linux_dsm_epyc7002/arch/x86/include/asm/tlbflush.h
Daniel Borkmann 2c4ea6e28d x86/tlb: Fix tlb flushing when lguest clears PGE
Fengguang reported random corruptions from various locations on x86-32
after commits d2852a2240 ("arch: add ARCH_HAS_SET_MEMORY config") and
9d876e79df ("bpf: fix unlocking of jited image when module ronx not set")
that uses the former. While x86-32 doesn't have a JIT like x86_64, the
bpf_prog_lock_ro() and bpf_prog_unlock_ro() got enabled due to
ARCH_HAS_SET_MEMORY, whereas Fengguang's test kernel doesn't have module
support built in and therefore never had the DEBUG_SET_MODULE_RONX setting
enabled.

After investigating the crashes further, it turned out that using
set_memory_ro() and set_memory_rw() didn't have the desired effect, for
example, setting the pages as read-only on x86-32 would still let
probe_kernel_write() succeed without error. This behavior would manifest
itself in situations where the vmalloc'ed buffer was accessed prior to
set_memory_*() such as in case of bpf_prog_alloc(). In cases where it
wasn't, the page attribute changes seemed to have taken effect, leading to
the conclusion that a TLB invalidate didn't happen. Moreover, it turned out
that this issue reproduced with qemu in "-cpu kvm64" mode, but not for
"-cpu host". When the issue occurs, change_page_attr_set_clr() did trigger
a TLB flush as expected via __flush_tlb_all() through cpa_flush_range(),
though.

There are 3 variants for issuing a TLB flush: invpcid_flush_all() (depends
on CPU feature bits X86_FEATURE_INVPCID, X86_FEATURE_PGE), cr4 based flush
(depends on X86_FEATURE_PGE), and cr3 based flush.  For "-cpu host" case in
my setup, the flush used invpcid_flush_all() variant, whereas for "-cpu
kvm64", the flush was cr4 based. Switching the kvm64 case to cr3 manually
worked fine, and further investigating the cr4 one turned out that
X86_CR4_PGE bit was not set in cr4 register, meaning the
__native_flush_tlb_global_irq_disabled() wrote cr4 twice with the same
value instead of clearing X86_CR4_PGE in the first write to trigger the
flush.

It turned out that X86_CR4_PGE was cleared from cr4 during init from
lguest_arch_host_init() via adjust_pge(). The X86_FEATURE_PGE bit is also
cleared from there due to concerns of using PGE in guest kernel that can
lead to hard to trace bugs (see bff672e630 ("lguest: documentation V:
Host") in init()). The CPU feature bits are cleared in dynamic
boot_cpu_data, but they never propagated to __flush_tlb_all() as it uses
static_cpu_has() instead of boot_cpu_has() for testing which variant of TLB
flushing to use, meaning they still used the old setting of the host
kernel.

Clearing via setup_clear_cpu_cap(X86_FEATURE_PGE) so this would propagate
to static_cpu_has() checks is too late at this point as sections have been
patched already, so for now, it seems reasonable to switch back to
boot_cpu_has(X86_FEATURE_PGE) as it was prior to commit c109bf9599
("x86/cpufeature: Remove cpu_has_pge"). This lets the TLB flush trigger via
cr3 as originally intended, properly makes the new page attributes visible
and thus fixes the crashes seen by Fengguang.

Fixes: c109bf9599 ("x86/cpufeature: Remove cpu_has_pge")
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: bp@suse.de
Cc: Kees Cook <keescook@chromium.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: lkp@01.org
Cc: Laura Abbott <labbott@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernrl.org/r/20170301125426.l4nf65rx4wahohyl@wfg-t540p.sh.intel.com
Link: http://lkml.kernel.org/r/25c41ad9eca164be4db9ad84f768965b7eb19d9e.1489191673.git.daniel@iogearbox.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2017-03-12 11:19:29 +01:00

