tjh.dev
Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
Documentation: x86: fix spelling mistakes
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
authored by
Eric Engestrom
and committed by
Jonathan Corbet
c8e84d2f
1248562b
+2
-2
+2
-2
Documentation/x86/intel_mpx.txt
+2
-2
Documentation/x86/intel_mpx.txt
···
136
136
If we were to preallocate them for the 128TB of user virtual address
137
137
space, we would need to reserve 512TB+2GB, which is larger than the
138
138
entire virtual address space today. This means they can not be reserved
139
-
ahead of time. Also, a single process's pre-popualated bounds directory
139
+
ahead of time. Also, a single process's pre-populated bounds directory
140
140
consumes 2GB of virtual *AND* physical memory. IOW, it's completely
141
141
infeasible to prepopulate bounds directories.
142
142
···
151
151
these calls.
152
152
153
153
Q: Could a bounds fault be handed to userspace and the tables allocated
154
-
there in a signal handler intead of in the kernel?
154
+
there in a signal handler instead of in the kernel?
155
155
A: mmap() is not on the list of safe async handler functions and even
156
156
if mmap() would work it still requires locking or nasty tricks to
157
157
keep track of the allocation state there.