[PATCH v5 RFC 07/14] tools/libxc: x86 PV common code

[Andrew Cooper <andrew.cooper3@citrix.com>]

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Frediano Ziglio <frediano.ziglio@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 tools/libxc/saverestore/common.h        |    5 +
 tools/libxc/saverestore/common_x86_pv.c |  250 +++++++++++++++++++++++++++++++
 tools/libxc/saverestore/common_x86_pv.h |  144 ++++++++++++++++++
 3 files changed, 399 insertions(+)
 create mode 100644 tools/libxc/saverestore/common_x86_pv.c
 create mode 100644 tools/libxc/saverestore/common_x86_pv.h

diff --git a/tools/libxc/saverestore/common.h b/tools/libxc/saverestore/common.h
index d9a3655..5f6af00 100644
--- a/tools/libxc/saverestore/common.h
+++ b/tools/libxc/saverestore/common.h
@@ -14,6 +14,10 @@
 
 #undef mfn_to_pfn
 #undef pfn_to_mfn
+#undef GET_FIELD
+#undef SET_FIELD
+#undef MEMCPY_FIELD
+#undef MEMSET_ARRAY_FIELD
 
 
 #include "stream_format.h"
@@ -240,6 +244,7 @@ struct context
     };
 };
 
+extern struct common_ops common_ops_x86_pv;
 
