ieee1275: Request memory with ibm, client-architecture-support

On PowerVM, the first time we boot a Linux partition, we may only get
256MB of real memory area, even if the partition has more memory.

This isn't enough to reliably verify a kernel. Fortunately, the Power
Architecture Platform Reference (PAPR) defines a method we can call to ask
for more memory: the broad and powerful ibm,client-architecture-support
(CAS) method.

CAS can do an enormous amount of things on a PAPR platform: as well as
asking for memory, you can set the supported processor level, the interrupt
controller, hash vs radix mmu, and so on.

If:

 - we are running under what we think is PowerVM (compatible property of /
   begins with "IBM"), and

 - the full amount of RMA is less than 512MB (as determined by the reg
   property of /memory)

then call CAS as follows: (refer to the Linux on Power Architecture
Reference, LoPAR, which is public, at B.5.2.3):

 - Use the "any" PVR value and supply 2 option vectors.

 - Set option vector 1 (PowerPC Server Processor Architecture Level)
   to "ignore".

 - Set option vector 2 with default or Linux-like options, including a
   min-rma-size of 512MB.

 - Set option vector 3 to request Floating Point, VMX and Decimal Floating
   point, but don't abort the boot if we can't get them.

 - Set option vector 4 to request a minimum VP percentage to 1%, which is
   what Linux requests, and is below the default of 10%. Without this,
   some systems with very large or very small configurations fail to boot.

This will cause a CAS reboot and the partition will restart with 512MB
of RMA. Importantly, grub will notice the 512MB and not call CAS again.

Notes about the choices of parameters:

 - A partition can be configured with only 256MB of memory, which would
   mean this request couldn't be satisfied, but PFW refuses to load with
   only 256MB of memory, so it's a bit moot. SLOF will run fine with 256MB,
   but we will never call CAS under qemu/SLOF because /compatible won't
   begin with "IBM".)

 - unspecified CAS vectors take on default values. Some of these values
   might restrict the ability of certain hardware configurations to boot.
   This is why we need to specify the VP percentage in vector 4, which is
   in turn why we need to specify vector 3.

Finally, we should have enough memory to verify a kernel, and we will
reach Linux. One of the first things Linux does while still running under
OpenFirmware is to call CAS with a much fuller set of options (including
asking for 512MB of memory). Linux includes a much more restrictive set of
PVR values and processor support levels, and this CAS invocation will likely
induce another reboot. On this reboot grub will again notice the higher RMA,
and not call CAS. We will get to Linux again, Linux will call CAS again, but
because the values are now set for Linux this will not induce another CAS
reboot and we will finally boot all the way to userspace.

On all subsequent boots, everything will be configured with 512MB of RMA,
so there will be no further CAS reboots from grub. (phyp is super sticky
with the RMA size - it persists even on cold boots. So if you've ever booted
Linux in a partition, you'll probably never have grub call CAS. It'll only
ever fire the first time a partition loads grub, or if you deliberately lower
the amount of memory your partition has below 512MB.)

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Stefan Berger <stefanb@linux.ibm.com>
Reviewed-by: Daniel Kiper <daniel.kiper@oracle.com>
Tested-by: Nageswara R Sastry <rnsastry@linux.ibm.com>
Reviewed-by: Robbie Harwood <rharwood@redhat.com>

diff --git a/grub-core/kern/ieee1275/cmain.c b/grub-core/kern/ieee1275/cmain.c
index 4442b6a831934ccfe6b6df4d230099842d1e427a..400d85d28ab601fffd60d7b5034b8566c52f0c0b 100644 (file)
--- a/grub-core/kern/ieee1275/cmain.c
+++ b/grub-core/kern/ieee1275/cmain.c
@@ -123,6 +123,11 @@ grub_ieee1275_find_options (void)
              break;
            }
        }
+
+#if defined(__powerpc__)
+      if (grub_strncmp (tmp, "IBM,", 4) == 0)
+       grub_ieee1275_set_flag (GRUB_IEEE1275_FLAG_CAN_TRY_CAS_FOR_MORE_MEMORY);
+#endif
     }
 
   if (is_smartfirmware)

diff --git a/grub-core/kern/ieee1275/init.c b/grub-core/kern/ieee1275/init.c
index 2adf4fdfc0e7c19837b8ed9640f6a1baceeffc90..0bc571e3e562f115d2e160c4aff644c90499be9b 100644 (file)
--- a/grub-core/kern/ieee1275/init.c
+++ b/grub-core/kern/ieee1275/init.c
@@ -200,11 +200,176 @@ heap_init (grub_uint64_t addr, grub_uint64_t len, grub_memory_type_t type,
   return 0;
 }
 
