On Tue, 2024-01-23 at 14:03 +0100, Jan Beulich wrote:
> On 22.12.2023 16:13, Oleksii Kurochko wrote:
> > Signed-off-by: Oleksii Kurochko <oleksii.kuroc...@gmail.com>
> > ---
> > Changes in V3:
> > - update the commit message
>
> ??? (yet again)
>
> > --- a/xen/arch/riscv/include/asm/mm.h
> > +++ b/xen/arch/riscv/include/asm/mm.h
> > @@ -3,8 +3,251 @@
> > #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 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))
>
> Everything you have above ...
>
> > +#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))
>
> ... appears a 2nd time right afterwards.
>
> > +#define virt_to_maddr(va) ((paddr_t)((vaddr_t)(va) & PADDR_MASK))
> > +#define maddr_to_virt(pa) ((void *)((paddr_t)(pa) |
> > 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)
>
> These would imo better use maddr_to_mfn() and mfn_to_maddr(), rather
> than
> kind of open-coding them. The former could also use PFN_DOWN() as an
> alternative.
We can't to as __virt_to_mfn() when is used it is usually wrapped by
_mfn() which expect to have unsigned long as an argument.
>
> > +/* 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)
>
> Is this really still needed? Would be pretty nice if in a new port we
> could get to start cleanly right away (i.e. by not needing per-file
> overrides, but using type-safe expansions here right away).
We still need __virt_to_mfn and __mfn_to_virt as common code use them:
* xen/common/xenoprof.c:24:#define virt_to_mfn(va)
mfn(__virt_to_mfn(va))
* xen/include/xen/domain_page.h:59:#define domain_page_map_to_mfn(ptr)
_mfn(__virt_to_mfn((unsigned long)(ptr)))
~ Oleksii
>
> > +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;
>
> Indentation is wrong (and thus misleading) for these two lines.
>
> > +
> > + } u;
>
> Nit: I don't see the value of the trailing blank line inside the
> union.
>
> > + union {
> > + /* Page is in use, but not as a shadow. */
>
> I question the appicability of "shadow" here.
>
> > + 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
> > + */
> > + uint32_t tlbflush_timestamp;
> > + };
> > + uint64_t pad;
> > +};
> > +
> > +#define frame_table ((struct page_info *)FRAMETABLE_VIRT_START)
> > +
> > +/* PDX of the first page in the frame table. */
> > +extern unsigned long frametable_base_pdx;
>
> From this I conclude memory on RISC-V systems may not start at (or
> near) 0?
>
> > +/* 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)
> > +{
> > +}
> > +
> > +static inline void put_page_and_type(struct page_info *page)
> > +{
> > + put_page_type(page);
> > + put_page(page);
> > +}
> > +
> > +/*
> > + * RISC-V 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 RISC-V */
> > +#define set_gpfn_from_mfn(mfn, pfn) do { (void) (mfn),
> > (void)(pfn); } while (0)
>
> Nit: Stray blank again after cast.
>
> > +#define mfn_to_gfn(d, mfn) ((void)(d), _gfn(mfn_x(mfn)))
>
> What's the relation of the comment with these two #define-s?
>
> > +#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)
>
> Nit: Style (missing blanks around binary operators). Also a few more
> times further down.
>
> > +/*
> > + * 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. */
>
> Why a commented out comment?
>
> > +#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)
> > +/* Page is broken? */
> > +#define _PGC_broken PG_shift(7)
> > +#define PGC_broken PG_mask(1, 7)
> > + /* Mutually-exclusive page states: { inuse, offlining, offlined,
> > free }. */
>
> Can similar comments in this block please all be similarly indented
> (or not)?
>
> > +#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)
>
> And here it then "properly" appears?
>
> > +#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)))
>
> Why does _start need prefixing wuth & and _end prefixing with a cast?
> First and foremost both want to be consistent. And then preferably
> with as little extra clutter as possible.
>
> > +#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 mfn_to_gfn(d, mfn) ((void)(d), _gfn(mfn_x(mfn)))
>
> This appeared further up already.
>
> > +#define domain_set_alloc_bitsize(d) ((void)0)
>
> Better ((void)(d)) ? And then ...
>
> > +#define domain_clamp_alloc_bitsize(d, b) (b)
>
> ... ((void)(d), (b)) here?
>
> Jan
