| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 6 Jun 2022 20:37:09 +0000
From: Ankur Arora <ankur.a.arora@...cle.com>
To: linux-kernel@...r.kernel.org, linux-mm@...ck.org, x86@...nel.org
Cc: torvalds@...ux-foundation.org, akpm@...ux-foundation.org,
mike.kravetz@...cle.com, mingo@...nel.org, luto@...nel.org,
tglx@...utronix.de, bp@...en8.de, peterz@...radead.org,
ak@...ux.intel.com, arnd@...db.de, jgg@...dia.com,
jon.grimm@....com, boris.ostrovsky@...cle.com,
konrad.wilk@...cle.com, joao.m.martins@...cle.com,
ankur.a.arora@...cle.com
Subject: [PATCH v3 05/21] mm/huge_page: generalize process_huge_page()
process_huge_page() processes subpages left-right, narrowing towards
the direction of the faulting subpage to keep spatially close
cachelines hot.
This is done, however, page-at-a-time. Retain the left-right
narrowing logic while using larger chunks for page regions
farther away from the target, and smaller chunks approaching
the target.
Clearing in large chunks allows for uarch specific optimizations.
Do this, however, only for far away subpages because we don't
care about keeping those cachelines hot.
In addition, while narrowing towards the target, access both the
left and right chunks in the forward direction instead of the
reverse -- x86 string instructions perform better that way.
Signed-off-by: Ankur Arora <ankur.a.arora@...cle.com>
---
mm/memory.c | 86 +++++++++++++++++++++++++++++++++++++++--------------
1 file changed, 64 insertions(+), 22 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index fbc7bc70dc3d..04c6bb5d75f6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5592,8 +5592,10 @@ struct subpage_arg {
struct page *dst;
struct page *src;
struct vm_area_struct *vma;
+ int page_unit;
};
+#define NWIDTH 4
/*
* Process all subpages of the specified huge page with the specified
* operation. The target subpage will be processed last to keep its
@@ -5604,37 +5606,75 @@ static inline void process_huge_page(struct subpage_arg *sa,
void (*process_subpages)(struct subpage_arg *sa,
unsigned long base_addr, int lidx, int ridx))
{
- int i, n, base, l;
+ int n, lbound, rbound;
+ int remaining, unit = sa->page_unit;
unsigned long addr = addr_hint &
~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1);
+ lbound = 0;
+ rbound = pages_per_huge_page - 1;
+ remaining = pages_per_huge_page;
+
/* Process target subpage last to keep its cache lines hot */
n = (addr_hint - addr) / PAGE_SIZE;
- if (2 * n <= pages_per_huge_page) {
- /* If target subpage in first half of huge page */
- base = 0;
- l = n;
- /* Process subpages at the end of huge page */
- process_subpages(sa, addr, 2*n, pages_per_huge_page-1);
- } else {
- /* If target subpage in second half of huge page */
- base = pages_per_huge_page - 2 * (pages_per_huge_page - n);
- l = pages_per_huge_page - n;
-
- /* Process subpages at the begin of huge page */
- process_subpages(sa, addr, 0, base);
- }
/*
- * Process remaining subpages in left-right-left-right pattern
- * towards the target subpage
+ * Process subpages in a left-right-left-right pattern towards the
+ * faulting subpage to keep spatially close cachelines hot.
+ *
+ * If the architecture advertises multi-page clearing/copying, use
+ * the largest extent available, process it in the forward direction,
+ * while iteratively narrowing as the target gets closer.
+ *
+ * Clearing in large chunks allows for uarch specific optimizations.
+ * Do this, however, only for far away subpages because we don't
+ * care about keeping those cachelines hot.
+ *
+ * In addition, while narrowing towards the target, access both the
+ * left and right chunks in the forward direction instead of the
+ * reverse -- x86 string instructions perform better that way.
*/
- for (i = 0; i < l; i++) {
- int left_idx = base + i;
- int right_idx = base + 2 * l - 1 - i;
+ while (remaining) {
+ int left_gap = n - lbound;
+ int right_gap = rbound - n;
+ int neighbourhood;
- process_subpages(sa, addr, left_idx, left_idx);
- process_subpages(sa, addr, right_idx, right_idx);
+ /*
+ * We want to defer processing of the immediate neighbourhood of
+ * the target until rest of the huge-page is exhausted.
+ */
+ neighbourhood = NWIDTH * (left_gap > NWIDTH ||
+ right_gap > NWIDTH);
+
+ /*
+ * Width of the remaining region on the left: n - lbound + 1.
+ * In addition hold an additional neighbourhood region, which is
+ * non-zero until the left, right gaps have been cleared.
+ *
+ * [ddddd....xxxxN
+ * ^ | `---- target
+ * `---|-- lbound
+ * `------------ left neighbourhood edge
+ */
+ if ((n - lbound + 1) >= unit + neighbourhood) {
+ process_subpages(sa, addr, lbound, lbound + unit - 1);
+ lbound += unit;
+ remaining -= unit;
+ }
+
+ /*
+ * Similarly the right:
+ * Nxxxx....ddd]
+ */
+ if ((rbound - n) >= (unit + neighbourhood)) {
+ process_subpages(sa, addr, rbound - unit + 1, rbound);
+ rbound -= unit;
+ remaining -= unit;
+ }
+
+ unit = min(sa->page_unit, unit >> 1);
+ if (unit == 0)
+ unit = 1;
}
}
@@ -5687,6 +5727,7 @@ void clear_huge_page(struct page *page,
.dst = page,
.src = NULL,
.vma = NULL,
+ .page_unit = clear_page_unit,
};
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
@@ -5741,6 +5782,7 @@ void copy_user_huge_page(struct page *dst, struct page *src,
.dst = dst,
.src = src,
.vma = vma,
+ .page_unit = 1,
};
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
--
2.31.1
Powered by blists - more mailing lists