[GIT pull] x86 updates for 4.19

From: Thomas Gleixner
Date: Sun Aug 26 2018 - 05:39:31 EST


Linus,

please pull the latest x86-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus

A pile of x86 fixes:

- Correct the L!TF fallout on 32bit and the off by one in the 'too much
RAM for protection' calculation.

- Add a helpful kernel message for the 'too much RAM' case

- Unbreak the VDSO in case that the compiler desides to use indirect
jumps/calls and emits retpolines which cannot be resolved because the
kernel uses its own thunks, which does not work for the VDSO. Make it
use the builtin thunks.

- Re-export start_thread() which was unexported when the 32/64bit
implementation was unified. start_thread() is required by modular binfmt
handlers.

- Trivial cleanups

Thanks,

tglx

------------------>
Andy Lutomirski (1):
x86/vdso: Fix vDSO build if a retpoline is emitted

Arnd Bergmann (1):
x86/mce: Add notifier_block forward declaration

Josh Poimboeuf (1):
x86/kvm/vmx: Remove duplicate l1d flush definitions

Rian Hunter (1):
x86/process: Re-export start_thread()

Vlastimil Babka (3):
x86/speculation/l1tf: Fix overflow in l1tf_pfn_limit() on 32bit
x86/speculation/l1tf: Fix off-by-one error when warning that system has too much RAM
x86/speculation/l1tf: Suggest what to do on systems with too much RAM


Makefile | 4 ++++
arch/x86/entry/vdso/Makefile | 6 ++++--
arch/x86/include/asm/mce.h | 1 +
arch/x86/include/asm/processor.h | 4 ++--
arch/x86/kernel/cpu/bugs.c | 4 ++++
arch/x86/kernel/process_64.c | 1 +
arch/x86/kvm/vmx.c | 3 ---
arch/x86/mm/init.c | 4 ++--
arch/x86/mm/mmap.c | 2 +-
9 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/Makefile b/Makefile
index a0650bf79606..7bab2e90e4e1 100644
--- a/Makefile
+++ b/Makefile
@@ -507,9 +507,13 @@ KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
endif

RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register
+RETPOLINE_VDSO_CFLAGS_GCC := -mindirect-branch=thunk-inline -mindirect-branch-register
RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk
+RETPOLINE_VDSO_CFLAGS_CLANG := -mretpoline
RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG)))
+RETPOLINE_VDSO_CFLAGS := $(call cc-option,$(RETPOLINE_VDSO_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_VDSO_CFLAGS_CLANG)))
export RETPOLINE_CFLAGS
+export RETPOLINE_VDSO_CFLAGS

KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
KBUILD_AFLAGS += $(call cc-option,-fno-PIE)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 9f695f517747..fa3f439f0a92 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -68,9 +68,9 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
$(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
-fno-omit-frame-pointer -foptimize-sibling-calls \
- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS)

-$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)

#
# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
@@ -132,11 +132,13 @@ KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)

$(obj)/vdso32.so.dbg: FORCE \
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 8c7b3e5a2d01..3a17107594c8 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -148,6 +148,7 @@ enum mce_notifier_prios {
MCE_PRIO_LOWEST = 0,
};

+struct notifier_block;
extern void mce_register_decode_chain(struct notifier_block *nb);
extern void mce_unregister_decode_chain(struct notifier_block *nb);

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 682286aca881..c24297268ebc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,9 +181,9 @@ extern const struct seq_operations cpuinfo_op;

extern void cpu_detect(struct cpuinfo_x86 *c);

-static inline unsigned long l1tf_pfn_limit(void)
+static inline unsigned long long l1tf_pfn_limit(void)
{
- return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1;
+ return BIT_ULL(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT);
}

extern void early_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index cb4a16292aa7..4c2313d0b9ca 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -702,6 +702,10 @@ static void __init l1tf_select_mitigation(void)
half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
+ pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
+ half_pa);
+ pr_info("However, doing so will make a part of your RAM unusable.\n");
+ pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
return;
}

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 476e3ddf8890..a451bc374b9b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -384,6 +384,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
start_thread_common(regs, new_ip, new_sp,
__USER_CS, __USER_DS, 0);
}
+EXPORT_SYMBOL_GPL(start_thread);

#ifdef CONFIG_COMPAT
void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 46b428c0990e..4be481c72f60 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9726,9 +9726,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
* information but as all relevant affected CPUs have 32KiB L1D cache size
* there is no point in doing so.
*/
-#define L1D_CACHE_ORDER 4
-static void *vmx_l1d_flush_pages;
-
static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
{
int size = PAGE_SIZE << L1D_CACHE_ORDER;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index acfab322fbe0..63a6f9fcaf20 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -923,7 +923,7 @@ unsigned long max_swapfile_size(void)

if (boot_cpu_has_bug(X86_BUG_L1TF)) {
/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
- unsigned long l1tf_limit = l1tf_pfn_limit() + 1;
+ unsigned long long l1tf_limit = l1tf_pfn_limit();
/*
* We encode swap offsets also with 3 bits below those for pfn
* which makes the usable limit higher.
@@ -931,7 +931,7 @@ unsigned long max_swapfile_size(void)
#if CONFIG_PGTABLE_LEVELS > 2
l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
#endif
- pages = min_t(unsigned long, l1tf_limit, pages);
+ pages = min_t(unsigned long long, l1tf_limit, pages);
}
return pages;
}
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index f40ab8185d94..1e95d57760cf 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -257,7 +257,7 @@ bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
/* If it's real memory always allow */
if (pfn_valid(pfn))
return true;
- if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+ if (pfn >= l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
return false;
return true;
}