 struct record
 {
diff --git a/tools/libxc/saverestore/common_x86_pv.c b/tools/libxc/saverestore/common_x86_pv.c
new file mode 100644
index 0000000..02a006b
--- /dev/null
+++ b/tools/libxc/saverestore/common_x86_pv.c
@@ -0,0 +1,250 @@
+#include <assert.h>
+
+#include "common_x86_pv.h"
+
+/* common_ops function */
+static bool x86_pv_pfn_is_valid(const struct context *ctx, xen_pfn_t pfn)
+{
+    return pfn <= ctx->x86_pv.max_pfn;
+}
+
+/* common_ops function */
+static xen_pfn_t x86_pv_pfn_to_gfn(const struct context *ctx, xen_pfn_t pfn)
+{
+    assert(pfn <= ctx->x86_pv.max_pfn);
+
+    if ( ctx->x86_pv.width == sizeof(uint64_t) )
+        /* 64 bit guest.  Need to truncate their pfns for 32 bit toolstacks */
+        return ((uint64_t *)ctx->x86_pv.p2m)[pfn];
+    else
+    {
+        /* 32 bit guest.  Need to expand INVALID_MFN for 64 bit toolstacks */
+        uint32_t mfn = ((uint32_t *)ctx->x86_pv.p2m)[pfn];
+
+        return mfn == ~0U ? INVALID_MFN : mfn;
+    }
+}
+
+/* common_ops function */
+static void x86_pv_set_page_type(struct context *ctx, xen_pfn_t pfn,
+                                 unsigned long type)
+{
+    assert(pfn <= ctx->x86_pv.max_pfn);
+
+    ctx->x86_pv.pfn_types[pfn] = type;
+}
+
+/* common_ops function */
+static void x86_pv_set_gfn(struct context *ctx, xen_pfn_t pfn,
+                           xen_pfn_t mfn)
+{
+    assert(pfn <= ctx->x86_pv.max_pfn);
+
+    if ( ctx->x86_pv.width == sizeof(uint64_t) )
+        /* 64 bit guest.  Need to expand INVALID_MFN for 32 bit toolstacks */
+        ((uint64_t *)ctx->x86_pv.p2m)[pfn] = mfn == INVALID_MFN ? ~0ULL : mfn;
+    else
+        /* 32 bit guest.  Can safely truncate INVALID_MFN for 64 bit toolstacks */
+        ((uint32_t *)ctx->x86_pv.p2m)[pfn] = mfn;
+}
+
+struct common_ops common_ops_x86_pv = {
+    .pfn_is_valid   = x86_pv_pfn_is_valid,
+    .pfn_to_gfn     = x86_pv_pfn_to_gfn,
+    .set_page_type  = x86_pv_set_page_type,
+    .set_gfn        = x86_pv_set_gfn,
+};
+
+xen_pfn_t mfn_to_pfn(struct context *ctx, xen_pfn_t mfn)
+{
+    assert(mfn <= ctx->x86_pv.max_mfn);
+    return ctx->x86_pv.m2p[mfn];
+}
+
+bool mfn_in_pseudophysmap(struct context *ctx, xen_pfn_t mfn)
+{
+    return ( (mfn <= ctx->x86_pv.max_mfn) &&
+             (mfn_to_pfn(ctx, mfn) <= ctx->x86_pv.max_pfn) &&
+             (ctx->ops.pfn_to_gfn(ctx, mfn_to_pfn(ctx, mfn) == mfn)) );
+}
+
+void dump_bad_pseudophysmap_entry(struct context *ctx, xen_pfn_t mfn)
+{
+    xc_interface *xch = ctx->xch;
+    xen_pfn_t pfn = ~0UL;
+
+    ERROR("mfn %#lx, max %#lx", mfn, ctx->x86_pv.max_mfn);
+
+    if ( (mfn != ~0UL) && (mfn <= ctx->x86_pv.max_mfn) )
+    {
+        pfn = ctx->x86_pv.m2p[mfn];
+        ERROR("  m2p[%#lx] = %#lx, max_pfn %#lx",
+              mfn, pfn, ctx->x86_pv.max_pfn);
+    }
+
+    if ( (pfn != ~0UL) && (pfn <= ctx->x86_pv.max_pfn) )
+        ERROR("  p2m[%#lx] = %#lx",
+              pfn, ctx->ops.pfn_to_gfn(ctx, pfn));
+}
+
+xen_pfn_t cr3_to_mfn(struct context *ctx, uint64_t cr3)
+{
+    if ( ctx->x86_pv.width == 8 )
+        return cr3 >> 12;
+    else
+        return (((uint32_t)cr3 >> 12) | ((uint32_t)cr3 << 20));
+}
+
+uint64_t mfn_to_cr3(struct context *ctx, xen_pfn_t mfn)
+{
+    if ( ctx->x86_pv.width == 8 )
+        return ((uint64_t)mfn) << 12;
+    else
+        return (((uint32_t)mfn << 12) | ((uint32_t)mfn >> 20));
+}
+
+int x86_pv_domain_info(struct context *ctx)
+{
+    xc_interface *xch = ctx->xch;
+    unsigned int guest_width, guest_levels, fpp;
+    int max_pfn;
+
+    /* Get the domain width */
+    if ( xc_domain_get_guest_width(xch, ctx->domid, &guest_width) )
+    {
+        PERROR("Unable to determine dom%d's width", ctx->domid);
+        return -1;
+    }
+
+    if ( guest_width == 4 )
+        guest_levels = 3;
+    else if ( guest_width == 8 )
