diff options
authorThomas Gleixner <tglx@linutronix.de>2018-01-14 00:23:57 +0100
committerThomas Gleixner <tglx@linutronix.de>2018-01-14 10:45:53 +0100
commitf10ee3dcc9f0aba92a5c4c064628be5200765dc2 (patch)
parent352909b49ba0d74929b96af6dfbefc854ab6ebb5 (diff)
x86/pti: Fix !PCID and sanitize defines
The switch to the user space page tables in the low level ASM code sets unconditionally bit 12 and bit 11 of CR3. Bit 12 is switching the base address of the page directory to the user part, bit 11 is switching the PCID to the PCID associated with the user page tables. This fails on a machine which lacks PCID support because bit 11 is set in CR3. Bit 11 is reserved when PCID is inactive. While the Intel SDM claims that the reserved bits are ignored when PCID is disabled, the AMD APM states that they should be cleared. This went unnoticed as the AMD APM was not checked when the code was developed and reviewed and test systems with Intel CPUs never failed to boot. The report is against a Centos 6 host where the guest fails to boot, so it's not yet clear whether this is a virt issue or can happen on real hardware too, but thats irrelevant as the AMD APM clearly ask for clearing the reserved bits. Make sure that on non PCID machines bit 11 is not set by the page table switching code. Andy suggested to rename the related bits and masks so they are clearly describing what they should be used for, which is done as well for clarity. That split could have been done with alternatives but the macro hell is horrible and ugly. This can be done on top if someone cares to remove the extra orq. For now it's a straight forward fix. Fixes: 6fd166aae78c ("x86/mm: Use/Fix PCID to optimize user/kernel switches") Reported-by: Laura Abbott <labbott@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable <stable@vger.kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: Willy Tarreau <w@1wt.eu> Cc: David Woodhouse <dwmw@amazon.co.uk> Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1801140009150.2371@nanos
3 files changed, 23 insertions, 21 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 45a63e00a6af..3f48f695d5e6 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -198,8 +198,11 @@ For 32-bit we have the following conventions - kernel is built with
* PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
* halves:
.macro SET_NOFLUSH_BIT reg:req
bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
@@ -208,7 +211,7 @@ For 32-bit we have the following conventions - kernel is built with
.macro ADJUST_KERNEL_CR3 reg:req
/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
- andq $(~PTI_SWITCH_MASK), \reg
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
@@ -239,15 +242,19 @@ For 32-bit we have the following conventions - kernel is built with
/* Flush needed, clear the bit */
btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
movq \scratch_reg2, \scratch_reg
- jmp .Lwrcr3_\@
+ jmp .Lwrcr3_pcid_\@
movq \scratch_reg2, \scratch_reg
SET_NOFLUSH_BIT \scratch_reg
+ /* Flip the ASID to the user version */
+ orq $(PTI_USER_PCID_MASK), \scratch_reg
- /* Flip the PGD and ASID to the user version */
- orq $(PTI_SWITCH_MASK), \scratch_reg
+ /* Flip the PGD to the user version */
+ orq $(PTI_USER_PGTABLE_MASK), \scratch_reg
mov \scratch_reg, %cr3
@@ -263,17 +270,12 @@ For 32-bit we have the following conventions - kernel is built with
movq %cr3, \scratch_reg
movq \scratch_reg, \save_reg
- * Is the "switch mask" all zero? That means that both of
- * these are zero:
- *
- * 1. The user/kernel PCID bit, and
- * 2. The user/kernel "bit" that points CR3 to the
- * bottom half of the 8k PGD
- *
- * That indicates a kernel CR3 value, not a user CR3.
+ * Test the user pagetable bit. If set, then the user page tables
+ * are active. If clear CR3 already has the kernel page table
+ * active.
- testq $(PTI_SWITCH_MASK), \scratch_reg
- jz .Ldone_\@
+ bt $PTI_USER_PGTABLE_BIT, \scratch_reg
+ jnc .Ldone_\@
ADJUST_KERNEL_CR3 \scratch_reg
movq \scratch_reg, %cr3
@@ -290,7 +292,7 @@ For 32-bit we have the following conventions - kernel is built with
* KERNEL pages can always resume with NOFLUSH as we do
* explicit flushes.
- bt $X86_CR3_PTI_SWITCH_BIT, \save_reg
+ bt $PTI_USER_PGTABLE_BIT, \save_reg
jnc .Lnoflush_\@
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 6a60fea90b9d..625a52a5594f 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -40,7 +40,7 @@
#define CR3_NOFLUSH BIT_ULL(63)
-# define X86_CR3_PTI_SWITCH_BIT 11
+# define X86_CR3_PTI_PCID_USER_BIT 11
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index f9b48ce152eb..3effd3c994af 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -81,13 +81,13 @@ static inline u16 kern_pcid(u16 asid)
* Make sure that the dynamic ASID space does not confict with the
* bit we are using to switch between user and kernel ASIDs.
* The ASID being passed in here should have respected the
* MAX_ASID_AVAILABLE and thus never have the switch bit set.
- VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT));
+ VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
* The dynamically-assigned ASIDs that get passed in are small
@@ -112,7 +112,7 @@ static inline u16 user_pcid(u16 asid)
u16 ret = kern_pcid(asid);
- ret |= 1 << X86_CR3_PTI_SWITCH_BIT;
+ ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
return ret;