[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v5 1/4] xen/riscv: add VM space layout
- To: Oleksii <oleksii.kurochko@xxxxxxxxx>
- From: Jan Beulich <jbeulich@xxxxxxxx>
- Date: Tue, 2 May 2023 08:09:36 +0200
- Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=suse.com; dmarc=pass action=none header.from=suse.com; dkim=pass header.d=suse.com; arc=none
- Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=PdlqNXxo5ZGgTvs/sF34dAjMHKHhoq8d9qTIJr7mB+4=; b=jIMF5SR1qM4S1N5pJbjHNNZIxHY0zTj57AxOUI7Oc07T0njG8Ssx6zlrrVvdDngb2EO0HjpLy5NtA9pcEyXVYprVCj4AHNjyuw4/gyjB9SdX/vPip/fhCe2XChTcy5fuSc+ebNH2eFHEHgiuVKVDsCPu0XZJE8K0dkG1J793MGh04AcKg1FWk4GoSROcbZQ8tR5zWegZKD1VpQatsipAJli4vtIREHzGq38pvtc1gGAlqBjKizH1RUyhdAzB3gt1JjL0UtnpS4Ww2oSSwdBKhgP4qtKLW8nBDKvW6aABGFhy0hF4wWHWQQwhST/51GhOBX2TqVt6gv2IrAoiBUGDaA==
- Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=HpgS0IdSxkR6dJoK6CWdJbwlLbRN/cwMh37o44u/t5+p4fDHfW8BrOc3XdFDHv1QQPlAO5tA1NgkXHaVk9nPXvlNy4WzIe+us1vsUBjHd1fle6HtwV9qbIHGnujBKBY+Q7ZV5aPmJSxJ3VYTpjG+jOAbHox5JcmQ/KOga4qLgLEHVjZmANM/4uLyCdtn32sNMWNHA2HyeVlvoVxA5Y65wnjhDDOey469tbBFHyOTdRsh3TlkKckYE9STJsScbucAl70gRYFVrDMFF8fl3MkySn/9s6fCk9ZYo85DMh35kB4iTTN4JZjZy2RZGWBrc8Mls44xKc3h8Qa6oG8jxL76Zg==
- Authentication-results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=suse.com;
- Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>, Gianluca Guida <gianluca@xxxxxxxxxxxx>, Bob Eshleman <bobbyeshleman@xxxxxxxxx>, Alistair Francis <alistair.francis@xxxxxxx>, Connor Davis <connojdavis@xxxxxxxxx>, xen-devel@xxxxxxxxxxxxxxxxxxxx, Stefano Stabellini <sstabellini@xxxxxxxxxx>, Julien Grall <julien@xxxxxxx>
- Delivery-date: Tue, 02 May 2023 06:09:45 +0000
- List-id: Xen developer discussion <xen-devel.lists.xenproject.org>
On 29.04.2023 12:05, Oleksii wrote:
>>>> For
>>>> RISC-V, I would recommend to make sure the struct page_info will
>>>> never
>>>> cross a cache boundary.
> Do you mean that size(struct page_info) <= cache line size?
I don't think that's what was meant. Instead I expect the goal is for no
struct page_info instance to ever cross a cache line boundary. IOW one
of sizeof(struct page_info) % cachelinesize == 0 or
cachelinesize % sizeof(struct page_info) == 0, or in yet different terms
(with the expectation that cache lines are always a power of two in size)
sizeof(struct page_info) == 2**n. Yet unless you're able to fit everything
in 32 bytes, that'll mean more overhead than strictly necessary.
Jan
|
