diff options
author | Paul Mackerras <paulus@ozlabs.org> | 2016-09-02 07:20:43 (GMT) |
---|---|---|
committer | Paul Mackerras <paulus@ozlabs.org> | 2016-09-09 06:14:48 (GMT) |
commit | 0eeede0c63305a33de31bd90b53b023c1d452c17 (patch) | |
tree | 32ae6883786e58c5e9b6fc9886cf8cea9590da79 /arch/powerpc/mm/hash_utils_64.c | |
parent | 694d0d0bb2030d2e36df73e2d23d5770511dbc8d (diff) | |
download | linux-0eeede0c63305a33de31bd90b53b023c1d452c17.tar.xz |
powerpc/mm: Speed up computation of base and actual page size for a HPTE
This replaces a 2-D search through an array with a simple 8-bit table
lookup for determining the actual and/or base page size for a HPT entry.
The encoding in the second doubleword of the HPTE is designed to encode
the actual and base page sizes without using any more bits than would be
needed for a 4k page number, by using between 1 and 8 low-order bits of
the RPN (real page number) field to encode the page sizes. A single
"large page" bit in the first doubleword indicates that these low-order
bits are to be interpreted like this.
We can determine the page sizes by using the low-order 8 bits of the RPN
to look up a 256-entry table. For actual page sizes less than 1MB, some
of the upper bits of these 8 bits are going to be real address bits, but
we can cope with that by replicating the entries for those smaller page
sizes.
While we're at it, let's move the hpte_page_size() and hpte_base_page_size()
functions from a KVM-specific header to a header for 64-bit HPT systems,
since this computation doesn't have anything specifically to do with KVM.
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Diffstat (limited to 'arch/powerpc/mm/hash_utils_64.c')
-rw-r--r-- | arch/powerpc/mm/hash_utils_64.c | 55 |
1 files changed, 55 insertions, 0 deletions
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 0821556..ef3ae89 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -93,6 +93,9 @@ static unsigned long _SDR1; struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; EXPORT_SYMBOL_GPL(mmu_psize_defs); +u8 hpte_page_sizes[1 << LP_BITS]; +EXPORT_SYMBOL_GPL(hpte_page_sizes); + struct hash_pte *htab_address; unsigned long htab_size_bytes; unsigned long htab_hash_mask; @@ -564,8 +567,60 @@ static void __init htab_scan_page_sizes(void) #endif /* CONFIG_HUGETLB_PAGE */ } +/* + * Fill in the hpte_page_sizes[] array. + * We go through the mmu_psize_defs[] array looking for all the + * supported base/actual page size combinations. Each combination + * has a unique pagesize encoding (penc) value in the low bits of + * the LP field of the HPTE. For actual page sizes less than 1MB, + * some of the upper LP bits are used for RPN bits, meaning that + * we need to fill in several entries in hpte_page_sizes[]. + * + * In diagrammatic form, with r = RPN bits and z = page size bits: + * PTE LP actual page size + * rrrr rrrz >=8KB + * rrrr rrzz >=16KB + * rrrr rzzz >=32KB + * rrrr zzzz >=64KB + * ... + * + * The zzzz bits are implementation-specific but are chosen so that + * no encoding for a larger page size uses the same value in its + * low-order N bits as the encoding for the 2^(12+N) byte page size + * (if it exists). + */ +static void init_hpte_page_sizes(void) +{ + long int ap, bp; + long int shift, penc; + + for (bp = 0; bp < MMU_PAGE_COUNT; ++bp) { + if (!mmu_psize_defs[bp].shift) + continue; /* not a supported page size */ + for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) { + penc = mmu_psize_defs[bp].penc[ap]; + if (penc == -1) + continue; + shift = mmu_psize_defs[ap].shift - LP_SHIFT; + if (shift <= 0) + continue; /* should never happen */ + /* + * For page sizes less than 1MB, this loop + * replicates the entry for all possible values + * of the rrrr bits. + */ + while (penc < (1 << LP_BITS)) { + hpte_page_sizes[penc] = (ap << 4) | bp; + penc += 1 << shift; + } + } + } +} + static void __init htab_init_page_sizes(void) { + init_hpte_page_sizes(); + if (!debug_pagealloc_enabled()) { /* * Pick a size for the linear mapping. Currently, we only |