- Switch to the generic C VDSO, as well as some cleanups of our VDSO setup/handling code. - Support for KUAP (Kernel User Access Prevention) on systems using the hashed page table MMU, using memory protection keys. - Better handling of PowerVM SMT8 systems where all threads of a core do not share an L2, allowing the scheduler to make better scheduling decisions. - Further improvements to our machine check handling. - Show registers when unwinding interrupt frames during stack traces. - Improvements to our pseries (PowerVM) partition migration code. - Several series from Christophe refactoring and cleaning up various parts of the 32-bit code. - Other smaller features, fixes & cleanups. Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King, Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz, Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour, Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe Kleine-König, Vincent Stehlé, Youling Tang, Zhang Xiaoxu. -----BEGIN PGP SIGNATURE----- iQJHBAABCAAxFiEEJFGtCPCthwEv2Y/bUevqPMjhpYAFAl/bURITHG1wZUBlbGxl cm1hbi5pZC5hdQAKCRBR6+o8yOGlgEzBEAC1Vwibcog2P9rkJPb0q3UGWSYSx25V h/LwwxtM9Tm14j/LZsSgkOgIsfMaWEBIw/8D4efQ7AX9aFo+R0c2DdQMx1MG5MXz gZk58+l3LwId6h9+OrwurpEW+ZmURLAtGMSyFdkeiZ3/XTnkbf1XnewC0QWQe56a EGLmjx1MFl45jspoy7UIUXsXoNJIfflEKhrgUzSUh8X2eLmvB9ws6A4BXxbVzyZl lZv3+uWimU2pFgdkB9jOCxoG4zFEr2o5ovLHG7zCCVo5JoXmTPQ5cMVBraH206ms +5vCmu4qI8uP5UlZW/mZfhrtDiMdHdQqqFOaQwVlOmoUbU6L6E6rxm3iVnov2Bbi iUgxoeJDxAb2cM2EWFK6oWVgr7+NkwvXM1IG8xtprhHrCdnC9r+psQr/dswb3LSg MJ7u/RCq3uixy2kWP8E0NEHw7ngQZ/ZKPqzfnmIWOC7tYUxgaL02I8Ff9/ZXAI2J CnmqFYOjrimHkcwXGOtKkXNvfU0DiL97qpK2AQNWElE8+bUUmpw+ltUrsdSycYmv Afc4WIcVrTA+a9laSLgjdZbolbNSa3p+cMIYdPrVx9g+xqygbxIKv+EDGNv1WHfD GU1gmohMY+ZkMOvFRMi8LAsEm0DH/etWE0py/8uyxDYKnGyD1Ur6452DStkmgGb2 azmcaOyLdb+HXA== =Ga3K -----END PGP SIGNATURE----- Merge tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: - Switch to the generic C VDSO, as well as some cleanups of our VDSO setup/handling code. - Support for KUAP (Kernel User Access Prevention) on systems using the hashed page table MMU, using memory protection keys. - Better handling of PowerVM SMT8 systems where all threads of a core do not share an L2, allowing the scheduler to make better scheduling decisions. - Further improvements to our machine check handling. - Show registers when unwinding interrupt frames during stack traces. - Improvements to our pseries (PowerVM) partition migration code. - Several series from Christophe refactoring and cleaning up various parts of the 32-bit code. - Other smaller features, fixes & cleanups. Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King, Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz, Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour, Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe Kleine-König, Vincent Stehlé, Youling Tang, and Zhang Xiaoxu. * tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (304 commits) powerpc/32s: Fix cleanup_cpu_mmu_context() compile bug powerpc: Add config fragment for disabling -Werror powerpc/configs: Add ppc64le_allnoconfig target powerpc/powernv: Rate limit opal-elog read failure message powerpc/pseries/memhotplug: Quieten some DLPAR operations powerpc/ps3: use dma_mapping_error() powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10 powerpc/perf: Fix Threshold Event Counter Multiplier width for P10 powerpc/mm: Fix hugetlb_free_pmd_range() and hugetlb_free_pud_range() KVM: PPC: Book3S HV: Fix mask size for emulated msgsndp KVM: PPC: fix comparison to bool warning KVM: PPC: Book3S: Assign boolean values to a bool variable powerpc: Inline setup_kup() powerpc/64s: Mark the kuap/kuep functions non __init KVM: PPC: Book3S HV: XIVE: Add a comment regarding VP numbering powerpc/xive: Improve error reporting of OPAL calls powerpc/xive: Simplify xive_do_source_eoi() powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_EOI_FW powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_MASK_FW powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_SHIFT_BUG ...
