From: Nicholas Piggin Date: Fri, 22 Dec 2017 11:17:12 +0000 (+1000) Subject: powerpc/pseries: lift RTAS limit for hash X-Git-Tag: v4.16-rc1~93^2~122 X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=commitdiff_plain;h=c610d65c0ad00f1b7bfe2f1eb8f867ca74741685;p=linux.git powerpc/pseries: lift RTAS limit for hash With the previous patch to switch to 64-bit mode after returning from RTAS and before doing any memory accesses, the RMA limit need not be clamped to 1GB to avoid RTAS bugs. Keep the 1GB limit for older firmware (although this is more of a kernel concern than RTAS), and remove it starting with POWER9. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index a386bd854b1c..64e704eefad1 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1853,11 +1853,13 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, * non-virtualized 64-bit hash MMU systems don't have a limitation * on real mode access. * - * We also clamp it to 1G to avoid some funky things - * such as RTAS bugs etc... + * For guests on platforms before POWER9, we clamp the it limit to 1G + * to avoid some funky things such as RTAS bugs etc... */ if (!early_cpu_has_feature(CPU_FTR_HVMODE)) { - ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000); + ppc64_rma_size = first_memblock_size; + if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) + ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000); /* Finally limit subsequent allocations */ memblock_set_current_limit(ppc64_rma_size);