x86/entry: Use the correct fence macro after swapgs in kernel CR3
authorLai Jiangshan <laijs@linux.alibaba.com>
Fri, 26 Nov 2021 10:11:22 +0000 (18:11 +0800)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 8 Dec 2021 08:04:54 +0000 (09:04 +0100)
commit308cc9668d7ca2e549e0331a21e8814310a14d15
treee348f23c07812255c64efd7e3160c4b962b03718
parentefc5d7be3eb0c63884ca2d620824625e00d2a218
x86/entry: Use the correct fence macro after swapgs in kernel CR3

[ Upstream commit 1367afaa2ee90d1c956dfc224e199fcb3ff3f8cc ]

The commit

  c75890700455 ("x86/entry/64: Remove unneeded kernel CR3 switching")

removed a CR3 write in the faulting path of load_gs_index().

But the path's FENCE_SWAPGS_USER_ENTRY has no fence operation if PTI is
enabled, see spectre_v1_select_mitigation().

Rather, it depended on the serializing CR3 write of SWITCH_TO_KERNEL_CR3
and since it got removed, add a FENCE_SWAPGS_KERNEL_ENTRY call to make
sure speculation is blocked.

 [ bp: Massage commit message and comment. ]

Fixes: c75890700455 ("x86/entry/64: Remove unneeded kernel CR3 switching")
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211126101209.8613-3-jiangshanlai@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
arch/x86/entry/entry_64.S