Re: [PATCH 0/2] i440fx chipset and larger system memory totals
Michael Kelly <[email protected]>
| Newsgroups | gmane.os.hurd.bugs |
|---|---|
| Message-ID | <[email protected]> |
Hi Damien, On 13/08/2026 09:04, Damien Zammit wrote: >> How does NetBSD guarantee that memory pages are allocated from > appropriate memory segments for geteblk(), rump_sys_pread() and > rump_sys_pwrite() ? > > Doesn't the caller of rump_sys_* allocate the memory? > Not sure about geteblk. Yes indeed that is the case. Hurd does so by passing the memory buffer pointer to those functions but I don't know where NetBSD would do the equivalent. Perhaps that's in a NetBSD libc or in NetBSD kernel space, but wherever it is, the same restriction on the memory for that pointer must also apply. Possibly I need to reword that part to make sure there's no misunderstanding. Mike.