From: Ingo Molnar <mingo@xxxxxxxxxx>
commit 05b042a1944322844eaae7ea596d5f154166d68a upstream.
When two recent commits that increased the size of the 'struct cpu_entry_area'
were merged in -tip, the 32-bit defconfig build started failing on the following
build time assert:
./include/linux/compiler.h:391:38: error: call to ‘__compiletime_assert_189’ declared with attribute error: BUILD_BUG_ON failed: CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE
arch/x86/mm/cpu_entry_area.c:189:2: note: in expansion of macro ‘BUILD_BUG_ON’
In function ‘setup_cpu_entry_area_ptes’,
Which corresponds to the following build time assert:
BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
The purpose of this assert is to sanity check the fixed-value definition of
CPU_ENTRY_AREA_PAGES arch/x86/include/asm/pgtable_32_types.h:
#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 41)
The '41' is supposed to match sizeof(struct cpu_entry_area)/PAGE_SIZE, which value
we didn't want to define in such a low level header, because it would cause
dependency hell.
Every time the size of cpu_entry_area is changed, we have to adjust CPU_ENTRY_AREA_PAGES
accordingly - and this assert is checking that constraint.
But the assert is both imprecise and buggy, primarily because it doesn't
include the single readonly IDT page that is mapped at CPU_ENTRY_AREA_BASE
(which begins at a PMD boundary).
This bug was hidden by the fact that by accident CPU_ENTRY_AREA_PAGES is defined
too large upstream (v5.4-rc8):
#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40)
While 'struct cpu_entry_area' is 155648 bytes, or 38 pages. So we had two extra
pages, which hid the bug.
The following commit (not yet upstream) increased the size to 40 pages:
x86/iopl: ("Restrict iopl() permission scope")
... but increased CPU_ENTRY_AREA_PAGES only 41 - i.e. shortening the gap
to just 1 extra page.
Then another not-yet-upstream commit changed the size again:
880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Which increased the cpu_entry_area size from 38 to 39 pages, but
didn't change CPU_ENTRY_AREA_PAGES (kept it at 40). This worked
fine, because we still had a page left from the accidental 'reserve'.
But when these two commits were merged into the same tree, the
combined size of cpu_entry_area grew from 38 to 40 pages, while
CPU_ENTRY_AREA_PAGES finally caught up to 40 as well.
Which is fine in terms of functionality, but the assert broke:
BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
because CPU_ENTRY_AREA_MAP_SIZE is the total size of the area,
which is 1 page larger due to the IDT page.
To fix all this, change the assert to two precise asserts:
BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
This takes the IDT page into account, and also connects the size-based
define of CPU_ENTRY_AREA_TOTAL_SIZE with the address-subtraction based
define of CPU_ENTRY_AREA_MAP_SIZE.
Also clean up some of the names which made it rather confusing:
- 'CPU_ENTRY_AREA_TOT_SIZE' wasn't actually the 'total' size of
the cpu-entry-area, but the per-cpu array size, so rename this
to CPU_ENTRY_AREA_ARRAY_SIZE.
- Introduce CPU_ENTRY_AREA_TOTAL_SIZE that _is_ the total mapping
size, with the IDT included.
- Add comments where '+1' denotes the IDT mapping - it wasn't
obvious and took me about 3 hours to decode...
Finally, because this particular commit is actually applied after
this patch:
880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Fix the CPU_ENTRY_AREA_PAGES value from 40 pages to the correct 39 pages.
All future commits that change cpu_entry_area will have to adjust
this value precisely.
As a side note, we should probably attempt to remove CPU_ENTRY_AREA_PAGES
and derive its value directly from the structure, without causing
header hell - but that is an adventure for another day! :-)
Fixes: 880a98c33996: ("x86/cpu_entry_area: Add guard page for entry stack on 32bit")
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: stable@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/include/asm/cpu_entry_area.h | 12 +++++++-----
arch/x86/include/asm/pgtable_32_types.h | 8 ++++----
arch/x86/mm/cpu_entry_area.c | 4 +++-
3 files changed, 14 insertions(+), 10 deletions(-)
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -45,7 +45,6 @@ struct cpu_entry_area {
*/
char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
#endif
-#ifdef CONFIG_CPU_SUP_INTEL
/*
* Per CPU debug store for Intel performance monitoring. Wastes a
* full page at the moment.
@@ -56,24 +55,27 @@ struct cpu_entry_area {
* Reserve enough fixmap PTEs.
*/
struct debug_store_buffers cpu_debug_buffers;
-#endif
};
-#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS)
+#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_ARRAY_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+/* Total size includes the readonly IDT mapping page as well: */
+#define CPU_ENTRY_AREA_TOTAL_SIZE (CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE)
DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
extern void setup_cpu_entry_areas(void);
extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+/* Single page reserved for the readonly IDT mapping: */
#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE
#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT)
#define CPU_ENTRY_AREA_MAP_SIZE \
- (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+ (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -42,11 +42,11 @@ extern bool __vmalloc_start_set; /* set
* Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
* to avoid include recursion hell
*/
-#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40)
+#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 39)
-#define CPU_ENTRY_AREA_BASE \
- ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \
- & PMD_MASK)
+/* The +1 is for the readonly IDT page: */
+#define CPU_ENTRY_AREA_BASE \
+ ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK)
#define PKMAP_BASE \
((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -143,7 +143,9 @@ static __init void setup_cpu_entry_area_
#ifdef CONFIG_X86_32
unsigned long start, end;
- BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+ /* The +1 is for the readonly IDT: */
+ BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
+ BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
start = CPU_ENTRY_AREA_BASE;
