mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
5b0e2cb020
Non-highlights: - Five fixes for the >128T address space handling, both to fix bugs in our implementation and to bring the semantics exactly into line with x86. Highlights: - Support for a new OPAL call on bare metal machines which gives us a true NMI (ie. is not masked by MSR[EE]=0) for debugging etc. - Support for Power9 DD2 in the CXL driver. - Improvements to machine check handling so that uncorrectable errors can be reported into the generic memory_failure() machinery. - Some fixes and improvements for VPHN, which is used under PowerVM to notify the Linux partition of topology changes. - Plumbing to enable TM (transactional memory) without suspend on some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND). - Support for emulating vector loads form cache-inhibited memory, on some Power9 revisions. - Disable the fast-endian switch "syscall" by default (behind a CONFIG), we believe it has never had any users. - A major rework of the API drivers use when initiating and waiting for long running operations performed by OPAL firmware, and changes to the powernv_flash driver to use the new API. - Several fixes for the handling of FP/VMX/VSX while processes are using transactional memory. - Optimisations of TLB range flushes when using the radix MMU on Power9. - Improvements to the VAS facility used to access coprocessors on Power9, and related improvements to the way the NX crypto driver handles requests. - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit. Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard, Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley, Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu, Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee, Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, William A. Kennington III. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJaDXGuAAoJEFHr6jzI4aWAEqwP/0TA35KFAK6wqfkCf67z4q+O I+5piI4eDV4jdCakfoIN1JfjhQRULNePSoCHTccan30mu/bm30p69xtOLL2/h5xH Mhz/eDBAOo0lrT20nyZfYMW3FnM66wnNf++qJ0O+8L052r4WOB02J0k1uM1ST01D 5Lb5mUoxRLRzCgKRYAYWJifn+IFPUB9NMsvMTym94krAFlIjIzMEQXhDoln+jJMr QmY5f1BTA/fLfXobn0zwoc/C1oa2PUtxd+rxbwGrLoZ6G843mMqUi90SMr5ybhXp RzepnBTj4by3vOsnk/X1mANyaZfLsunp75FwnjHdPzKrAS/TuPp8D/iSxxE/PzEq cLwJFBnFXSgQMefDErXxhHSDz2dAg5r14rsTpDcq2Ko8TPV4rPsuSfmbd9Txekb0 yWHsjoJUBBMl2QcWqIHl+AlV8j1RklF6solcTBcGnH1CZJMfa05VKXV7xGEvOHa0 RJ+/xPyR9KjoB/SUp++9Vmx/M6SwQYFOJlr3Zpg9LNtR8WpoPYu1E6eO+u1Hhzny eJqaNstH+i+VdY9eqszkAsEBh8o9M/+b+7Wx7TetvU+v368CbXtgFYs9qy2oZjPF t9sY/BHaHZ8eZ7I00an77a0fVV5B1PVASUtIz5CqkwGpMvX6Z6W2K/XUUFI61kuu E06HS6Ht8UPJAzrAPUMl =Rq81 -----END PGP SIGNATURE----- Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: "A bit of a small release, I suspect in part due to me travelling for KS. But my backlog of patches to review is smaller than usual, so I think in part folks just didn't send as much this cycle. Non-highlights: - Five fixes for the >128T address space handling, both to fix bugs in our implementation and to bring the semantics exactly into line with x86. Highlights: - Support for a new OPAL call on bare metal machines which gives us a true NMI (ie. is not masked by MSR[EE]=0) for debugging etc. - Support for Power9 DD2 in the CXL driver. - Improvements to machine check handling so that uncorrectable errors can be reported into the generic memory_failure() machinery. - Some fixes and improvements for VPHN, which is used under PowerVM to notify the Linux partition of topology changes. - Plumbing to enable TM (transactional memory) without suspend on some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND). - Support for emulating vector loads form cache-inhibited memory, on some Power9 revisions. - Disable the fast-endian switch "syscall" by default (behind a CONFIG), we believe it has never had any users. - A major rework of the API drivers use when initiating and waiting for long running operations performed by OPAL firmware, and changes to the powernv_flash driver to use the new API. - Several fixes for the handling of FP/VMX/VSX while processes are using transactional memory. - Optimisations of TLB range flushes when using the radix MMU on Power9. - Improvements to the VAS facility used to access coprocessors on Power9, and related improvements to the way the NX crypto driver handles requests. - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit. Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard, Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley, Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu, Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee, Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A. Kennington III" * tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits) powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature powerpc/64s: Fix masking of SRR1 bits on instruction fault powerpc/64s: mm_context.addr_limit is only used on hash powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary powerpc/64s/hash: Fix fork() with 512TB process address space powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Fix 512T hint detection to use >= 128T powerpc: Fix DABR match on hash based systems powerpc/signal: Properly handle return value from uprobe_deny_signal() powerpc/fadump: use kstrtoint to handle sysfs store powerpc/lib: Implement UACCESS_FLUSHCACHE API powerpc/lib: Implement PMEM API powerpc/powernv/npu: Don't explicitly flush nmmu tlb powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm() powerpc/powernv/idle: Round up latency and residency values powerpc/kprobes: refactor kprobe_lookup_name for safer string operations powerpc/kprobes: Blacklist emulate_update_regs() from kprobes powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace powerpc/kprobes: Disable preemption before invoking probe handler for optprobes ...
217 lines
5.1 KiB
C
217 lines
5.1 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_POWERPC_HUGETLB_H
|
|
#define _ASM_POWERPC_HUGETLB_H
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
#include <asm/page.h>
|
|
#include <asm-generic/hugetlb.h>
|
|
|
|
extern struct kmem_cache *hugepte_cache;
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
|
|
#include <asm/book3s/64/hugetlb.h>
|
|
/*
|
|
* This should work for other subarchs too. But right now we use the
|
|
* new format only for 64bit book3s
|
|
*/
|
|
static inline pte_t *hugepd_page(hugepd_t hpd)
|
|
{
|
|
BUG_ON(!hugepd_ok(hpd));
|
|
/*
|
|
* We have only four bits to encode, MMU page size
|
|
*/
|
|
BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
|
|
return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
|
|
}
|
|
|
|
static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
|
|
{
|
|
return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
|
|
}
|
|
|
|
static inline unsigned int hugepd_shift(hugepd_t hpd)
|
|
{
|
|
return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
|
|
}
|
|
static inline void flush_hugetlb_page(struct vm_area_struct *vma,
|
|
unsigned long vmaddr)
|
|
{
|
|
if (radix_enabled())
|
|
return radix__flush_hugetlb_page(vma, vmaddr);
|
|
}
|
|
|
|
#else
|
|
|
|
static inline pte_t *hugepd_page(hugepd_t hpd)
|
|
{
|
|
BUG_ON(!hugepd_ok(hpd));
|
|
#ifdef CONFIG_PPC_8xx
|
|
return (pte_t *)__va(hpd_val(hpd) &
|
|
~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
|
|
#else
|
|
return (pte_t *)((hpd_val(hpd) &
|
|
~HUGEPD_SHIFT_MASK) | PD_HUGE);
|
|
#endif
|
|
}
|
|
|
|
static inline unsigned int hugepd_shift(hugepd_t hpd)
|
|
{
|
|
#ifdef CONFIG_PPC_8xx
|
|
return ((hpd_val(hpd) & _PMD_PAGE_MASK) >> 1) + 17;
|
|
#else
|
|
return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
|
|
#endif
|
|
}
|
|
|
|
#endif /* CONFIG_PPC_BOOK3S_64 */
|
|
|
|
|
|
static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
|
|
unsigned pdshift)
|
|
{
|
|
/*
|
|
* On FSL BookE, we have multiple higher-level table entries that
|
|
* point to the same hugepte. Just use the first one since they're all
|
|
* identical. So for that case, idx=0.