+/*
+ * How much memory does OF believe it has? (regardless of whether
+ * it's accessible or not)
+ */
+static grub_err_t
+grub_ieee1275_total_mem (grub_uint64_t *total)
+{
+  grub_ieee1275_phandle_t root;
+  grub_ieee1275_phandle_t memory;
+  grub_uint32_t reg[4];
+  grub_ssize_t reg_size;
+  grub_uint32_t address_cells = 1;
+  grub_uint32_t size_cells = 1;
+  grub_uint64_t size;
+
+  /* If we fail to get to the end, report 0. */
+  *total = 0;
+
+  /* Determine the format of each entry in `reg'.  */
+  if (grub_ieee1275_finddevice ("/", &root))
+    return grub_error (GRUB_ERR_UNKNOWN_DEVICE, "couldn't find / node");
+  if (grub_ieee1275_get_integer_property (root, "#address-cells", &address_cells,
+                                         sizeof (address_cells), 0))
+    return grub_error (GRUB_ERR_UNKNOWN_DEVICE, "couldn't examine #address-cells");
+  if (grub_ieee1275_get_integer_property (root, "#size-cells", &size_cells,
+                                         sizeof (size_cells), 0))
+    return grub_error (GRUB_ERR_UNKNOWN_DEVICE, "couldn't examine #size-cells");
+
+  if (size_cells > address_cells)
+    address_cells = size_cells;
+
+  /* Load `/memory/reg'.  */
+  if (grub_ieee1275_finddevice ("/memory", &memory))
+    return grub_error (GRUB_ERR_UNKNOWN_DEVICE, "couldn't find /memory node");
+  if (grub_ieee1275_get_integer_property (memory, "reg", reg,
+                                         sizeof (reg), &reg_size))
+    return grub_error (GRUB_ERR_UNKNOWN_DEVICE, "couldn't examine /memory/reg property");
+  if (reg_size < 0 || (grub_size_t) reg_size > sizeof (reg))
+    return grub_error (GRUB_ERR_UNKNOWN_DEVICE, "/memory response buffer exceeded");
+
+  if (grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_BROKEN_ADDRESS_CELLS))
+    {
+      address_cells = 1;
+      size_cells = 1;
+    }
+
+  /* Decode only the size */
+  size = reg[address_cells];
+  if (size_cells == 2)
+    size = (size << 32) | reg[address_cells + 1];
+
+  *total = size;
+
+  return grub_errno;
+}
+
+#if defined(__powerpc__)
+
+/* See PAPR or arch/powerpc/kernel/prom_init.c */
+struct option_vector2
+{
+  grub_uint8_t byte1;
+  grub_uint16_t reserved;
+  grub_uint32_t real_base;
+  grub_uint32_t real_size;
+  grub_uint32_t virt_base;
+  grub_uint32_t virt_size;
+  grub_uint32_t load_base;
+  grub_uint32_t min_rma;
+  grub_uint32_t min_load;
+  grub_uint8_t min_rma_percent;
+  grub_uint8_t max_pft_size;
+} GRUB_PACKED;
+
+struct pvr_entry
+{
+  grub_uint32_t mask;
+  grub_uint32_t entry;
+};
+
+struct cas_vector
+{
+  struct
+  {
+    struct pvr_entry terminal;
+  } pvr_list;
+  grub_uint8_t num_vecs;
+  grub_uint8_t vec1_size;
+  grub_uint8_t vec1;
+  grub_uint8_t vec2_size;
+  struct option_vector2 vec2;
+  grub_uint8_t vec3_size;
+  grub_uint16_t vec3;
+  grub_uint8_t vec4_size;
+  grub_uint16_t vec4;
+} GRUB_PACKED;
+
+/*
+ * Call ibm,client-architecture-support to try to get more RMA.
+ * We ask for 512MB which should be enough to verify a distro kernel.
+ * We ignore most errors: if we don't succeed we'll proceed with whatever
+ * memory we have.
+ */
+static void
+grub_ieee1275_ibm_cas (void)
+{
+  int rc;
+  grub_ieee1275_ihandle_t root;
+  struct cas_args
+  {
+    struct grub_ieee1275_common_hdr common;
+    grub_ieee1275_cell_t method;
+    grub_ieee1275_ihandle_t ihandle;
+    grub_ieee1275_cell_t cas_addr;
+    grub_ieee1275_cell_t result;
+  } args;
+  struct cas_vector vector =
+  {
+    .pvr_list = { { 0x00000000, 0xffffffff } }, /* any processor */
+    .num_vecs = 4 - 1,
+    .vec1_size = 0,
+    .vec1 = 0x80, /* ignore */
+    .vec2_size = 1 + sizeof (struct option_vector2) - 2,
+    .vec2 = {
+      0, 0, -1, -1, -1, -1, -1, 512, -1, 0, 48
+    },
+    .vec3_size = 2 - 1,
+    .vec3 = 0x00e0, /* ask for FP + VMX + DFP but don't halt if unsatisfied */
+    .vec4_size = 2 - 1,
+    .vec4 = 0x0001, /* set required minimum capacity % to the lowest value */
+  };
+
+  INIT_IEEE1275_COMMON (&args.common, "call-method", 3, 2);
+  args.method = (grub_ieee1275_cell_t) "ibm,client-architecture-support";
+  rc = grub_ieee1275_open ("/", &root);
+  if (rc)
+    {
+      grub_error (GRUB_ERR_IO, "could not open root when trying to call CAS");
+      return;
+    }
+  args.ihandle = root;
+  args.cas_addr = (grub_ieee1275_cell_t) &vector;
+
+  grub_printf ("Calling ibm,client-architecture-support from grub...");
+  IEEE1275_CALL_ENTRY_FN (&args);
+  grub_printf ("done\n");
+
+  grub_ieee1275_close (root);
+}
+
+#endif /* __powerpc__ */
+
 static void
 grub_claim_heap (void)
 {
   unsigned long total = 0;
 
