linux/arch/powerpc/kernel/paca.c

365 lines
9.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* c 2001 PPC 64 Team, IBM Corp
*/
#include <linux/smp.h>
#include <linux/export.h>
#include <linux/memblock.h>
#include <linux/sched/task.h>
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:58 +08:00
#include <linux/numa.h>
mm: reorder includes after introduction of linux/pgtable.h The replacement of <asm/pgrable.h> with <linux/pgtable.h> made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s <file> <header>" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include <linux/%s>" % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include <linux/"): in_hdrs = True elif not moved and in_hdrs: moved = True print hdr_to_move print line Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 12:32:42 +08:00
#include <linux/pgtable.h>
#include <asm/lppaca.h>
#include <asm/paca.h>
2008-08-30 09:43:47 +08:00
#include <asm/sections.h>
#include <asm/kexec.h>
#include <asm/svm.h>
#include <asm/ultravisor.h>
powerpc/rtas: Implement reentrant rtas call Implement rtas_call_reentrant() for reentrant rtas-calls: "ibm,int-on", "ibm,int-off",ibm,get-xive" and "ibm,set-xive". On LoPAPR Version 1.1 (March 24, 2016), from 7.3.10.1 to 7.3.10.4, items 2 and 3 say: 2 - For the PowerPC External Interrupt option: The * call must be reentrant to the number of processors on the platform. 3 - For the PowerPC External Interrupt option: The * argument call buffer for each simultaneous call must be physically unique. So, these rtas-calls can be called in a lockless way, if using a different buffer for each cpu doing such rtas call. For this, it was suggested to add the buffer (struct rtas_args) in the PACA struct, so each cpu can have it's own buffer. The PACA struct received a pointer to rtas buffer, which is allocated in the memory range available to rtas 32-bit. Reentrant rtas calls are useful to avoid deadlocks in crashing, where rtas-calls are needed, but some other thread crashed holding the rtas.lock. This is a backtrace of a deadlock from a kdump testing environment: #0 arch_spin_lock #1 lock_rtas () #2 rtas_call (token=8204, nargs=1, nret=1, outputs=0x0) #3 ics_rtas_mask_real_irq (hw_irq=4100) #4 machine_kexec_mask_interrupts #5 default_machine_crash_shutdown #6 machine_crash_shutdown #7 __crash_kexec #8 crash_kexec #9 oops_end Signed-off-by: Leonardo Bras <leobras.c@gmail.com> [mpe: Move under #ifdef PSERIES to avoid build breakage] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200518234245.200672-3-leobras.c@gmail.com
2020-05-19 07:42:45 +08:00
#include <asm/rtas.h>
#include "setup.h"
#ifndef CONFIG_SMP
#define boot_cpuid 0
#endif
static void *__init alloc_paca_data(unsigned long size, unsigned long align,
unsigned long limit, int cpu)
{
powerpc: prefer memblock APIs returning virtual address Patch series "memblock: simplify several early memory allocation", v4. These patches simplify some of the early memory allocations by replacing usage of older memblock APIs with newer and shinier ones. Quite a few places in the arch/ code allocated memory using a memblock API that returns a physical address of the allocated area, then converted this physical address to a virtual one and then used memset(0) to clear the allocated range. More recent memblock APIs do all the three steps in one call and their usage simplifies the code. It's important to note that regardless of API used, the core allocation is nearly identical for any set of memblock allocators: first it tries to find a free memory with all the constraints specified by the caller and then falls back to the allocation with some or all constraints disabled. The first three patches perform the conversion of call sites that have exact requirements for the node and the possible memory range. The fourth patch is a bit one-off as it simplifies openrisc's implementation of pte_alloc_one_kernel(), and not only the memblock usage. The fifth patch takes care of simpler cases when the allocation can be satisfied with a simple call to memblock_alloc(). The sixth patch removes one-liner wrappers for memblock_alloc on arm and unicore32, as suggested by Christoph. This patch (of 6): There are a several places that allocate memory using memblock APIs that return a physical address, convert the returned address to the virtual address and frequently also memset(0) the allocated range. Update these places to use memblock allocators already returning a virtual address. Use memblock functions that clear the allocated memory instead of calling memset(0) where appropriate. The calls to memblock_alloc_base() that were not followed by memset(0) are replaced with memblock_alloc_try_nid_raw(). Since the latter does not panic() when the allocation fails, the appropriate panic() calls are added to the call sites. Link: http://lkml.kernel.org/r/1546248566-14910-2-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Greentime Hu <green.hu@gmail.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@suse.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Mark Salter <msalter@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Stafford Horne <shorne@gmail.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Simek <michal.simek@xilinx.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-08 08:30:48 +08:00
void *ptr;
int nid;
/*
* boot_cpuid paca is allocated very early before cpu_to_node is up.
