Re: [PATCH v2 36/39] xen/riscv: add minimal stuff to asm/mm.h to build full Xen

[Oleksii <oleksii.kurochko@xxxxxxxxx>]

On Thu, 2023-12-14 at 18:08 +0100, Jan Beulich wrote:
> On 24.11.2023 11:30, Oleksii Kurochko wrote:
> > --- a/xen/arch/riscv/include/asm/mm.h
> > +++ b/xen/arch/riscv/include/asm/mm.h
> > @@ -3,10 +3,271 @@
> >  #ifndef _ASM_RISCV_MM_H
> >  #define _ASM_RISCV_MM_H
> >  
> > +#include <public/xen.h>
> > +#include <xen/pdx.h>
> > +#include <xen/types.h>
> > +
> > +#include <asm/page.h>
> >  #include <asm/page-bits.h>
> >  
> > -#define pfn_to_paddr(pfn) ((paddr_t)(pfn) << PAGE_SHIFT)
> > -#define paddr_to_pfn(pa)  ((unsigned long)((pa) >> PAGE_SHIFT))
> 
> I'm a little puzzled here: Just a few patches ago you introduced them
> into
> asm/page.h, and (only) now you're removing them here.
I think it was some issue during rebasing of latest changes and
staging.

> 
> > +#define paddr_to_pdx(pa)    mfn_to_pdx(maddr_to_mfn(pa))
> > +#define gfn_to_gaddr(gfn)   pfn_to_paddr(gfn_x(gfn))
> > +#define gaddr_to_gfn(ga)    _gfn(paddr_to_pfn(ga))
> > +#define mfn_to_maddr(mfn)   pfn_to_paddr(mfn_x(mfn))
> > +#define maddr_to_mfn(ma)    _mfn(paddr_to_pfn(ma))
> > +#define vmap_to_mfn(va)    
> > maddr_to_mfn(virt_to_maddr((vaddr_t)va))
> > +#define vmap_to_page(va)    mfn_to_page(vmap_to_mfn(va))
> > +#define paddr_to_pdx(pa)    mfn_to_pdx(maddr_to_mfn(pa))
> > +#define gfn_to_gaddr(gfn)   pfn_to_paddr(gfn_x(gfn))
> > +#define gaddr_to_gfn(ga)    _gfn(paddr_to_pfn(ga))
> > +#define mfn_to_maddr(mfn)   pfn_to_paddr(mfn_x(mfn))
> > +#define maddr_to_mfn(ma)    _mfn(paddr_to_pfn(ma))
> > +#define vmap_to_mfn(va)    
> > maddr_to_mfn(virt_to_maddr((vaddr_t)va))
> > +#define vmap_to_page(va)    mfn_to_page(vmap_to_mfn(va))
> > +
> > +#define virt_to_maddr(va) ((paddr_t)((vaddr_t)(va) & PADDR_MASK))
> > +#define maddr_to_virt(pa) ((void *)((paddr_t)(pa) |
> > XEN_VIRT_START))
> 
> Is this really XEN_VIRT_START? I.e. does your directmap start there,
> right where the Xen image area also starts?
No, it is not. I tried to re-use PPC's version of mm.h ( as it was
already merged ) and missed to update this macros. Actually right now
it is defined for RISC-V as:

static inline void *maddr_to_virt(paddr_t ma)
{
    ASSERT((mfn_to_pdx(maddr_to_mfn(ma)) - directmap_base_pdx) <
           (DIRECTMAP_SIZE >> PAGE_SHIFT));
    return (void *)(XENHEAP_VIRT_START -
                    (directmap_base_pdx << PAGE_SHIFT) +
                    ((ma & ma_va_bottom_mask) |
                     ((ma & ma_top_mask) >> pfn_pdx_hole_shift)));
}


but I think about to stub it with BUG() if it will work or to change
XEN_VIRT_START to DIRECTMAP_VIRT_START.