+#if defined(__powerpc__)
+  if (grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_CAN_TRY_CAS_FOR_MORE_MEMORY))
+    {
+      grub_uint64_t rma_size;
+      grub_err_t err;
+
+      err = grub_ieee1275_total_mem (&rma_size);
+      /* if we have an error, don't call CAS, just hope for the best */
+      if (err == GRUB_ERR_NONE && rma_size < (512 * 1024 * 1024))
+       grub_ieee1275_ibm_cas ();
+    }
+#endif
+
   grub_machine_mmap_iterate (heap_init, &total);
 }
 #endif

diff --git a/include/grub/ieee1275/ieee1275.h b/include/grub/ieee1275/ieee1275.h
index f53228703bdb0c33a28737e1a720ab2608c9e3ee..77e4e61e5ba1e34acb3818263d4e7d2a83409a3f 100644 (file)
--- a/include/grub/ieee1275/ieee1275.h
+++ b/include/grub/ieee1275/ieee1275.h
@@ -128,6 +128,16 @@ enum grub_ieee1275_flag
   GRUB_IEEE1275_FLAG_CURSORONOFF_ANSI_BROKEN,
 
   GRUB_IEEE1275_FLAG_RAW_DEVNAMES,
+
+#if defined(__powerpc__)
+  /*
+   * On PFW, the first time we boot a Linux partition, we may only get 256MB of
+   * real memory area, even if the partition has more memory. Set this flag if
+   * we think we're running under PFW. Then, if this flag is set, and the RMA is
+   * only 256MB in size, try asking for more with CAS.
+   */
+  GRUB_IEEE1275_FLAG_CAN_TRY_CAS_FOR_MORE_MEMORY,
+#endif
 };
 
 extern int EXPORT_FUNC(grub_ieee1275_test_flag) (enum grub_ieee1275_flag flag);