| Message ID | 20250215012032.1206409-2-seanjc@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | x86: Bump per-CPU stack/data to 12KiB | expand |
diff --git a/x86/cstart.S b/x86/cstart.S index ceee58f9..df3458fe 100644 --- a/x86/cstart.S +++ b/x86/cstart.S @@ -8,9 +8,8 @@ ipi_vector = 0x20 max_cpus = MAX_TEST_CPUS .bss - +.align 4096 . = . + 4096 * max_cpus - .align 16 stacktop: .data diff --git a/x86/cstart64.S b/x86/cstart64.S index 4dff1102..bafb2017 100644 --- a/x86/cstart64.S +++ b/x86/cstart64.S @@ -6,9 +6,8 @@ ipi_vector = 0x20 max_cpus = MAX_TEST_CPUS .bss - +.align 4096 . = . + 4096 * max_cpus - .align 16 stacktop: .data
Align the per-CPU stacks, and by extension, the per-CPU data area to page boundaries so that when things go sideways, it's at least somewhat obvious that a test overran its stack. E.g. as is, stacks often start at the *bottom* of a page, and so it looks like they're always broken because they immediately split a page. Signed-off-by: Sean Christopherson <seanjc@google.com> --- x86/cstart.S | 3 +-- x86/cstart64.S | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-)