> 
> > +/* Convert between Xen-heap virtual addresses and machine frame
> > numbers. */
> > +#define __virt_to_mfn(va) (virt_to_maddr(va) >> PAGE_SHIFT)
> > +#define __mfn_to_virt(mfn) (maddr_to_virt((paddr_t)(mfn) <<
> > PAGE_SHIFT))
> 
> Nit: Excess parentheses again.
Thanks. Ill update.

> 
> > +/* Convert between Xen-heap virtual addresses and page-info
> > structures. */
> > +static inline struct page_info *virt_to_page(const void *v)
> > +{
> > +    BUG();
> > +    return NULL;
> > +}
> > +
> > +/*
> > + * We define non-underscored wrappers for above conversion
> > functions.
> > + * These are overriden in various source files while underscored
> > version
> > + * remain intact.
> > + */
> > +#define virt_to_mfn(va)     __virt_to_mfn(va)
> > +#define mfn_to_virt(mfn)    __mfn_to_virt(mfn)
> > +
> > +struct page_info
> > +{
> > +    /* Each frame can be threaded onto a doubly-linked list. */
> > +    struct page_list_entry list;
> > +
> > +    /* Reference count and various PGC_xxx flags and fields. */
> > +    unsigned long count_info;
> > +
> > +    /* Context-dependent fields follow... */
> > +    union {
> > +        /* Page is in use: ((count_info & PGC_count_mask) != 0).
> > */
> > +        struct {
> > +            /* Type reference count and various PGT_xxx flags and
> > fields. */
> > +            unsigned long type_info;
> > +        } inuse;
> > +        /* Page is on a free list: ((count_info & PGC_count_mask)
> > == 0). */
> > +        union {
> > +            struct {
> > +                /*
> > +                 * Index of the first *possibly* unscrubbed page
> > in the buddy.
> > +                 * One more bit than maximum possible order to
> > accommodate
> > +                 * INVALID_DIRTY_IDX.
> > +                 */
> > +#define INVALID_DIRTY_IDX ((1UL << (MAX_ORDER + 1)) - 1)
> > +                unsigned long first_dirty:MAX_ORDER + 1;
> > +
> > +                /* Do TLBs need flushing for safety before next
> > page use? */
> > +                bool need_tlbflush:1;
> > +
> > +#define BUDDY_NOT_SCRUBBING    0
> > +#define BUDDY_SCRUBBING        1
> > +#define BUDDY_SCRUB_ABORT      2
> > +                unsigned long scrub_state:2;
> > +            };
> > +
> > +            unsigned long val;
> > +            } free;
> 
> Something's wrong with indentation here.
Thanks. Ill double check.

> 
> > +    } u;
> > +
> > +    union {
> > +        /* Page is in use, but not as a shadow. */
> > +        struct {
> > +            /* Owner of this page (zero if page is anonymous). */
> > +            struct domain *domain;
> > +        } inuse;
> > +
> > +        /* Page is on a free list. */
> > +        struct {
> > +            /* Order-size of the free chunk this page is the head
> > of. */
> > +            unsigned int order;
> > +        } free;
> > +
> > +    } v;
> > +
> > +    union {
> > +        /*
> > +         * Timestamp from 'TLB clock', used to avoid extra safety
> > flushes.
> > +         * Only valid for: a) free pages, and b) pages with zero
> > type count
> > +         */
> > +        u32 tlbflush_timestamp;
> 
> Nit: uint32_t and ...
> 
> > +    };
> > +    u64 pad;
> 
> ... uint64_t please in new code. Assuming, for the latter, you really
> need
> the field in the first place: I can't see what it's needed for.
This structure was copied from Arm's mm.h.
I am not sure too if it is needed. It seems to me it should be 8 byte
aligned without this pad for 64-bit archs.


