]>
Commit | Line | Data |
---|---|---|
ffd06e02 YS |
1 | Spin table in cache |
2 | ===================================== | |
3 | As specified by ePAPR v1.1, the spin table needs to be in cached memory. After | |
a187559e | 4 | DDR is initialized and U-Boot relocates itself into DDR, the spin table is |
ffd06e02 YS |
5 | accessible for core 0. It is part of release.S, within 4KB range after |
6 | __secondary_start_page. For other cores to use the spin table, the booting | |
7 | process is described below: | |
8 | ||
9 | Core 0 sets up the reset page on the top 4K of memory (or 4GB if total memory | |
10 | is more than 4GB), and creates a TLB to map it to 0xffff_f000, regardless of | |
11 | the physical address of this page, with WIMGE=0b01010. Core 0 also enables boot | |
12 | page translation for secondary cores to use this page of memory. Then 4KB | |
13 | memory is copied from __secondary_start_page to the boot page, after flusing | |
14 | cache because this page is mapped as normal DDR. Before copying the reset page, | |
15 | core 0 puts the physical address of the spin table (which is in release.S and | |
16 | relocated to the top of mapped memory) into a variable __spin_table_addr so | |
17 | that secondary cores can see it. | |
18 | ||
19 | When secondary cores boot up from 0xffff_f000 page, they only have one default | |
20 | TLB. While booting, they set up another TLB in AS=1 space and jump into | |
21 | the new space. The new TLB covers the physical address of the spin table page, | |
22 | with WIMGE =0b00100. Now secondary cores can keep polling the spin table | |
23 | without stress DDR bus because both the code and the spin table is in cache. | |
24 | ||
25 | For the above to work, DDR has to set the 'M' bit of WIMGE, in order to keep | |
26 | cache coherence. |