Change Details

Using per-CPU and per-thread trampolines is expensive and error-prone, since we're rewriting the same memory blocks constantly. Per-probe trampolines solve this problem by giving each probe its own block of executable memory, which more or less remains the same after the initial write. What this patch does, is get rid of the initialization code which allocates a trampoline for each thread. Each port of kinst will eventually retire kinst_md_init() and kinst_md_deinit(), as those functions are only used to allocate the per-CPU trampolines, and will instead allocate a trampoline for each new probe created. This change is not currently supported on amd64, as the amd64 port needs further changes to work, so this is a temporary/gradual patch to fix the riscv and arm64 ports.

Using per-CPU and per-thread trampolines is expensive and error-prone, since we're rewriting the same memory blocks constantly. Per-probe trampolines solve this problem by giving each probe its own block of executable memory, which more or less remains the same after the initial write. What this patch does, is get rid of the initialization code which allocates a trampoline for each thread, and instead let each port of kinst allocate a trampoline for each new probe created. It also sets up the infrastructure needed to support the new trampoline scheme. This change is not currently supported on amd64, as the amd64 port needs further changes to work, so this is a temporary/gradual patch to fix the riscv and arm64 ports.

Using per-CPU and per-thread trampolines is expensive and error-prone, since we're rewriting the same memory blocks constantly. Per-probe trampolines solve this problem by giving each probe its own block of executable memory, which more or less remains the same after the initial write. What this patch does, is get rid of the initialization code which allocates a trampoline for each thread., Each port of kinst willand instead let each port of eventually retire kinst_md_init() and kinst_md_deinit(),kinst allocate a trampoline for each new probe created. as thoseIt also sets up functions are only used to allocate the per-CPU trampolines, and will instead allocate athe infrastructure needed to support the new trampoline for each new probe createdscheme. This change is not currently supported on amd64, as the amd64 port needs further changes to work, so this is a temporary/gradual patch to fix the riscv and arm64 ports.