Commit bdbf649e authored Sep 28, 2018 by Alexey Kardashevskiy Committed by Michael Ellerman Dec 20, 2018

powerpc/powernv/ioda: Allocate indirect TCE levels of cached userspace addresses on demand



The powernv platform maintains 2 TCE tables for VFIO - a hardware TCE
table and a table with userspace addresses; the latter is used for
marking pages dirty when corresponging TCEs are unmapped from
the hardware table.

a68bd126 ("powerpc/powernv/ioda: Allocate indirect TCE levels
on demand") enabled on-demand allocation of the hardware table,
however it missed the other table so it has still been fully allocated
at the boot time. This fixes the issue by allocating a single level,
just like we do for the hardware table.

Fixes: a68bd126 ("powerpc/powernv/ioda: Allocate indirect TCE levels on demand")
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

parent 8c6c942d

arch/powerpc/platforms/powernv/pci-ioda-tce.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -299,7 +299,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
		if (alloc_userspace_copy) {
		offset = 0;
		uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
		levels, tce_table_size, &offset,
		tmplevels, tce_table_size, &offset,
		&total_allocated_uas);
		if (!uas)
		goto free_tces_exit;