summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2019-12-01 17:49:47 +0300
committerIngo Molnar <mingo@kernel.org>2019-12-01 22:57:25 +0300
commit91298f1a302dad0f0f630413c812818636faa8a0 (patch)
tree9c3f5db005a45301d21a6377ea9158ec8d3731b9 /arch
parent7b0b8cfd261c569177d64d6e9b1800fbe412fd65 (diff)
downloadlinux-91298f1a302dad0f0f630413c812818636faa8a0.tar.xz
x86/mm/pat: Fix off-by-one bugs in interval tree search
There's a bug in the new PAT code, the conversion of memtype_check_conflict() is buggy: 8d04a5f97a5f: ("x86/mm/pat: Convert the PAT tree to a generic interval tree") dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end); found_type = match->type; - node = rb_next(&match->rb); - while (node) { - match = rb_entry(node, struct memtype, rb); - - if (match->start >= end) /* Checked all possible matches */ - goto success; - - if (is_node_overlap(match, start, end) && - match->type != found_type) { + match = memtype_interval_iter_next(match, start, end); + while (match) { + if (match->type != found_type) goto failure; - } - node = rb_next(&match->rb); + match = memtype_interval_iter_next(match, start, end); } Note how the '>= end' condition to end the interval check, got converted into: + match = memtype_interval_iter_next(match, start, end); This is subtly off by one, because the interval trees interfaces require closed interval parameters: include/linux/interval_tree_generic.h /* \ * Iterate over intervals intersecting [start;last] \ * \ * Note that a node's interval intersects [start;last] iff: \ * Cond1: ITSTART(node) <= last \ * and \ * Cond2: start <= ITLAST(node) \ */ \ ... if (ITSTART(node) <= last) { /* Cond1 */ \ if (start <= ITLAST(node)) /* Cond2 */ \ return node; /* node is leftmost match */ \ [start;last] is a closed interval (note that '<= last' check) - while the PAT 'end' parameter is 1 byte beyond the end of the range, because ioremap() and the other mapping APIs usually use the [start,end) half-open interval, derived from 'size'. This is what ioremap() does for example: /* * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; phys_addr &= PHYSICAL_PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; retval = reserve_memtype(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); phys_addr+size will be on a page boundary, after the last byte of the mapped interval. So the correct parameter to use in the interval tree searches is not 'end' but 'end-1'. This could have relevance if conflicting PAT ranges are exactly adjacent, for example a future WC region is followed immediately by an already mapped UC- region - in this case memtype_check_conflict() would incorrectly deny the WC memtype region and downgrade the memtype to UC-. BTW., rather annoyingly this downgrading is done silently in memtype_check_insert(): int memtype_check_insert(struct memtype *new, enum page_cache_mode *ret_type) { int err = 0; err = memtype_check_conflict(new->start, new->end, new->type, ret_type); if (err) return err; if (ret_type) new->type = *ret_type; memtype_interval_insert(new, &memtype_rbroot); return 0; } So on such a conflict we'd just silently get UC- in *ret_type, and write it into the new region, never the wiser ... So assuming that the patch below fixes the primary bug the diagnostics side of ioremap() cache attribute downgrades would be another thing to fix. Anyway, I checked all the interval-tree iterations, and most of them are off by one - but I think the one related to memtype_check_conflict() is the one causing this particular performance regression. The only correct interval-tree searches were these two: arch/x86/mm/pat_interval.c: match = memtype_interval_iter_first(&memtype_rbroot, 0, ULONG_MAX); arch/x86/mm/pat_interval.c: match = memtype_interval_iter_next(match, 0, ULONG_MAX); The ULONG_MAX was hiding the off-by-one in plain sight. :-) Note that the bug was probably benign in the sense of implementing a too strict cache attribute conflict policy and downgrading cache attributes, so AFAICS the worst outcome of this bug would be a performance regression, not any instabilities. Reported-by: kernel test robot <rong.a.chen@intel.com> Reported-by: Kenneth R. Crudup <kenny@panix.com> Reported-by: Mariusz Ceier <mceier+kernel@gmail.com> Tested-by: Mariusz Ceier <mceier@gmail.com> Tested-by: Kenneth R. Crudup <kenny@panix.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20191201144947.GA4167@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/mm/pat_interval.c12
1 files changed, 6 insertions, 6 deletions
diff --git a/arch/x86/mm/pat_interval.c b/arch/x86/mm/pat_interval.c
index 47a1bf30748f..6855362eaf21 100644
--- a/arch/x86/mm/pat_interval.c
+++ b/arch/x86/mm/pat_interval.c
@@ -56,7 +56,7 @@ static struct memtype *memtype_match(u64 start, u64 end, int match_type)
{
struct memtype *match;
- match = memtype_interval_iter_first(&memtype_rbroot, start, end);
+ match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
while (match != NULL && match->start < end) {
if ((match_type == MEMTYPE_EXACT_MATCH) &&
(match->start == start) && (match->end == end))
@@ -66,7 +66,7 @@ static struct memtype *memtype_match(u64 start, u64 end, int match_type)
(match->start < start) && (match->end == end))
return match;
- match = memtype_interval_iter_next(match, start, end);
+ match = memtype_interval_iter_next(match, start, end-1);
}
return NULL; /* Returns NULL if there is no match */
@@ -79,7 +79,7 @@ static int memtype_check_conflict(u64 start, u64 end,
struct memtype *match;
enum page_cache_mode found_type = reqtype;
- match = memtype_interval_iter_first(&memtype_rbroot, start, end);
+ match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
if (match == NULL)
goto success;
@@ -89,12 +89,12 @@ static int memtype_check_conflict(u64 start, u64 end,
dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
found_type = match->type;
- match = memtype_interval_iter_next(match, start, end);
+ match = memtype_interval_iter_next(match, start, end-1);
while (match) {
if (match->type != found_type)
goto failure;
- match = memtype_interval_iter_next(match, start, end);
+ match = memtype_interval_iter_next(match, start, end-1);
}
success:
if (newtype)
@@ -160,7 +160,7 @@ struct memtype *memtype_erase(u64 start, u64 end)
struct memtype *memtype_lookup(u64 addr)
{
return memtype_interval_iter_first(&memtype_rbroot, addr,
- addr + PAGE_SIZE);
+ addr + PAGE_SIZE-1);
}
#if defined(CONFIG_DEBUG_FS)