Messages in this thread | | | Date | Thu, 23 Jun 2022 22:23:39 +0800 | Subject | Re: [PATCH 5/5] arm64: kdump: Don't defer the reservation of crash high memory | From | Kefeng Wang <> |
| |
On 2022/6/23 18:27, Catalin Marinas wrote: > On Wed, Jun 22, 2022 at 08:03:21PM +0800, Kefeng Wang wrote: >> On 2022/6/22 2:04, Catalin Marinas wrote: >>> On Tue, Jun 21, 2022 at 02:24:01PM +0800, Kefeng Wang wrote: >>>> On 2022/6/21 13:33, Baoquan He wrote: >>>>> On 06/13/22 at 04:09pm, Zhen Lei wrote: >>>>>> If the crashkernel has both high memory above DMA zones and low memory >>>>>> in DMA zones, kexec always loads the content such as Image and dtb to the >>>>>> high memory instead of the low memory. This means that only high memory >>>>>> requires write protection based on page-level mapping. The allocation of >>>>>> high memory does not depend on the DMA boundary. So we can reserve the >>>>>> high memory first even if the crashkernel reservation is deferred. >>>>>> >>>>>> This means that the block mapping can still be performed on other kernel >>>>>> linear address spaces, the TLB miss rate can be reduced and the system >>>>>> performance will be improved. >>>>> Ugh, this looks a little ugly, honestly. >>>>> >>>>> If that's for sure arm64 can't split large page mapping of linear >>>>> region, this patch is one way to optimize linear mapping. Given kdump >>>>> setting is necessary on arm64 server, the booting speed is truly >>>>> impacted heavily. >>>> Is there some conclusion or discussion that arm64 can't split large page >>>> mapping? >>>> >>>> Could the crashkernel reservation (and Kfence pool) be splited dynamically? >>>> >>>> I found Mark replay "arm64: remove page granularity limitation from >>>> KFENCE"[1], >>>> >>>> "We also avoid live changes from block<->table mappings, since the >>>> archtitecture gives us very weak guarantees there and generally requires >>>> a Break-Before-Make sequence (though IIRC this was tightened up >>>> somewhat, so maybe going one way is supposed to work). Unless it's >>>> really necessary, I'd rather not split these block mappings while >>>> they're live." >>> The problem with splitting is that you can end up with two entries in >>> the TLB for the same VA->PA mapping (e.g. one for a 4KB page and another >>> for a 2MB block). In the lucky case, the CPU will trigger a TLB conflict >>> abort (but can be worse like loss of coherency). >> Thanks for your explanation, >>> Prior to FEAT_BBM (added in ARMv8.4), such scenario was not allowed at >>> all, the software would have to unmap the range, TLBI, remap. With >>> FEAT_BBM (level 2), we can do this without tearing the mapping down but >>> we still need to handle the potential TLB conflict abort. The handler >>> only needs a TLBI but if it touches the memory range being changed it >>> risks faulting again. With vmap stacks and the kernel image mapped in >>> the vmalloc space, we have a small window where this could be handled >>> but we probably can't go into the C part of the exception handling >>> (tracing etc. may access a kmalloc'ed object for example). >> So if without FEAT_BBM,we can only guarantee BBM sequence via >> "unmap the range, TLBI, remap" or the following option, > Yes, that's the break-before-make sequence. > >> and with FEAT_BBM (level 2), we could have easy way to avoid TLB >> conflict for some vmalloc space, but still hard to deal with other >> scence? > It's not too hard in theory. Basically there's a small risk of getting a > TLB conflict abort for the mappings you change without a BBM sequence (I > think it's nearly non-existed when going from large block to smaller > pages, though the architecture states that it's still possible). Since > we only want to do this for the linear map and the kernel and stack are > in the vmalloc space, we can handle such trap as an safety measure (it > just needs a TLBI). It may help to tweak a model to force it to generate > such conflict aborts, otherwise we'd not be able to test the code. > > It's possible that such trap is raised at EL2 if a guest caused the > conflict abort (the architecture left this as IMP DEF). The hypervisors > may need to be taught to do a TLBI VMALLS12E1 instead of killing the > guest. I haven't checked what KVM does. Got it,many thanks.
| |