> 
> > +};
> > +
> > +#define frame_table ((struct page_info *)FRAMETABLE_VIRT_START)
> > +
> > +/* PDX of the first page in the frame table. */
> > +extern unsigned long frametable_base_pdx;
> > +
> > +/* Convert between machine frame numbers and page-info structures.
> > */
> > +#define
> > mfn_to_page(mfn)                                            \
> > +    (frame_table + (mfn_to_pdx(mfn) - frametable_base_pdx))
> > +#define
> > page_to_mfn(pg)                                             \
> > +    pdx_to_mfn((unsigned long)((pg) - frame_table) +
> > frametable_base_pdx)
> > +
> > +static inline void *page_to_virt(const struct page_info *pg)
> > +{
> > +    return mfn_to_virt(mfn_x(page_to_mfn(pg)));
> > +}
> > +
> > +/*
> > + * Common code requires get_page_type and put_page_type.
> > + * We don't care about typecounts so we just do the minimum to
> > make it
> > + * happy.
> > + */
> > +static inline int get_page_type(struct page_info *page, unsigned
> > long type)
> > +{
> > +    return 1;
> > +}
> > +
> > +static inline void put_page_type(struct page_info *page)
> > +{
> > +    return;
> 
> No need for this; the body can ve entirely empty, as we have it
> elsewhere.
Thanks. I'll update.

> 
> > +}
> > +
> > +/* TODO */
> > +static inline bool get_page_nr(struct page_info *page, const
> > struct domain *domain,
> > +                        unsigned long nr)
> > +{
> > +    BUG();
> > +}
> > +static inline void put_page_nr(struct page_info *page, unsigned
> > long nr)
> > +{
> > +    BUG();
> > +}
> 
> What are these two needed for?
> 
> > +static inline void put_page_and_type(struct page_info *page)
> > +{
> > +    put_page_type(page);
> > +    put_page(page);
> > +}
> > +
> > +/*
> > + * RISCV does not have an M2P, but common code expects a handful
> > of
> > + * M2P-related defines and functions. Provide dummy versions of
> > these.
> > + */
> > +#define INVALID_M2P_ENTRY        (~0UL)
> > +#define SHARED_M2P_ENTRY         (~0UL - 1UL)
> > +#define SHARED_M2P(_e)           ((_e) == SHARED_M2P_ENTRY)
> > +
> > +/* Xen always owns P2M on PPC */
> 
> PPC?
Should be RISC-V. Missed to change.