307 lines
9.4 KiB
C
307 lines
9.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __ASM_POWERPC_MMU_CONTEXT_H
|
|
#define __ASM_POWERPC_MMU_CONTEXT_H
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/spinlock.h>
|
|
#include <asm/mmu.h>
|
|
#include <asm/cputable.h>
|
|
#include <asm/cputhreads.h>
|
|
|
|
/*
|
|
* Most if the context management is out of line
|
|
*/
|
|
#define init_new_context init_new_context
|
|
extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
|
|
#define destroy_context destroy_context
|
|
extern void destroy_context(struct mm_struct *mm);
|
|
#ifdef CONFIG_SPAPR_TCE_IOMMU
|
|
struct mm_iommu_table_group_mem_t;
|
|
|
|
extern int isolate_lru_page(struct page *page); /* from internal.h */
|
|
extern bool mm_iommu_preregistered(struct mm_struct *mm);
|
|
extern long mm_iommu_new(struct mm_struct *mm,
|
|
unsigned long ua, unsigned long entries,
|
|
struct mm_iommu_table_group_mem_t **pmem);
|
|
extern long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua,
|
|
unsigned long entries, unsigned long dev_hpa,
|
|
struct mm_iommu_table_group_mem_t **pmem);
|
|
extern long mm_iommu_put(struct mm_struct *mm,
|
|
struct mm_iommu_table_group_mem_t *mem);
|
|
extern void mm_iommu_init(struct mm_struct *mm);
|
|
extern void mm_iommu_cleanup(struct mm_struct *mm);
|
|
extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
|
|
unsigned long ua, unsigned long size);
|
|
extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
|
|
struct mm_struct *mm, unsigned long ua, unsigned long size);
|
|
extern struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
|
|
unsigned long ua, unsigned long entries);
|
|
extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
|
|
unsigned long ua, unsigned int pageshift, unsigned long *hpa);
|
|
extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
|
|
unsigned long ua, unsigned int pageshift, unsigned long *hpa);
|
|
extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua);
|
|
extern bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
|
|
unsigned int pageshift, unsigned long *size);
|
|
extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
|
|
extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
|
|
#else
|
|
static inline bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
|
|
unsigned int pageshift, unsigned long *size)
|
|
{
|
|
return false;
|
|
}
|
|
static inline void mm_iommu_init(struct mm_struct *mm) { }
|
|
#endif
|
|
extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
|
|
extern void set_context(unsigned long id, pgd_t *pgd);
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
extern void radix__switch_mmu_context(struct mm_struct *prev,
|
|
struct mm_struct *next);
|
|
static inline void switch_mmu_context(struct mm_struct *prev,
|
|
struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
if (radix_enabled())
|
|
return radix__switch_mmu_context(prev, next);
|
|
return switch_slb(tsk, next);
|
|
}
|
|
|
|
extern int hash__alloc_context_id(void);
|
|
extern void hash__reserve_context_id(int id);
|
|
extern void __destroy_context(int context_id);
|
|
static inline void mmu_context_init(void) { }
|
|
|
|
static inline int alloc_extended_context(struct mm_struct *mm,
|
|
unsigned long ea)
|
|
{
|
|
int context_id;
|
|
|
|
int index = ea >> MAX_EA_BITS_PER_CONTEXT;
|
|
|
|
context_id = hash__alloc_context_id();
|
|
if (context_id < 0)
|
|
return context_id;
|
|
|
|
VM_WARN_ON(mm->context.extended_id[index]);
|
|
mm->context.extended_id[index] = context_id;
|
|
return context_id;
|
|
}
|
|
|
|
static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
|
|
{
|
|
int context_id;
|
|
|
|
context_id = get_user_context(&mm->context, ea);
|
|
if (!context_id)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
#else
|
|
extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk);
|
|
extern unsigned long __init_new_context(void);
|
|
extern void __destroy_context(unsigned long context_id);
|
|
extern void mmu_context_init(void);
|
|
static inline int alloc_extended_context(struct mm_struct *mm,
|
|
unsigned long ea)
|
|
{
|
|
/* non book3s_64 should never find this called */
|
|
WARN_ON(1);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
|
|
extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
|
|
#else
|
|
static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
|
|
#endif
|
|
|
|
extern void switch_cop(struct mm_struct *next);
|
|
extern int use_cop(unsigned long acop, struct mm_struct *mm);
|
|
extern void drop_cop(unsigned long acop, struct mm_struct *mm);
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
static inline void inc_mm_active_cpus(struct mm_struct *mm)
|
|
{
|
|
atomic_inc(&mm->context.active_cpus);
|
|
}
|
|
|
|
static inline void dec_mm_active_cpus(struct mm_struct *mm)
|
|
{
|
|
atomic_dec(&mm->context.active_cpus);
|
|
}
|
|
|
|
static inline void mm_context_add_copro(struct mm_struct *mm)
|
|
{
|
|
/*
|
|
* If any copro is in use, increment the active CPU count
|
|
* in order to force TLB invalidations to be global as to
|
|
* propagate to the Nest MMU.
|
|
*/
|
|
if (atomic_inc_return(&mm->context.copros) == 1)
|
|
inc_mm_active_cpus(mm);
|
|
}
|
|
|
|
static inline void mm_context_remove_copro(struct mm_struct *mm)
|
|
{
|
|
int c;
|
|
|
|
/*
|
|
* When removing the last copro, we need to broadcast a global
|
|
* flush of the full mm, as the next TLBI may be local and the
|
|
* nMMU and/or PSL need to be cleaned up.
