On Thu, 04 Jan 2024 13:27:07 -0600, Dave Hansen <dave.hansen@xxxxxxxxx>
wrote:
On 1/4/24 11:11, Haitao Huang wrote:
If those are OK with users and also make it acceptable for merge
quickly, I'm happy to do that 🙂
How about we put some actual numbers behind this? How much complexity
are we talking about here? What's the diffstat for the utterly
bare-bones implementation and what does it cost on top of that to do the
per-cgroup reclaim?
For bare-bone:
arch/x86/Kconfig | 13 ++++++++++++
arch/x86/kernel/cpu/sgx/Makefile | 1 +
arch/x86/kernel/cpu/sgx/epc_cgroup.c | 104
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/sgx/epc_cgroup.h | 39
+++++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/sgx/main.c | 41
++++++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/sgx/sgx.h | 5 +++++
include/linux/misc_cgroup.h | 42
+++++++++++++++++++++++++++++++++++++
kernel/cgroup/misc.c | 52
+++++++++++++++++++++++++++++++---------------
8 files changed, 281 insertions(+), 16 deletions(-)
Additional for per-cgroup reclaim:
arch/x86/kernel/cpu/sgx/encl.c | 41 +++++++++--------
arch/x86/kernel/cpu/sgx/encl.h | 3 +-
arch/x86/kernel/cpu/sgx/epc_cgroup.c | 224
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
arch/x86/kernel/cpu/sgx/epc_cgroup.h | 18 ++++++--
arch/x86/kernel/cpu/sgx/main.c | 226
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------------------------------
arch/x86/kernel/cpu/sgx/sgx.h | 85
+++++++++++++++++++++++++++++++++--
6 files changed, 480 insertions(+), 117 deletions(-)
Thanks
Haitao