* Set bottom-up mode, because the boot CPU should be on node-0,
* which will put its paca in the right place.
*/
if (cpu == boot_cpuid) {
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:58 +08:00
nid = NUMA_NO_NODE;
memblock_set_bottom_up(true);
} else {
nid = early_cpu_to_node(cpu);
}
powerpc: prefer memblock APIs returning virtual address Patch series "memblock: simplify several early memory allocation", v4. These patches simplify some of the early memory allocations by replacing usage of older memblock APIs with newer and shinier ones. Quite a few places in the arch/ code allocated memory using a memblock API that returns a physical address of the allocated area, then converted this physical address to a virtual one and then used memset(0) to clear the allocated range. More recent memblock APIs do all the three steps in one call and their usage simplifies the code. It's important to note that regardless of API used, the core allocation is nearly identical for any set of memblock allocators: first it tries to find a free memory with all the constraints specified by the caller and then falls back to the allocation with some or all constraints disabled. The first three patches perform the conversion of call sites that have exact requirements for the node and the possible memory range. The fourth patch is a bit one-off as it simplifies openrisc's implementation of pte_alloc_one_kernel(), and not only the memblock usage. The fifth patch takes care of simpler cases when the allocation can be satisfied with a simple call to memblock_alloc(). The sixth patch removes one-liner wrappers for memblock_alloc on arm and unicore32, as suggested by Christoph. This patch (of 6): There are a several places that allocate memory using memblock APIs that return a physical address, convert the returned address to the virtual address and frequently also memset(0) the allocated range. Update these places to use memblock allocators already returning a virtual address. Use memblock functions that clear the allocated memory instead of calling memset(0) where appropriate. The calls to memblock_alloc_base() that were not followed by memset(0) are replaced with memblock_alloc_try_nid_raw(). Since the latter does not panic() when the allocation fails, the appropriate panic() calls are added to the call sites. Link: http://lkml.kernel.org/r/1546248566-14910-2-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Greentime Hu <green.hu@gmail.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@suse.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Mark Salter <msalter@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Stafford Horne <shorne@gmail.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Simek <michal.simek@xilinx.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-08 08:30:48 +08:00
ptr = memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
limit, nid);
if (!ptr)
panic("cannot allocate paca data");
if (cpu == boot_cpuid)
memblock_set_bottom_up(false);
powerpc: prefer memblock APIs returning virtual address Patch series "memblock: simplify several early memory allocation", v4. These patches simplify some of the early memory allocations by replacing usage of older memblock APIs with newer and shinier ones. Quite a few places in the arch/ code allocated memory using a memblock API that returns a physical address of the allocated area, then converted this physical address to a virtual one and then used memset(0) to clear the allocated range. More recent memblock APIs do all the three steps in one call and their usage simplifies the code. It's important to note that regardless of API used, the core allocation is nearly identical for any set of memblock allocators: first it tries to find a free memory with all the constraints specified by the caller and then falls back to the allocation with some or all constraints disabled. The first three patches perform the conversion of call sites that have exact requirements for the node and the possible memory range. The fourth