Skip to content
  1. Feb 06, 2017
  3. Feb 03, 2017
  5. Feb 02, 2017
  7. Jan 31, 2017
  9. Jan 30, 2017
    • Alistair Popple's avatar
      powerpc/powernv: Use OPAL call for TCE kill on NVLink2 · 616badd2
      Alistair Popple authored 
      

Add detection of NPU2 PHBs. NPU2/NVLink2 has a different register
layout for the TCE kill register therefore TCE invalidation should be
done via the OPAL call rather than using the register directly as it
is for PHB3 and NVLink1. This changes TCE invalidation to use the OPAL
call in the case of a NPU2 PHB model.

Signed-off-by: default avatarAlistair Popple <alistair@popple.id.au>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      616badd2
    • Alistair Popple's avatar
      powerpc/powernv: Initialise nest mmu · 1d0761d2
      Alistair Popple authored 
      

POWER9 contains an off core mmu called the nest mmu (NMMU). This is
used by other hardware units on the chip to translate virtual
addresses into real addresses. The unit attempting an address
translation provides the majority of the context required for the
translation request except for the base address of the partition table
(ie. the PTCR) which needs to be programmed into the NMMU.

This patch adds a call to OPAL to set the PTCR for the nest mmu in
opal_init().

Signed-off-by: default avatarAlistair Popple <alistair@popple.id.au>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      1d0761d2
    • Reza Arbab's avatar
      powerpc/mm: Allow memory hotplug into an offline node · 2a8628d4
      Reza Arbab authored 
      Relax the check preventing us from hotplugging into an offline node.

This limitation was added in commit 482ec7c4

 ("[PATCH] powerpc numa:
Support sparse online node map") to prevent adding resources to an
uninitialized node.

These days, there is no harm in doing so. The addition will actually
cause the node to be initialized and onlined; add_memory_resource()
calls hotadd_new_pgdat() (if necessary) and node_set_online().

Signed-off-by: default avatarReza Arbab <arbab@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      2a8628d4
    • Reza Arbab's avatar
      powerpc/mm: Simplify loop control in parse_numa_properties() · 7656cd8e
      Reza Arbab authored 
      

The flow of the main loop in parse_numa_properties() is overly
complicated. Simplify it to be less confusing and easier to read.
No functional change.

The end of the main loop in parse_numa_properties() looks like this:

	for_each_node_by_type(...) {
		...
		if (!condition) {
			if (--ranges)
				goto new_range;
			else
				continue;
		}

		statement();

		if (--ranges)
			goto new_range;
		/* else
		 *	continue; <- implicit, this is the end of the loop
		 */
	}

The only effect of !condition is to skip execution of statement(). This
can be rewritten in a simpler way:

	for_each_node_by_type(...) {
		...
		if (condition)
			statement();

		if (--ranges)
			goto new_range;
	}

Signed-off-by: default avatarReza Arbab <arbab@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      7656cd8e
    • Mahesh Salgaonkar's avatar
      powerpc/fadump: Fix the race in crash_fadump(). · f2a5e8f0
      Mahesh Salgaonkar authored 
      

There are chances that multiple CPUs can call crash_fadump() simultaneously
and would start duplicating same info to vmcoreinfo ELF note section. This
causes makedumpfile to fail during kdump capture. One example is,
triggering dumprestart from HMC which sends system reset to all the CPUs at
once.

makedumpfile --dump-dmesg /proc/vmcore
read_vmcoreinfo_basic_info: Invalid data in /tmp/vmcoreinfoyjgxlL: CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971
makedumpfile Failed.
Running makedumpfile --dump-dmesg /proc/vmcore failed (1).

makedumpfile  -d 31 -l /proc/vmcore
read_vmcoreinfo_basic_info: Invalid data in /tmp/vmcoreinfo1mmVdO: CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971CRASHTIME=1475605971
makedumpfile Failed.
Running makedumpfile  -d 31 -l /proc/vmcore failed (1).

Signed-off-by: default avatarMahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      f2a5e8f0