+        guest_levels = 4;
+    else
+    {
+        ERROR("Invalid guest width %d.  Expected 32 or 64", guest_width * 8);
+        return -1;
+    }
+    ctx->x86_pv.width = guest_width;
+    ctx->x86_pv.levels = guest_levels;
+    fpp = PAGE_SIZE / ctx->x86_pv.width;
+
+    DPRINTF("%d bits, %d levels", guest_width * 8, guest_levels);
+
+    /* Get the domain's size */
+    max_pfn = xc_domain_maximum_gpfn(xch, ctx->domid);
+    if ( max_pfn < 0 )
+    {
+        PERROR("Unable to obtain guests max pfn");
+        return -1;
+    }
+
+    if ( max_pfn > 0 )
+    {
+        ctx->x86_pv.max_pfn = max_pfn;
+        ctx->x86_pv.p2m_frames = (ctx->x86_pv.max_pfn + fpp) / fpp;
+
+        DPRINTF("max_pfn %#x, p2m_frames %d", max_pfn, ctx->x86_pv.p2m_frames);
+    }
+
+    return 0;
+}
+
+int x86_pv_map_m2p(struct context *ctx)
+{
+    xc_interface *xch = ctx->xch;
+    long max_page = xc_maximum_ram_page(xch);
+    unsigned long m2p_chunks, m2p_size;
+    privcmd_mmap_entry_t *entries = NULL;
+    xen_pfn_t *extents_start = NULL;
+    int rc = -1, i;
+
+    if ( max_page < 0 )
+    {
+        PERROR("Failed to get maximum ram page");
+        goto err;
+    }
+
+    ctx->x86_pv.max_mfn = max_page;
+    m2p_size   = M2P_SIZE(ctx->x86_pv.max_mfn);
+    m2p_chunks = M2P_CHUNKS(ctx->x86_pv.max_mfn);
+
+    extents_start = malloc(m2p_chunks * sizeof(xen_pfn_t));
+    if ( !extents_start )
+    {
+        ERROR("Unable to allocate %zu bytes for m2p mfns",
+              m2p_chunks * sizeof(xen_pfn_t));
+        goto err;
+    }
+
+    if ( xc_machphys_mfn_list(xch, m2p_chunks, extents_start) )
+    {
+        PERROR("Failed to get m2p mfn list");
+        goto err;
+    }
+
+    entries = malloc(m2p_chunks * sizeof(privcmd_mmap_entry_t));
+    if ( !entries )
+    {
+        ERROR("Unable to allocate %zu bytes for m2p mapping mfns",
+              m2p_chunks * sizeof(privcmd_mmap_entry_t));
+        goto err;
+    }
+
+    for ( i = 0; i < m2p_chunks; ++i )
+        entries[i].mfn = extents_start[i];
+
+    ctx->x86_pv.m2p = xc_map_foreign_ranges(
+        xch, DOMID_XEN, m2p_size, PROT_READ,
+        M2P_CHUNK_SIZE, entries, m2p_chunks);
+
+    if ( !ctx->x86_pv.m2p )
+    {
+        PERROR("Failed to mmap m2p ranges");
+        goto err;
+    }
+
+    ctx->x86_pv.nr_m2p_frames = (M2P_CHUNK_SIZE >> PAGE_SHIFT) * m2p_chunks;
+
+#ifdef __i386__
+    /* 32 bit toolstacks automatically get the compat m2p */
+    ctx->x86_pv.compat_m2p_mfn0 = entries[0].mfn;
+#else
+    /* 64 bit toolstacks need to ask Xen specially for it */
+    {
+        struct xen_machphys_mfn_list xmml = {
+            .max_extents = 1,
+            .extent_start = { &ctx->x86_pv.compat_m2p_mfn0 }
+        };
+
+        rc = do_memory_op(xch, XENMEM_machphys_compat_mfn_list,
+                          &xmml, sizeof(xmml));
+        if ( rc || xmml.nr_extents != 1 )
+        {
+            PERROR("Failed to get compat mfn list from Xen");
+            rc = -1;
+            goto err;
+        }
+    }
+#endif
+
+    /* All Done */
+    rc = 0;
+    DPRINTF("max_mfn %#lx", ctx->x86_pv.max_mfn);
+
+err:
+    free(entries);
+    free(extents_start);
+
+    return rc;
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/tools/libxc/saverestore/common_x86_pv.h b/tools/libxc/saverestore/common_x86_pv.h
new file mode 100644
index 0000000..bb2e9fc
--- /dev/null
+++ b/tools/libxc/saverestore/common_x86_pv.h
@@ -0,0 +1,144 @@
+#ifndef __COMMON_X86_PV_H
+#define __COMMON_X86_PV_H
+
+#include "common_x86.h"
+
+/* Gets a field from an *_any union */
+#define GET_FIELD(_c, _p, _f)                   \
+    ({ (_c)->x86_pv.width == 8 ?                \
+            (_p)->x64._f:                       \
+            (_p)->x32._f;                       \
+    })                                          \