patch is a bit one-off as it simplifies openrisc's implementation of pte_alloc_one_kernel(), and not only the memblock usage. The fifth patch takes care of simpler cases when the allocation can be satisfied with a simple call to memblock_alloc(). The sixth patch removes one-liner wrappers for memblock_alloc on arm and unicore32, as suggested by Christoph. This patch (of 6): There are a several places that allocate memory using memblock APIs that return a physical address, convert the returned address to the virtual address and frequently also memset(0) the allocated range. Update these places to use memblock allocators already returning a virtual address. Use memblock functions that clear the allocated memory instead of calling memset(0) where appropriate. The calls to memblock_alloc_base() that were not followed by memset(0) are replaced with memblock_alloc_try_nid_raw(). Since the latter does not panic() when the allocation fails, the appropriate panic() calls are added to the call sites. Link: http://lkml.kernel.org/r/1546248566-14910-2-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Greentime Hu <green.hu@gmail.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@suse.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Mark Salter <msalter@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Stafford Horne <shorne@gmail.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Simek <michal.simek@xilinx.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-08 08:30:48 +08:00
return ptr;
}
#ifdef CONFIG_PPC_PSERIES
#define LPPACA_SIZE 0x400
static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit,
int cpu)
{
size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE);
static unsigned long shared_lppaca_size;
static void *shared_lppaca;
void *ptr;
if (!shared_lppaca) {
memblock_set_bottom_up(true);
/*
* See Documentation/powerpc/ultravisor.rst for more details.
*
* UV/HV data sharing is in PAGE_SIZE granularity. In order to
* minimize the number of pages shared, align the allocation to
* PAGE_SIZE.
*/
shared_lppaca =
memblock_alloc_try_nid(shared_lppaca_total_size,
PAGE_SIZE, MEMBLOCK_LOW_LIMIT,
limit, NUMA_NO_NODE);
if (!shared_lppaca)
panic("cannot allocate shared data");
memblock_set_bottom_up(false);
uv_share_page(PHYS_PFN(__pa(shared_lppaca)),
shared_lppaca_total_size >> PAGE_SHIFT);
}
ptr = shared_lppaca + shared_lppaca_size;
shared_lppaca_size += size;
/*
* This is very early in boot, so no harm done if the kernel crashes at
* this point.
*/
BUG_ON(shared_lppaca_size > shared_lppaca_total_size);
return ptr;
}
/*
* See asm/lppaca.h for more detail.
*
* lppaca structures must must be 1kB in size, L1 cache line aligned,
* and not cross 4kB boundary. A 1kB size and 1kB alignment will satisfy
* these requirements.
*/
static inline void init_lppaca(struct lppaca *lppaca)
{
BUILD_BUG_ON(sizeof(struct lppaca) != 640);
*lppaca = (struct lppaca) {
.desc = cpu_to_be32(0xd397d781), /* "LpPa" */
.size = cpu_to_be16(LPPACA_SIZE),
.fpregs_in_use = 1,
.slb_count = cpu_to_be16(64),
.vmxregs_in_use = 0,
.page_ins = 0, };
};
static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
{
struct lppaca *lp;
BUILD_BUG_ON(sizeof(struct lppaca) > LPPACA_SIZE);
if (early_cpu_has_feature(CPU_FTR_HVMODE))
return NULL;
if (is_secure_guest())
lp = alloc_shared_lppaca(LPPACA_SIZE, limit, cpu);
else
lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu);
init_lppaca(lp);
return lp;
}
#endif /* CONFIG_PPC_PSERIES */
#ifdef CONFIG_PPC_BOOK3S_64
/*
* 3 persistent SLBs are allocated here. The buffer will be zero
* initially, hence will all be invaild until we actually write them.
*
* If you make the number of persistent SLB entries dynamic, please also
* update PR KVM to flush and restore them accordingly.
*/
static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
{
struct slb_shadow *s;
if (cpu != boot_cpuid) {
/*
* Boot CPU comes here before early_radix_enabled
* is parsed (e.g., for disable_radix). So allocate
* always and this will be fixed up in free_unused_pacas.
