summaryrefslogtreecommitdiff
path: root/arch/sparc
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-04-28 05:42:02 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-04-28 05:42:02 +0300
commit7fa8a8ee9400fe8ec188426e40e481717bc5e924 (patch)
treecc8fd6b4f936ec01e73238643757451e20478c07 /arch/sparc
parent91ec4b0d11fe115581ce2835300558802ce55e6c (diff)
parent4d4b6d66db63ceed399f1fb1a4b24081d2590eb1 (diff)
downloadlinux-7fa8a8ee9400fe8ec188426e40e481717bc5e924.tar.xz
Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of switching from a user process to a kernel thread. - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj Raghav. - zsmalloc performance improvements from Sergey Senozhatsky. - Yue Zhao has found and fixed some data race issues around the alteration of memcg userspace tunables. - VFS rationalizations from Christoph Hellwig: - removal of most of the callers of write_one_page() - make __filemap_get_folio()'s return value more useful - Luis Chamberlain has changed tmpfs so it no longer requires swap backing. Use `mount -o noswap'. - Qi Zheng has made the slab shrinkers operate locklessly, providing some scalability benefits. - Keith Busch has improved dmapool's performance, making part of its operations O(1) rather than O(n). - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd, permitting userspace to wr-protect anon memory unpopulated ptes. - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive rather than exclusive, and has fixed a bunch of errors which were caused by its unintuitive meaning. - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature, which causes minor faults to install a write-protected pte. - Vlastimil Babka has done some maintenance work on vma_merge(): cleanups to the kernel code and improvements to our userspace test harness. - Cleanups to do_fault_around() by Lorenzo Stoakes. - Mike Rapoport has moved a lot of initialization code out of various mm/ files and into mm/mm_init.c. - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for DRM, but DRM doesn't use it any more. - Lorenzo has also coverted read_kcore() and vread() to use iterators and has thereby removed the use of bounce buffers in some cases. - Lorenzo has also contributed further cleanups of vma_merge(). - Chaitanya Prakash provides some fixes to the mmap selftesting code. - Matthew Wilcox changes xfs and afs so they no longer take sleeping locks in ->map_page(), a step towards RCUification of pagefaults. - Suren Baghdasaryan has improved mmap_lock scalability by switching to per-VMA locking. - Frederic Weisbecker has reworked the percpu cache draining so that it no longer causes latency glitches on cpu isolated workloads. - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig logic. - Liu Shixin has changed zswap's initialization so we no longer waste a chunk of memory if zswap is not being used. - Yosry Ahmed has improved the performance of memcg statistics flushing. - David Stevens has fixed several issues involving khugepaged, userfaultfd and shmem. - Christoph Hellwig has provided some cleanup work to zram's IO-related code paths. - David Hildenbrand has fixed up some issues in the selftest code's testing of our pte state changing. - Pankaj Raghav has made page_endio() unneeded and has removed it. - Peter Xu contributed some rationalizations of the userfaultfd selftests. - Yosry Ahmed has fixed an issue around memcg's page recalim accounting. - Chaitanya Prakash has fixed some arm-related issues in the selftests/mm code. - Longlong Xia has improved the way in which KSM handles hwpoisoned pages. - Peter Xu fixes a few issues with uffd-wp at fork() time. - Stefan Roesch has changed KSM so that it may now be used on a per-process and per-cgroup basis. * tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits) mm,unmap: avoid flushing TLB in batch if PTE is inaccessible shmem: restrict noswap option to initial user namespace mm/khugepaged: fix conflicting mods to collapse_file() sparse: remove unnecessary 0 values from rc mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area() hugetlb: pte_alloc_huge() to replace huge pte_alloc_map() maple_tree: fix allocation in mas_sparse_area() mm: do not increment pgfault stats when page fault handler retries zsmalloc: allow only one active pool compaction context selftests/mm: add new selftests for KSM mm: add new KSM process and sysfs knobs mm: add new api to enable ksm per process mm: shrinkers: fix debugfs file permissions mm: don't check VMA write permissions if the PTE/PMD indicates write permissions migrate_pages_batch: fix statistics for longterm pin retry userfaultfd: use helper function range_in_vma() lib/show_mem.c: use for_each_populated_zone() simplify code mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list() fs/buffer: convert create_page_buffers to folio_create_buffers fs/buffer: add folio_create_empty_buffers helper ...
