 86e02ea..3060568 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1494,7 +1494,7 @@ static int xen_pgd_alloc(struct mm_struct *mm)
page->private = (unsigned long)user_pgd;

if (user_pgd != NULL) {
- user_pgd[pgd_index(VSYSCALL_START)] =
+ user_pgd[pgd_index(VSYSCALL_ADDR)] =
__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
ret = 0;
}
@@ -2062,8 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
case FIX_KMAP_BEGIN ... FIX_KMAP_END:
# endif
#else
- case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
- case VVAR_PAGE:
+ case VSYSCALL_PAGE:
#endif
case FIX_TEXT_POKE0:
case FIX_TEXT_POKE1:
@@ -2104,8 +2103,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
#ifdef CONFIG_X86_64
/* Replicate changes to map the vsyscall page into the user
pagetable vsyscall mapping. */
- if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
- idx == VVAR_PAGE) {
+ if (idx == VSYSCALL_PAGE) {
unsigned long vaddr = __fix_to_virt(idx);
set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
}
--
1.9.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/