|
|
*/
|
|
unsigned long idx = 0;
|
|
|
|
pte_t *dir = hugepd_page(hpd);
|
|
#ifndef CONFIG_PPC_FSL_BOOK3E
|
|
idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
|
|
#endif
|
|
|
|
return dir + idx;
|
|
}
|
|
|
|
pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
|
|
unsigned long addr, unsigned *shift);
|
|
|
|
void flush_dcache_icache_hugepage(struct page *page);
|
|
|
|
#if defined(CONFIG_PPC_MM_SLICES)
|
|
int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
|
|
unsigned long len);
|
|
#else
|
|
static inline int is_hugepage_only_range(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
unsigned long len)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
|
|
pte_t pte);
|
|
#ifdef CONFIG_PPC_8xx
|
|
static inline void flush_hugetlb_page(struct vm_area_struct *vma,
|
|
unsigned long vmaddr)
|
|
{
|
|
flush_tlb_page(vma, vmaddr);
|
|
}
|
|
#else
|
|
void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
|
|
#endif
|
|
|
|
void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
|
|
unsigned long end, unsigned long floor,
|
|
unsigned long ceiling);
|
|
|
|
/*
|
|
* The version of vma_mmu_pagesize() in arch/powerpc/mm/hugetlbpage.c needs
|
|
* to override the version in mm/hugetlb.c
|
|
*/
|
|
#define vma_mmu_pagesize vma_mmu_pagesize
|
|
|
|
/*
|
|
* If the arch doesn't supply something else, assume that hugepage
|
|
* size aligned regions are ok without further preparation.
|
|
*/
|
|
static inline int prepare_hugepage_range(struct file *file,
|
|
unsigned long addr, unsigned long len)
|
|
{
|
|
struct hstate *h = hstate_file(file);
|
|
if (len & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
if (addr & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, pte_t pte)
|
|
{
|
|
set_pte_at(mm, addr, ptep, pte);
|
|
}
|
|
|
|
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
#ifdef CONFIG_PPC64
|
|
return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
|
|
#else
|
|
return __pte(pte_update(ptep, ~0UL, 0));
|
|
#endif
|
|
}
|
|
|
|
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
pte_t pte;
|
|
pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
|
|
flush_hugetlb_page(vma, addr);
|
|
}
|
|
|
|
static inline int huge_pte_none(pte_t pte)
|
|
{
|
|
return pte_none(pte);
|
|
}
|
|
|
|
static inline pte_t huge_pte_wrprotect(pte_t pte)
|
|
{
|
|
return pte_wrprotect(pte);
|
|
}
|
|
|
|
static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
|
|
unsigned long addr, pte_t *ptep,
|
|
pte_t pte, int dirty)
|
|
{
|
|
#ifdef HUGETLB_NEED_PRELOAD
|
|
/*
|
|
* The "return 1" forces a call of update_mmu_cache, which will write a
|
|
* TLB entry. Without this, platforms that don't do a write of the TLB
|
|
* entry in the TLB miss handler asm will fault ad infinitum.
|
|
*/
|
|
ptep_set_access_flags(vma, addr, ptep, pte, dirty);
|
|
return 1;
|
|
#else
|
|
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
|
|
#endif
|
|
}
|
|
|
|
static inline pte_t huge_ptep_get(pte_t *ptep)
|
|
{
|
|
return *ptep;
|
|
}
|
|
|
|
static inline void arch_clear_hugepage_flags(struct page *page)
|
|
{
|
|
}
|
|
|
|
#else /* ! CONFIG_HUGETLB_PAGE */
|
|
static inline void flush_hugetlb_page(struct vm_area_struct *vma,
|
|
unsigned long vmaddr)
|
|
{
|
|
}
|
|
|
|
#define hugepd_shift(x) 0
|
|
static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
|
|
unsigned pdshift)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_HUGETLB_PAGE */
|
|
|
|
#endif /* _ASM_POWERPC_HUGETLB_H */
|