Diffstat (limited to 'arch/sparc')
-rw-r--r--arch/sparc/Kconfig21
-rw-r--r--arch/sparc/include/asm/pgtable_64.h116
-rw-r--r--arch/sparc/kernel/pci_sun4v.c2
-rw-r--r--arch/sparc/kernel/traps_64.c2
-rw-r--r--arch/sparc/mm/tsb.c4
5 files changed, 80 insertions, 65 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index d4c1d96f85cd..8535e19062f6 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -271,18 +271,17 @@ config ARCH_SPARSEMEM_DEFAULT
def_bool y if SPARC64
config ARCH_FORCE_MAX_ORDER
- int "Maximum zone order"
- default "13"
+ int "Order of maximal physically contiguous allocations"
+ default "12"
help
- The kernel memory allocator divides physically contiguous memory
- blocks into "zones", where each zone is a power of two number of
- pages. This option selects the largest power of two that the kernel
- keeps in the memory allocator. If you need to allocate very large
- blocks of physically contiguous memory, then you may need to
- increase this value.
-
- This config option is actually maximum order plus one. For example,
- a value of 13 means that the largest free memory block is 2^12 pages.
+ The kernel page allocator limits the size of maximal physically
+ contiguous allocations. The limit is called MAX_ORDER and it
+ defines the maximal power of two of number of pages that can be
+ allocated as a single contiguous block. This option allows
+ overriding the default setting when ability to allocate very
+ large blocks of physically contiguous memory is required.
+
+ Don't change if unsure.
if SPARC64 || COMPILE_TEST
source "kernel/power/Kconfig"
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 2dc8d4641734..5563efa1a19f 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -357,6 +357,42 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
*/
#define pgprot_noncached pgprot_noncached
+static inline unsigned long pte_dirty(pte_t pte)
+{
+ unsigned long mask;
+
+ __asm__ __volatile__(
+ "\n661: mov %1, %0\n"
+ " nop\n"
+ " .section .sun4v_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " sethi %%uhi(%2), %0\n"
+ " sllx %0, 32, %0\n"
+ " .previous\n"
+ : "=r" (mask)
+ : "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V));
+
+ return (pte_val(pte) & mask);
+}
+
+static inline unsigned long pte_write(pte_t pte)
+{
+ unsigned long mask;
+
+ __asm__ __volatile__(
+ "\n661: mov %1, %0\n"
+ " nop\n"
+ " .section .sun4v_2insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " sethi %%uhi(%2), %0\n"
+ " sllx %0, 32, %0\n"
+ " .previous\n"
+ : "=r" (mask)
+ : "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V));
+
+ return (pte_val(pte) & mask);
+}
+
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
#define arch_make_huge_pte arch_make_huge_pte
@@ -418,28 +454,43 @@ static inline bool is_hugetlb_pte(pte_t pte)
}
#endif
+static inline pte_t __pte_mkhwwrite(pte_t pte)
+{
+ unsigned long val = pte_val(pte);
+
+ /*
+ * Note: we only want to set the HW writable bit if the SW writable bit
+ * and the SW dirty bit are set.