335 lines
8.1 KiB
C

#ifndef _ASM_X86_TLBFLUSH_H
#define _ASM_X86_TLBFLUSH_H
#include <linux/mm.h>
#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
#include <asm/special_insns.h>
static inline void __invpcid(unsigned long pcid, unsigned long addr,
unsigned long type)
{
struct { u64 d[2]; } desc = { { pcid, addr } };
/*
* The memory clobber is because the whole point is to invalidate
* stale TLB entries and, especially if we're flushing global
* mappings, we don't want the compiler to reorder any subsequent
* memory accesses before the TLB flush.
*
* The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
* invpcid (%rcx), %rax in long mode.
*/
asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
: : "m" (desc), "a" (type), "c" (&desc) : "memory");
}
#define INVPCID_TYPE_INDIV_ADDR 0
#define INVPCID_TYPE_SINGLE_CTXT 1
#define INVPCID_TYPE_ALL_INCL_GLOBAL 2
#define INVPCID_TYPE_ALL_NON_GLOBAL 3
/* Flush all mappings for a given pcid and addr, not including globals. */
static inline void invpcid_flush_one(unsigned long pcid,
unsigned long addr)
{
__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
}
/* Flush all mappings for a given PCID, not including globals. */
static inline void invpcid_flush_single_context(unsigned long pcid)
{
__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
}
/* Flush all mappings, including globals, for all PCIDs. */
static inline void invpcid_flush_all(void)
{
__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
}
/* Flush all mappings for all PCIDs except globals. */
static inline void invpcid_flush_all_nonglobals(void)
{
__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
}
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define __flush_tlb() __native_flush_tlb()
#define __flush_tlb_global() __native_flush_tlb_global()
#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
#endif
struct tlb_state {
#ifdef CONFIG_SMP
struct mm_struct *active_mm;
int state;
#endif
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
*/
unsigned long cr4;
};
DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
/* Initialize cr4 shadow for this CPU. */
static inline void cr4_init_shadow(void)
{
this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
}
/* Set in this cpu's CR4. */
static inline void cr4_set_bits(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
if ((cr4 | mask) != cr4) {
cr4 |= mask;
this_cpu_write(cpu_tlbstate.cr4, cr4);
__write_cr4(cr4);
}
}
/* Clear in this cpu's CR4. */
static inline void cr4_clear_bits(unsigned long mask)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
if ((cr4 & ~mask) != cr4) {
cr4 &= ~mask;
this_cpu_write(cpu_tlbstate.cr4, cr4);
__write_cr4(cr4);
}
}
/* Read the CR4 shadow. */
static inline unsigned long cr4_read_shadow(void)
{
return this_cpu_read(cpu_tlbstate.cr4);
}
/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
* up after us can get the correct flags. This should only be used
* during boot on the boot cpu.
*/
extern unsigned long mmu_cr4_features;
extern u32 *trampoline_cr4_features;
static inline void cr4_set_bits_and_update_boot(unsigned long mask)
{
mmu_cr4_features |= mask;
if (trampoline_cr4_features)
*trampoline_cr4_features = mmu_cr4_features;
cr4_set_bits(mask);
}
static inline void __native_flush_tlb(void)
{
/*
* If current->mm == NULL then we borrow a mm which may change during a
* task switch and therefore we must not be preempted while we write CR3
* back:
*/
preempt_disable();
native_write_cr3(native_read_cr3());
preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
{
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
/* clear PGE */
native_write_cr4(cr4 & ~X86_CR4_PGE);
/* write old PGE again and flush TLBs */
native_write_cr4(cr4);
}
static inline void __native_flush_tlb_global(void)
{
unsigned long flags;
if (static_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
*/
invpcid_flush_all();
return;
}
/*
* Read-modify-write to CR4 - protect it from preemption and
* from interrupts. (Use the raw variant because this code can
* be called from deep inside debugging code.)
*/
raw_local_irq_save(flags);
__native_flush_tlb_global_irq_disabled();
raw_local_irq_restore(flags);
}
static inline void __native_flush_tlb_single(unsigned long addr)
{
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
}
static inline void __flush_tlb_all(void)
{
if (boot_cpu_has(X86_FEATURE_PGE))
__flush_tlb_global();
else
__flush_tlb();
}
static inline void __flush_tlb_one(unsigned long addr)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
}
#define TLB_FLUSH_ALL -1UL
/*
* TLB flushing:
*
* - flush_tlb() flushes the current mm struct TLBs
* - flush_tlb_all() flushes all processes TLBs
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
* - flush_tlb_range(vma, start, end) flushes a range of pages
* - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
* - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus
*
* ..but the i386 has somewhat limited tlb flushing capabilities,
* and page-granular flushes are available only on i486 and up.
*/
#ifndef CONFIG_SMP
/* "_up" is for UniProcessor.
*
* This is a helper for other header functions. *Not* intended to be called
* directly. All global TLB flushes need to either call this, or to bump the
* vm statistics themselves.
*/
static inline void __flush_tlb_up(void)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
}
static inline void flush_tlb_all(void)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb_all();
}
static inline void flush_tlb(void)
{
__flush_tlb_up();
}
static inline void local_flush_tlb(void)
{
__flush_tlb_up();
}
static inline void flush_tlb_mm(struct mm_struct *mm)
{
if (mm == current->active_mm)
__flush_tlb_up();
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long addr)
{
if (vma->vm_mm == current->active_mm)
__flush_tlb_one(addr);
}
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
if (vma->vm_mm == current->active_mm)
__flush_tlb_up();
}
static inline void flush_tlb_mm_range(struct mm_struct *mm,
unsigned long start, unsigned long end, unsigned long vmflag)
{
if (mm == current->active_mm)
__flush_tlb_up();
}
static inline void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
unsigned long start,
unsigned long end)
{
}
static inline void reset_lazy_tlbstate(void)
{
}
static inline void flush_tlb_kernel_range(unsigned long start,
unsigned long end)
{
flush_tlb_all();
}
#else /* SMP */
#include <asm/smp.h>
#define local_flush_tlb() __flush_tlb()
#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
#define flush_tlb_range(vma, start, end) \
flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
extern void flush_tlb_all(void);
extern void flush_tlb_current_task(void);
extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
#define flush_tlb() flush_tlb_current_task()
void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
unsigned long start, unsigned long end);
#define TLBSTATE_OK 1
#define TLBSTATE_LAZY 2
static inline void reset_lazy_tlbstate(void)
{
this_cpu_write(cpu_tlbstate.state, 0);
this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
}
#endif /* SMP */
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
#endif
#endif /* _ASM_X86_TLBFLUSH_H */