*/
if (early_radix_enabled())
return NULL;
}
s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
s->buffer_length = cpu_to_be32(sizeof(*s));
return s;
}
#endif /* CONFIG_PPC_BOOK3S_64 */
powerpc/rtas: Implement reentrant rtas call Implement rtas_call_reentrant() for reentrant rtas-calls: "ibm,int-on", "ibm,int-off",ibm,get-xive" and "ibm,set-xive". On LoPAPR Version 1.1 (March 24, 2016), from 7.3.10.1 to 7.3.10.4, items 2 and 3 say: 2 - For the PowerPC External Interrupt option: The * call must be reentrant to the number of processors on the platform. 3 - For the PowerPC External Interrupt option: The * argument call buffer for each simultaneous call must be physically unique. So, these rtas-calls can be called in a lockless way, if using a different buffer for each cpu doing such rtas call. For this, it was suggested to add the buffer (struct rtas_args) in the PACA struct, so each cpu can have it's own buffer. The PACA struct received a pointer to rtas buffer, which is allocated in the memory range available to rtas 32-bit. Reentrant rtas calls are useful to avoid deadlocks in crashing, where rtas-calls are needed, but some other thread crashed holding the rtas.lock. This is a backtrace of a deadlock from a kdump testing environment: #0 arch_spin_lock #1 lock_rtas () #2 rtas_call (token=8204, nargs=1, nret=1, outputs=0x0) #3 ics_rtas_mask_real_irq (hw_irq=4100) #4 machine_kexec_mask_interrupts #5 default_machine_crash_shutdown #6 machine_crash_shutdown #7 __crash_kexec #8 crash_kexec #9 oops_end Signed-off-by: Leonardo Bras <leobras.c@gmail.com> [mpe: Move under #ifdef PSERIES to avoid build breakage] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200518234245.200672-3-leobras.c@gmail.com
2020-05-19 07:42:45 +08:00
#ifdef CONFIG_PPC_PSERIES
/**
* new_rtas_args() - Allocates rtas args
* @cpu: CPU number
* @limit: Memory limit for this allocation
*
* Allocates a struct rtas_args and return it's pointer,
* if not in Hypervisor mode
*
* Return: Pointer to allocated rtas_args
* NULL if CPU in Hypervisor Mode
*/
static struct rtas_args * __init new_rtas_args(int cpu, unsigned long limit)
{
limit = min_t(unsigned long, limit, RTAS_INSTANTIATE_MAX);
if (early_cpu_has_feature(CPU_FTR_HVMODE))
return NULL;
return alloc_paca_data(sizeof(struct rtas_args), L1_CACHE_BYTES,
limit, cpu);
}
#endif /* CONFIG_PPC_PSERIES */
/* The Paca is an array with one entry per processor. Each contains an
* lppaca, which contains the information shared between the
* hypervisor and Linux.
* On systems with hardware multi-threading, there are two threads
* per processor. The Paca array must contain an entry for each thread.
* The VPD Areas will give a max logical processors = 2 * max physical
* processors. The processor VPD array needs one entry per physical
* processor (not thread).
