kernel.git/arch/s390/include/asm/pgtable.h, branch linux-6.19.y

Merge tag 's390-6.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

2025-12-03T00:37:00Z

Pull s390 updates from Heiko Carstens: - Provide a new interface for dynamic configuration and deconfiguration of hotplug memory, allowing with and without memmap_on_memory support. This makes the way memory hotplug is handled on s390 much more similar to other architectures - Remove compat support. There shouldn't be any compat user space around anymore, therefore get rid of a lot of code which also doesn't need to be tested anymore - Add stackprotector support. GCC 16 will get new compiler options, which allow to generate code required for kernel stackprotector support - Merge pai_crypto and pai_ext PMU drivers into a new driver. This removes a lot of duplicated code. The new driver is also extendable and allows to support new PMUs - Add driver override support for AP queues - Rework and extend zcrypt and AP trace events to allow for tracing of crypto requests - Support block sizes larger than 65535 bytes for CCW tape devices - Since the rework of the virtual kernel address space the module area and the kernel image are within the same 4GB area. This eliminates the need of weak per cpu variables. Get rid of ARCH_MODULE_NEEDS_WEAK_PER_CPU - Various other small improvements and fixes * tag 's390-6.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (92 commits) watchdog: diag288_wdt: Remove KMSG_COMPONENT macro s390/entry: Use lay instead of aghik s390/vdso: Get rid of -m64 flag handling s390/vdso: Rename vdso64 to vdso s390: Rename head64.S to head.S s390/vdso: Use common STABS_DEBUG and DWARF_DEBUG macros s390: Add stackprotector support s390/modules: Simplify module_finalize() slightly s390: Remove KMSG_COMPONENT macro s390/percpu: Get rid of ARCH_MODULE_NEEDS_WEAK_PER_CPU s390/ap: Restrict driver_override versus apmask and aqmask use s390/ap: Rename mutex ap_perms_mutex to ap_attr_mutex s390/ap: Support driver_override for AP queue devices s390/ap: Use all-bits-one apmask/aqmask for vfio in_use() checks s390/debug: Update description of resize operation s390/syscalls: Switch to generic system call table generation s390/syscalls: Remove system call table pointer from thread_struct s390/uapi: Remove 31 bit support from uapi header files s390: Remove compat support tools: Remove s390 compat support ...

s390/mm: Fix __ptep_rdp() inline assembly

2025-11-14T14:58:20Z

When a zero ASCE is passed to the __ptep_rdp() inline assembly, the generated instruction should have the R3 field of the instruction set to zero. However the inline assembly is written incorrectly: for such cases a zero is loaded into a register allocated by the compiler and this register is then used by the instruction. This means that selected TLB entries may not be flushed since the specified ASCE does not match the one which was used when the selected TLB entries were created. Fix this by removing the asce and opt parameters of __ptep_rdp(), since all callers always pass zero, and use a hard-coded register zero for the R3 field. Fixes: 0807b856521f ("s390/mm: add support for RDP (Reset DAT-Protection)") Cc: stable@vger.kernel.org Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens

s390/mm: Replace the CSP instruction with CSPG

2025-11-06T13:12:31Z

The CSPG instruction is part of the Dat-Enhancement facility 1, which is always available. Given that it can be used everywhere where also the CSP instruction can be used, replace CSP with CSPG everywhere. This allows to remove the csp() inline assembly. Also remove the unused gmap_pmdp_csp() function. Acked-by: Alexander Gordeev Reviewed-by: Claudio Imbrenda Signed-off-by: Heiko Carstens

Merge tag 'kvm-s390-next-6.18-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

2025-09-30T17:09:20Z

KVM: s390: A bugfix and a performance improvement * Improve interrupt cpu for wakeup, change the heuristic to decide wich vCPU to deliver a floating interrupt to. * Clear the pte when discarding a swapped page because of CMMA; this bug was introduced in 6.16 when refactoring gmap code.

KVM: s390: Fix to clear PTE when discarding a swapped page

2025-09-30T13:58:30Z

KVM run fails when guests with 'cmm' cpu feature and host are under memory pressure and use swap heavily. This is because npages becomes ENOMEN (out of memory) in hva_to_pfn_slow() which inturn propagates as EFAULT to qemu. Clearing the page table entry when discarding an address that maps to a swap entry resolves the issue. Fixes: 200197908dc4 ("KVM: s390: Refactor and split some gmap helpers") Cc: stable@vger.kernel.org Suggested-by: Claudio Imbrenda Signed-off-by: Gautam Gala Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda

