On Mon, Oct 14, 2024 at 04:46:16PM +0200, David Hildenbrand wrote:
> To support memory devices under QEMU/KVM, such as virtio-mem,
> we have to prepare our kernel virtual address space accordingly and
> have to know the highest possible physical memory address we might see
> later: the storage limit. The good old SCLP interface is not suitable for
> this use case.
>
> In particular, memory owned by memory devices has no relationship to
> storage increments, it is always detected using the device driver, and
> unaware OSes (no driver) must never try making use of that memory.
> Consequently this memory is located outside of the "maximum storage
> increment"-indicated memory range.
>
> Let's use our new diag500 STORAGE_LIMIT subcode to query this storage
> limit that can exceed the "maximum storage increment", and use the
> existing interfaces (i.e., SCLP) to obtain information about the initial
> memory that is not owned+managed by memory devices.
>
> If a hypervisor does not support such memory devices, the address exposed
> through diag500 STORAGE_LIMIT will correspond to the maximum storage
> increment exposed through SCLP.
>
> To teach kdump on s390 to include memory owned by memory devices, there
> will be ways to query the relevant memory ranges from the device via a
> driver running in special kdump mode (like virtio-mem already implements
> to filter /proc/vmcore access so we don't end up reading from unplugged
> device blocks).
>
> Tested-by: Mario Casquero <mcasquer@xxxxxxxxxx>
> Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
> ---
> arch/s390/boot/physmem_info.c | 46 ++++++++++++++++++++++++++--
> arch/s390/include/asm/physmem_info.h | 3 ++
> 2 files changed, 46 insertions(+), 3 deletions(-)
...
> +static int diag500_storage_limit(unsigned long *max_physmem_end)
> +{
> + register unsigned long __nr asm("1") = 0x4;
> + register unsigned long __storage_limit asm("2") = 0;
> + unsigned long reg1, reg2;
> + psw_t old;
In general we do not allow register asm usage anymore in s390 code,
except for a very few defined places. This is due to all the problems
that we've seen with code instrumentation and register corruption.
The patch below changes your code accordingly, but it is
untested. Please verify that your code still works.
> @@ -157,7 +189,9 @@ unsigned long detect_max_physmem_end(void)
> {
> unsigned long max_physmem_end = 0;
>
> - if (!sclp_early_get_memsize(&max_physmem_end)) {
> + if (!diag500_storage_limit(&max_physmem_end)) {
> + physmem_info.info_source = MEM_DETECT_DIAG500_STOR_LIMIT;
> + } else if (!sclp_early_get_memsize(&max_physmem_end)) {
> physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO;
> } else {
> max_physmem_end = search_mem_end();
> @@ -170,11 +204,17 @@ void detect_physmem_online_ranges(unsigned long max_physmem_end)
> {
> if (!sclp_early_read_storage_info()) {
> physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO;
> + return;
> } else if (!diag260()) {
> physmem_info.info_source = MEM_DETECT_DIAG260;
> - } else if (max_physmem_end) {
> - add_physmem_online_range(0, max_physmem_end);
> + return;
> + } else if (physmem_info.info_source == MEM_DETECT_DIAG500_STOR_LIMIT) {
> + max_physmem_end = 0;
> + if (!sclp_early_get_memsize(&max_physmem_end))
> + physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO;
> }
> + if (max_physmem_end)
> + add_physmem_online_range(0, max_physmem_end);
> }
In general looks good to me, but I'd like to see that Vasily or
Alexander give an Ack to this patch.
diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c
index fb4e66e80fd8..975fc478e0e3 100644
--- a/arch/s390/boot/physmem_info.c
+++ b/arch/s390/boot/physmem_info.c
@@ -109,10 +109,11 @@ static int diag260(void)
return 0;
}
+#define DIAG500_SC_STOR_LIMIT 4
+
static int diag500_storage_limit(unsigned long *max_physmem_end)
{
- register unsigned long __nr asm("1") = 0x4;
- register unsigned long __storage_limit asm("2") = 0;
+ unsigned long storage_limit;
unsigned long reg1, reg2;
psw_t old;
@@ -123,21 +124,24 @@ static int diag500_storage_limit(unsigned long *max_physmem_end)
" st %[reg2],4(%[psw_pgm])\n"
" larl %[reg1],1f\n"
" stg %[reg1],8(%[psw_pgm])\n"
+ " lghi 1,%[subcode]\n"
+ " lghi 2,0\n"
" diag 2,4,0x500\n"
"1: mvc 0(16,%[psw_pgm]),0(%[psw_old])\n"
+ " lgr %[slimit],2\n"
: [reg1] "=&d" (reg1),
[reg2] "=&a" (reg2),
- "+&d" (__storage_limit),
+ [slimit] "=d" (storage_limit),
"=Q" (get_lowcore()->program_new_psw),
"=Q" (old)
: [psw_old] "a" (&old),
[psw_pgm] "a" (&get_lowcore()->program_new_psw),
- "d" (__nr)
- : "memory");
- if (!__storage_limit)
- return -EINVAL;
- /* convert inclusive end to exclusive end. */
- *max_physmem_end = __storage_limit + 1;
+ [subcode] "i" (DIAG500_SC_STOR_LIMIT)
+ : "memory", "1", "2");
+ if (!storage_limit)
+ return -EINVAL;
+ /* Convert inclusive end to exclusive end */
+ *max_physmem_end = storage_limit + 1;
return 0;
}