+
+/* Gets a field from an *_any union */
+#define SET_FIELD(_c, _p, _f, _v)               \
+    ({ if ( (_c)->x86_pv.width == 8 )           \
+            (_p)->x64._f = (_v);                \
+        else                                    \
+            (_p)->x32._f = (_v);                \
+    })
+
+/* memcpy field _f from _s to _d, of an *_any union */
+#define MEMCPY_FIELD(_c, _d, _s, _f)                                    \
+    ({ if ( (_c)->x86_pv.width == 8 )                                   \
+            memcpy(&(_d)->x64._f, &(_s)->x64._f, sizeof((_d)->x64._f)); \
+        else                                                            \
+            memcpy(&(_d)->x32._f, &(_s)->x32._f, sizeof((_d)->x32._f)); \
+    })
+
+/* memset array field _f with value _v, from an *_any union */
+#define MEMSET_ARRAY_FIELD(_c, _d, _f, _v)                              \
+    ({ if ( (_c)->x86_pv.width == 8 )                                   \
+           memset(&(_d)->x64._f[0], (_v), sizeof((_d)->x64._f));        \
+       else                                                             \
+           memset(&(_d)->x32._f[0], (_v), sizeof((_d)->x32._f));        \
+    })
+
+/*
+ * Convert an mfn to a pfn, given Xens m2p table.
+ *
+ * Caller must ensure that the requested mfn is in range.
+ */
+xen_pfn_t mfn_to_pfn(struct context *ctx, xen_pfn_t mfn);
+
+/*
+ * Convert a pfn to an mfn, given the guests p2m table.
+ *
+ * Caller must ensure that the requested pfn is in range.
+ */
+xen_pfn_t pfn_to_mfn(struct context *ctx, xen_pfn_t pfn);
+
+/*
+ * Set a mapping in the p2m table.
+ *
+ * Caller must ensure that the requested pfn is in range.
+ */
+void set_p2m(struct context *ctx, xen_pfn_t pfn, xen_pfn_t mfn);
+
+/*
+ * Query whether a particular mfn is valid in the physmap of a guest.
+ */
+bool mfn_in_pseudophysmap(struct context *ctx, xen_pfn_t mfn);
+
+/*
+ * Debug a particular mfn by walking the p2m and m2p.
+ */
+void dump_bad_pseudophysmap_entry(struct context *ctx, xen_pfn_t mfn);
+
+/*
+ * Convert a PV cr3 field to an mfn.
+ *
+ * Adjusts for Xen's extended-cr3 format to pack a 44bit physical address into
+ * a 32bit architectural cr3.
+ */
+xen_pfn_t cr3_to_mfn(struct context *ctx, uint64_t cr3);
+
+/*
+ * Convert an mfn to a PV cr3 field.
+ *
+ * Adjusts for Xen's extended-cr3 format to pack a 44bit physical address into
+ * a 32bit architectural cr3.
+ */
+uint64_t mfn_to_cr3(struct context *ctx, xen_pfn_t mfn);
+
+/*
+ * Extract an mfn from a Pagetable Entry.
+ */
+static inline xen_pfn_t pte_to_frame(struct context *ctx, uint64_t pte)
+{
+    if ( ctx->x86_pv.width == 8 )
+        return (pte >> PAGE_SHIFT) & ((1ULL << (52 - PAGE_SHIFT)) - 1);
+    else
+        return (pte >> PAGE_SHIFT) & ((1ULL << (44 - PAGE_SHIFT)) - 1);
+}
+
+/*
+ * Change the mfn in a Pagetable Entry while leaving the flags alone.
+ */
+static inline void update_pte(struct context *ctx, uint64_t *pte, xen_pfn_t mfn)
+{
+    if ( ctx->x86_pv.width == 8 )
+        *pte &= ~(((1ULL << (52 - PAGE_SHIFT)) - 1) << PAGE_SHIFT);
+    else
+        *pte &= ~(((1ULL << (44 - PAGE_SHIFT)) - 1) << PAGE_SHIFT);
+
+    *pte |= (uint64_t)mfn << PAGE_SHIFT;
+}
+
+/*
+ * Get current domain information.
+ *
+ * Fills ctx->x86_pv
+ * - .width
+ * - .levels
+ * - .fpp
+ * - .p2m_frames
+ *
+ * Used by the save side to create the X86_PV_INFO record, and by the restore
+ * side to verify the incoming stream.
+ *
+ * Returns 0 on success and non-zero on error.
+ */
+int x86_pv_domain_info(struct context *ctx);
+
+/*
+ * Maps the Xen M2P.
+ *
+ * Fills ctx->x86_pv.
+ * - .max_mfn
+ * - .m2p
+ *
+ * Returns 0 on success and non-zero on error.
+ */
+int x86_pv_map_m2p(struct context *ctx);
+
+#endif
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
-- 
1.7.10.4