Commit-ID: 51c3fbd89d7554caa3290837604309f8d8669d99 Gitweb: https://git.kernel.org/tip/51c3fbd89d7554caa3290837604309f8d8669d99 Author: Dan Williams dan.j.williams@intel.com AuthorDate: Tue, 11 Dec 2018 07:49:39 -0800 Committer: Thomas Gleixner tglx@linutronix.de CommitDate: Tue, 11 Dec 2018 18:28:20 -0800
x86/mm: Fix decoy address handling vs 32-bit builds
A decoy address is used by set_mce_nospec() to update the cache attributes for a page that may contain poison (multi-bit ECC error) while attempting to minimize the possibility of triggering a speculative access to that page.
When reserve_memtype() is handling a decoy address it needs to convert it to its real physical alias. The conversion, AND'ing with __PHYSICAL_MASK, is broken for a 32-bit physical mask and reserve_memtype() is passed the last physical page. Gert reports triggering the:
BUG_ON(start >= end);
...assertion when running a 32-bit non-PAE build on a platform that has a driver resource at the top of physical memory:
BIOS-e820: [mem 0x00000000fff00000-0x00000000ffffffff] reserved
Given that the decoy address scheme is only targeted at 64-bit builds and assumes that the top of physical address space is free for use as a decoy address range, simply bypass address sanitization in the 32-bit case.
Lastly, there was no need to crash the system when this failure occurred, and no need to crash future systems if the assumptions of decoy addresses are ever violated. Change the BUG_ON() to a WARN() with an error return.
Fixes: 510ee090abc3 ("x86/mm/pat: Prepare {reserve, free}_memtype() for...") Reported-by: Gert Robben t2@gert.gr Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Gert Robben t2@gert.gr Cc: stable@vger.kernel.org Cc: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Dave Hansen dave.hansen@linux.intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Borislav Petkov bp@alien8.de Cc: "H. Peter Anvin" hpa@zytor.com Cc: platform-driver-x86@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/154454337985.789277.12133288391664677775.stgit@dwi...
--- arch/x86/mm/pat.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 08013524fba1..4fe956a63b25 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -519,8 +519,13 @@ static u64 sanitize_phys(u64 address) * for a "decoy" virtual address (bit 63 clear) passed to * set_memory_X(). __pa() on a "decoy" address results in a * physical address with bit 63 set. + * + * Decoy addresses are not present for 32-bit builds, see + * set_mce_nospec(). */ - return address & __PHYSICAL_MASK; + if (IS_ENABLED(CONFIG_X86_64)) + return address & __PHYSICAL_MASK; + return address; }
/* @@ -546,7 +551,11 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
start = sanitize_phys(start); end = sanitize_phys(end); - BUG_ON(start >= end); /* end is exclusive */ + if (start >= end) { + WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__, + start, end - 1, cattr_name(req_type)); + return -EINVAL; + }
if (!pat_enabled()) { /* This is identical to page table setting without PAT */