s390/mm: Enable THP_SWAP and THP_MIGRATION

2025-07-31T16:59:26Z

After hugetlbfs PTE_MARKER support for s390 introduced region-third and segment table swap entries, it is now possible to also enable THP_SWAP and THP_MIGRATION for s390. s390 has different layout for PTE and region / segment table entries (RSTE). This is also true for swap entries, and their swap type and offset encoding. For hugetlbfs PTE_MARKER support, s390 has internal __swp_type_rste() and __swp_offset_rste() helpers to correctly handle RSTE swap entries. But common swap code does not know about this difference, and only uses __swp_type(), __swp_offset() and __swp_entry() helpers for conversion between arch-dependent and arch-independent representation of swp_entry_t for all pagetable levels. On s390, those helpers only work for PTE swap entries. Therefore, implement __pmd_to_swp_entry() to build a fake PTE swap entry and return the arch-dependent representation of that. Correspondingly, implement __swp_entry_to_pmd() to convert that into a proper PMD swap entry again. With this, the arch-dependent swp_entry_t representation will always look like a PTE swap entry in common code. This is somewhat similar to fake PTEs in hugetlbfs code for s390, but only requires conversion of the swap type and offset, and not all the possible PTE bits. For PMD swap entry SOFT_DIRTY handling, use the same helpers as for normal PMDs. Similar to PTEs, the SOFT_DIRTY bit location is the same for swap and normal entries. Reviewed-by: Heiko Carstens Signed-off-by: Gerald Schaefer Signed-off-by: Alexander Gordeev

mm: pgtable: fix pte_swp_exclusive

2025-06-11T21:52:08Z

Make pte_swp_exclusive return bool instead of int. This will better reflect how pte_swp_exclusive is actually used in the code. This fixes swap/swapoff problems on Alpha due pte_swp_exclusive not returning correct values when _PAGE_SWP_EXCLUSIVE bit resides in upper 32-bits of PTE (like on alpha). Suggested-by: Al Viro Signed-off-by: Magnus Lindholm Cc: Sam James Link: https://lore.kernel.org/lkml/20250218175735.19882-2-linmag7@gmail.com/ Link: https://lore.kernel.org/lkml/20250602041118.GA2675383@ZenIV/ [ Applied as the 'sed' script Al suggested - Linus ] Signed-off-by: Linus Torvalds

arch: remove mk_pmd()

2025-05-12T00:48:04Z

There are now no callers of mk_huge_pmd() and mk_pmd(). Remove them. Link: https://lkml.kernel.org/r/20250402181709.2386022-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Zi Yan Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Anton Ivanov Cc: Dave Hansen Cc: David Hildenbrand Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Johannes Berg Cc: Muchun Song Cc: Richard Weinberger Cc: Signed-off-by: Andrew Morton

mm: introduce a common definition of mk_pte()

2025-05-12T00:48:02Z

Most architectures simply call pfn_pte(). Centralise that as the normal definition and remove the definition of mk_pte() from the architectures which have either that exact definition or something similar. Link: https://lkml.kernel.org/r/20250402181709.2386022-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Geert Uytterhoeven # m68k Acked-by: David Hildenbrand Reviewed-by: Alexander Gordeev # s390 Cc: Zi Yan Cc: Andreas Larsson Cc: Anton Ivanov Cc: Dave Hansen Cc: "David S. Miller" Cc: Johannes Berg Cc: Muchun Song Cc: Richard Weinberger Cc: Signed-off-by: Andrew Morton

mm: set the pte dirty if the folio is already dirty

2025-05-12T00:48:02Z

Patch series "Add folio_mk_pte()", v2. Today if you have a folio and want to create a PTE that points to the first page in it, you have to convert from a folio to a page. That's zero-cost today but will be more expensive in the future. I didn't want to add folio_mk_pte() to each architecture, and I didn't want to lose any optimisations that architectures have from their own implementation of mk_pte(). Fortunately, most architectures have by now turned their mk_pte() into a fairly bland variant of pfn_pte(), but s390 has a special optimisation that needs to be moved into generic code in the first patch. At the end of this patch set, we have mk_pte() and folio_mk_pte() in mm.h and each architecture only has to implement pfn_pte(). We've also eliminated mk_huge_pte(), mk_huge_pmd() and mk_pmd(). This patch (of 11): If the first access to a folio is a read that is then followed by a write, we can save a page fault. s390 implemented this in their mk_pte() in commit abf09bed3cce ("s390/mm: implement software dirty bits"), but other architectures can also benefit from this. Link: https://lkml.kernel.org/r/20250402181709.2386022-1-willy@infradead.org Link: https://lkml.kernel.org/r/20250402181709.2386022-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: David Hildenbrand Reviewed-by: Alexander Gordeev # for s390 Cc: Zi Yan Cc: Andreas Larsson Cc: Anton Ivanov Cc: Dave Hansen Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Johannes Berg Cc: Muchun Song Cc: Richard Weinberger Cc: Signed-off-by: Andrew Morton