+ */
+ __asm__ __volatile__(
+ "\n661: or %0, %2, %0\n"
+ " .section .sun4v_1insn_patch, \"ax\"\n"
+ " .word 661b\n"
+ " or %0, %3, %0\n"
+ " .previous\n"
+ : "=r" (val)
+ : "0" (val), "i" (_PAGE_W_4U), "i" (_PAGE_W_4V));
+
+ return __pte(val);
+}
+
static inline pte_t pte_mkdirty(pte_t pte)
{
- unsigned long val = pte_val(pte), tmp;
+ unsigned long val = pte_val(pte), mask;
__asm__ __volatile__(
- "\n661: or %0, %3, %0\n"
- " nop\n"
- "\n662: nop\n"
+ "\n661: mov %1, %0\n"
" nop\n"
" .section .sun4v_2insn_patch, \"ax\"\n"
" .word 661b\n"
- " sethi %%uhi(%4), %1\n"
- " sllx %1, 32, %1\n"
- " .word 662b\n"
- " or %1, %%lo(%4), %1\n"
- " or %0, %1, %0\n"
+ " sethi %%uhi(%2), %0\n"
+ " sllx %0, 32, %0\n"
" .previous\n"
- : "=r" (val), "=r" (tmp)
- : "0" (val), "i" (_PAGE_MODIFIED_4U | _PAGE_W_4U),
- "i" (_PAGE_MODIFIED_4V | _PAGE_W_4V));
+ : "=r" (mask)
+ : "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V));
- return __pte(val);
+ pte = __pte(val | mask);
+ return pte_write(pte) ? __pte_mkhwwrite(pte) : pte;
}
static inline pte_t pte_mkclean(pte_t pte)
@@ -481,7 +532,8 @@ static inline pte_t pte_mkwrite(pte_t pte)
: "=r" (mask)
: "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V));
- return __pte(val | mask);
+ pte = __pte(val | mask);
+ return pte_dirty(pte) ? __pte_mkhwwrite(pte) : pte;
}
static inline pte_t pte_wrprotect(pte_t pte)
@@ -584,42 +636,6 @@ static inline unsigned long pte_young(pte_t pte)
return (pte_val(pte) & mask);
}
-static inline unsigned long pte_dirty(pte_t pte)
-{
- unsigned long mask;
-
- __asm__ __volatile__(
- "\n661: mov %1, %0\n"
- " nop\n"
- " .section .sun4v_2insn_patch, \"ax\"\n"
- " .word 661b\n"
- " sethi %%uhi(%2), %0\n"
- " sllx %0, 32, %0\n"
- " .previous\n"
- : "=r" (mask)
- : "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V));
-
- return (pte_val(pte) & mask);
-}
-
-static inline unsigned long pte_write(pte_t pte)
-{
- unsigned long mask;
-
- __asm__ __volatile__(
- "\n661: mov %1, %0\n"
- " nop\n"
- " .section .sun4v_2insn_patch, \"ax\"\n"
- " .word 661b\n"
- " sethi %%uhi(%2), %0\n"
- " sllx %0, 32, %0\n"
- " .previous\n"
- : "=r" (mask)
- : "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V));
-
- return (pte_val(pte) & mask);
-}
-
static inline unsigned long pte_exec(pte_t pte)
{
unsigned long mask;
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 384480971805..7d91ca6aa675 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -193,7 +193,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
size = IO_PAGE_ALIGN(size);
order = get_order(size);
- if (unlikely(order >= MAX_ORDER))
+ if (unlikely(order > MAX_ORDER))
return NULL;
npages = size >> IO_PAGE_SHIFT;
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 5b4de4a89dec..08ffd17d5ec3 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -897,7 +897,7 @@ void __init cheetah_ecache_flush_init(void)
/* Now allocate error trap reporting scoreboard. */
sz = NR_CPUS * (2 * sizeof(struct cheetah_err_info));
- for (order = 0; order < MAX_ORDER; order++) {
+ for (order = 0; order <= MAX_ORDER; order++) {
if ((PAGE_SIZE << order) >= sz)
break;
}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 912205787161..5e2931a18409 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -402,8 +402,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
unsigned long new_rss_limit;
gfp_t gfp_flags;
- if (max_tsb_size > (PAGE_SIZE << MAX_ORDER))
- max_tsb_size = (PAGE_SIZE << MAX_ORDER);
+ if (max_tsb_size > PAGE_SIZE << MAX_ORDER)
+ max_tsb_size = PAGE_SIZE << MAX_ORDER;
new_cache_index = 0;
for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) {