|
|
*
|
|
* Both the 'copros' and 'active_cpus' counts are looked at in
|
|
* flush_all_mm() to determine the scope (local/global) of the
|
|
* TLBIs, so we need to flush first before decrementing
|
|
* 'copros'. If this API is used by several callers for the
|
|
* same context, it can lead to over-flushing. It's hopefully
|
|
* not common enough to be a problem.
|
|
*
|
|
* Skip on hash, as we don't know how to do the proper flush
|
|
* for the time being. Invalidations will remain global if
|
|
* used on hash. Note that we can't drop 'copros' either, as
|
|
* it could make some invalidations local with no flush
|
|
* in-between.
|
|
*/
|
|
if (radix_enabled()) {
|
|
flush_all_mm(mm);
|
|
|
|
c = atomic_dec_if_positive(&mm->context.copros);
|
|
/* Detect imbalance between add and remove */
|
|
WARN_ON(c < 0);
|
|
|
|
if (c == 0)
|
|
dec_mm_active_cpus(mm);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* vas_windows counter shows number of open windows in the mm
|
|
* context. During context switch, use this counter to clear the
|
|
* foreign real address mapping (CP_ABORT) for the thread / process
|
|
* that intend to use COPY/PASTE. When a process closes all windows,
|
|
* disable CP_ABORT which is expensive to run.
|
|
*
|
|
* For user context, register a copro so that TLBIs are seen by the
|
|
* nest MMU. mm_context_add/remove_vas_window() are used only for user
|
|
* space windows.
|
|
*/
|
|
static inline void mm_context_add_vas_window(struct mm_struct *mm)
|
|
{
|
|
atomic_inc(&mm->context.vas_windows);
|
|
mm_context_add_copro(mm);
|
|
}
|
|
|
|
static inline void mm_context_remove_vas_window(struct mm_struct *mm)
|
|
{
|
|
int v;
|
|
|
|
mm_context_remove_copro(mm);
|
|
v = atomic_dec_if_positive(&mm->context.vas_windows);
|
|
|
|
/* Detect imbalance between add and remove */
|
|
WARN_ON(v < 0);
|
|
}
|
|
#else
|
|
static inline void inc_mm_active_cpus(struct mm_struct *mm) { }
|
|
static inline void dec_mm_active_cpus(struct mm_struct *mm) { }
|
|
static inline void mm_context_add_copro(struct mm_struct *mm) { }
|
|
static inline void mm_context_remove_copro(struct mm_struct *mm) { }
|
|
#endif
|
|
|
|
|
|
extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk);
|
|
|
|
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
switch_mm_irqs_off(prev, next, tsk);
|
|
local_irq_restore(flags);
|
|
}
|
|
#define switch_mm_irqs_off switch_mm_irqs_off
|
|
|
|
/*
|
|
* After we have set current->mm to a new value, this activates
|
|
* the context for the new mm so we see the new mappings.
|
|
*/
|
|
#define activate_mm activate_mm
|
|
static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
|
|
{
|
|
switch_mm_irqs_off(prev, next, current);
|
|
}
|
|
|
|
/* We don't currently use enter_lazy_tlb() for anything */
|
|
#ifdef CONFIG_PPC_BOOK3E_64
|
|
#define enter_lazy_tlb enter_lazy_tlb
|
|
static inline void enter_lazy_tlb(struct mm_struct *mm,
|
|
struct task_struct *tsk)
|
|
{
|
|
/* 64-bit Book3E keeps track of current PGD in the PACA */
|
|
get_paca()->pgd = NULL;
|
|
}
|
|
#endif
|
|
|
|
extern void arch_exit_mmap(struct mm_struct *mm);
|
|
|
|
static inline void arch_unmap(struct mm_struct *mm,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
unsigned long vdso_base = (unsigned long)mm->context.vdso - PAGE_SIZE;
|
|
|
|
if (start <= vdso_base && vdso_base < end)
|
|
mm->context.vdso = NULL;
|
|
}
|
|
|
|
#ifdef CONFIG_PPC_MEM_KEYS
|
|
bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
|
|
bool execute, bool foreign);
|
|
void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm);
|
|
#else /* CONFIG_PPC_MEM_KEYS */
|
|
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
|
|
bool write, bool execute, bool foreign)
|
|
{
|
|
/* by default, allow everything */
|
|
return true;
|
|
}
|
|
|
|
#define pkey_mm_init(mm)
|
|
#define thread_pkey_regs_save(thread)
|
|
#define thread_pkey_regs_restore(new_thread, old_thread)
|
|
#define thread_pkey_regs_init(thread)
|
|
#define arch_dup_pkeys(oldmm, mm)
|
|
|
|
static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags)
|
|
{
|
|
return 0x0UL;
|
|
}
|
|
|
|
#endif /* CONFIG_PPC_MEM_KEYS */
|
|
|
|
static inline int arch_dup_mmap(struct mm_struct *oldmm,
|
|
struct mm_struct *mm)
|
|
{
|
|
arch_dup_pkeys(oldmm, mm);
|
|
return 0;
|
|
}
|
|
|
|
#include <asm-generic/mmu_context.h>
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* __ASM_POWERPC_MMU_CONTEXT_H */
|