> 
> > +#define set_gpfn_from_mfn(mfn, pfn) do { (void) (mfn),
> > (void)(pfn); } while (0)
> > +#define mfn_to_gfn(d, mfn) ((void)(d), _gfn(mfn_x(mfn)))
> > +
> > +#define PDX_GROUP_SHIFT (16 + 5)
> > +
> > +static inline unsigned long domain_get_maximum_gpfn(struct domain
> > *d)
> > +{
> > +    BUG();
> > +    return 0;
> > +}
> > +
> > +static inline long arch_memory_op(int op,
> > XEN_GUEST_HANDLE_PARAM(void) arg)
> > +{
> > +    BUG();
> > +    return 0;
> > +}
> > +
> > +/*
> > + * On RISCV, all the RAM is currently direct mapped in Xen.
> > + * Hence return always true.
> > + */
> > +static inline bool arch_mfns_in_directmap(unsigned long mfn,
> > unsigned long nr)
> > +{
> > +    return true;
> > +}
> > +
> > +#define PG_shift(idx)   (BITS_PER_LONG - (idx))
> > +#define PG_mask(x, idx) (x ## UL << PG_shift(idx))
> > +
> > +#define PGT_none          PG_mask(0, 1)  /* no special uses of
> > this page   */
> > +#define PGT_writable_page PG_mask(1, 1)  /* has writable
> > mappings?         */
> > +#define PGT_type_mask     PG_mask(1, 1)  /* Bits 31 or
> > 63.                 */
> > +
> > + /* Count of uses of this frame as its current type. */
> > +#define PGT_count_width   PG_shift(2)
> > +#define PGT_count_mask    ((1UL<<PGT_count_width)-1)
> > +
> > +/*
> > + * Page needs to be scrubbed. Since this bit can only be set on a
> > page that is
> > + * free (i.e. in PGC_state_free) we can reuse PGC_allocated bit.
> > + */
> > +#define _PGC_need_scrub   _PGC_allocated
> > +#define PGC_need_scrub    PGC_allocated
> > +
> > +//  /* Cleared when the owning guest 'frees' this page. */
> > +#define _PGC_allocated    PG_shift(1)
> > +#define PGC_allocated     PG_mask(1, 1)
> > +  /* Page is Xen heap? */
> > +#define _PGC_xen_heap     PG_shift(2)
> > +#define PGC_xen_heap      PG_mask(1, 2)
> > +#ifdef CONFIG_STATIC_MEMORY
> > +/* Page is static memory */
> > +#define _PGC_static    PG_shift(3)
> > +#define PGC_static     PG_mask(1, 3)
> > +#else
> > +#define PGC_static     0
> > +#endif
> 
> Please omit this until you really know whether you're going to
> support
> static memory.
Ok. I'll drop that.
> 
> > +/* ... */
> 
> ???
It was taken for Arm and I don't know what is the purpose of the
comment so it makes sense to drop it.
> 
> > +/* Page is broken? */
> > +#define _PGC_broken       PG_shift(7)
> > +#define PGC_broken        PG_mask(1, 7)
> > + /* Mutually-exclusive page states: { inuse, offlining, offlined,
> > free }. */
> > +#define PGC_state         PG_mask(3, 9)
> > +#define PGC_state_inuse   PG_mask(0, 9)
> > +#define PGC_state_offlining PG_mask(1, 9)
> > +#define PGC_state_offlined PG_mask(2, 9)
> > +#define PGC_state_free    PG_mask(3, 9)
> > +// #define page_state_is(pg, st) (((pg)->count_info&PGC_state) ==
> > PGC_state_##st)
> > +
> > +/* Count of references to this frame. */
> > +#define PGC_count_width   PG_shift(9)
> > +#define PGC_count_mask    ((1UL<<PGC_count_width)-1)
> > +
> > +#define page_state_is(pg, st) (((pg)->count_info&PGC_state) ==
> > PGC_state_##st)
> > +
> > +#define _PGC_extra        PG_shift(10)
> > +#define PGC_extra         PG_mask(1, 10)
> > +
> > +#define is_xen_heap_page(page) ((page)->count_info & PGC_xen_heap)
> > +#define is_xen_heap_mfn(mfn) \
> > +    (mfn_valid(mfn) && is_xen_heap_page(mfn_to_page(mfn)))
> > +
> > +#define is_xen_fixed_mfn(mfn)                                   \
> > +    ((mfn_to_maddr(mfn) >= virt_to_maddr(&_start)) &&           \
> > +     (mfn_to_maddr(mfn) <= virt_to_maddr((vaddr_t)_end - 1)))
> > +
> > +#define page_get_owner(_p)    (_p)->v.inuse.domain
> > +#define page_set_owner(_p,_d) ((_p)->v.inuse.domain = (_d))
> > +
> > +/* TODO: implement */
> > +#define mfn_valid(mfn) ({ (void) (mfn); 0; })
> > +// #define max_page (0UL)
> 
> ???
This macros isn't needed for now ( when I tried to make minimal build I
just commented such places and forgot to remove it ).
> 
> > +#define mfn_to_gfn(d, mfn) ((void)(d), _gfn(mfn_x(mfn)))
> > +
> > +#define domain_set_alloc_bitsize(d) ((void)0)
> > +#define domain_clamp_alloc_bitsize(d, b) (b)
> > +
> > +#define PFN_ORDER(_pfn) ((_pfn)->v.free.order)
> 
> No leading underscore needed here, I suppose.
Thanks. I'll remove underscore.

~ Oleksii