*/
struct paca_struct **paca_ptrs __read_mostly;
EXPORT_SYMBOL(paca_ptrs);
powerpc/64: Prevent stack protection in early boot The previous commit reduced the amount of code that is run before we setup a paca. However there are still a few remaining functions that run with no paca, or worse, with an arbitrary value in r13 that will be used as a paca pointer. In particular the stack protector canary is stored in the paca, so if stack protector is activated for any of these functions we will read the stack canary from wherever r13 points. If r13 happens to point outside of memory we will get a machine check / checkstop. For example if we modify initialise_paca() to trigger stack protection, and then boot in the mambo simulator with r13 poisoned in skiboot before calling the kernel: DEBUG: 19952232: (19952232): INSTRUCTION: PC=0xC0000000191FC1E8: [0x3C4C006D]: addis r2,r12,0x6D [fetch] DEBUG: 19952236: (19952236): INSTRUCTION: PC=0xC00000001807EAD8: [0x7D8802A6]: mflr r12 [fetch] FATAL ERROR: 19952276: (19952276): Check Stop for 0:0: Machine Check with ME bit of MSR off DEBUG: 19952276: (19952276): INSTRUCTION: PC=0xC0000000191FCA7C: [0xE90D0CF8]: ld r8,0xCF8(r13) [Instruction Failed] INFO: 19952276: (19952277): ** Execution stopped: Mambo Error, Machine Check Stop, ** systemsim % bt pc: 0xC0000000191FCA7C initialise_paca+0x54 lr: 0xC0000000191FC22C early_setup+0x44 stack:0x00000000198CBED0 0x0 +0x0 stack:0x00000000198CBF00 0xC0000000191FC22C early_setup+0x44 stack:0x00000000198CBF90 0x1801C968 +0x1801C968 So annotate the relevant functions to ensure stack protection is never enabled for them. Fixes: 06ec27aea9fc ("powerpc/64: add stack protector support") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200320032116.1024773-2-mpe@ellerman.id.au
2020-03-20 11:21:16 +08:00
void __init __nostackprotector initialise_paca(struct paca_struct *new_paca, int cpu)
{
#ifdef CONFIG_PPC_PSERIES
new_paca->lppaca_ptr = NULL;
#endif
#ifdef CONFIG_PPC_BOOK3E
new_paca->kernel_pgd = swapper_pg_dir;
#endif
new_paca->lock_token = 0x8000;
new_paca->paca_index = cpu;
new_paca->kernel_toc = kernel_toc_addr();
new_paca->kernelbase = (unsigned long) _stext;
/* Only set MSR:IR/DR when MMU is initialized */
new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR);
new_paca->hw_cpu_id = 0xffff;
new_paca->kexec_state = KEXEC_STATE_NONE;
new_paca->__current = &init_task;
new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL;
#ifdef CONFIG_PPC_BOOK3S_64
new_paca->slb_shadow_ptr = NULL;
#endif
#ifdef CONFIG_PPC_BOOK3E
/* For now -- if we have threads this will be adjusted later */
new_paca->tcd_ptr = &new_paca->tcd;
#endif
powerpc/rtas: Implement reentrant rtas call Implement rtas_call_reentrant() for reentrant rtas-calls: "ibm,int-on", "ibm,int-off",ibm,get-xive" and "ibm,set-xive". On LoPAPR Version 1.1 (March 24, 2016), from 7.3.10.1 to 7.3.10.4, items 2 and 3 say: 2 - For the PowerPC External Interrupt option: The * call must be reentrant to the number of processors on the platform. 3 - For the PowerPC External Interrupt option: The * argument call buffer for each simultaneous call must be physically unique. So, these rtas-calls can be called in a lockless way, if using a different buffer for each cpu doing such rtas call. For this, it was suggested to add the buffer (struct rtas_args) in the PACA struct, so each cpu can have it's own buffer. The PACA struct received a pointer to rtas buffer, which is allocated in the memory range available to rtas 32-bit. Reentrant rtas calls are useful to avoid deadlocks in crashing, where rtas-calls are needed, but some other thread crashed holding the rtas.lock. This is a backtrace of a deadlock from a kdump testing environment: #0 arch_spin_lock #1 lock_rtas () #2 rtas_call (token=8204, nargs=1, nret=1, outputs=0x0) #3 ics_rtas_mask_real_irq (hw_irq=4100) #4 machine_kexec_mask_interrupts #5 default_machine_crash_shutdown #6 machine_crash_shutdown #7 __crash_kexec #8 crash_kexec #9 oops_end Signed-off-by: Leonardo Bras <leobras.c@gmail.com> [mpe: Move under #ifdef PSERIES to avoid build breakage] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200518234245.200672-3-leobras.c@gmail.com
2020-05-19 07:42:45 +08:00
#ifdef CONFIG_PPC_PSERIES
new_paca->rtas_args_reentrant = NULL;
#endif
}
/* Put the paca pointer into r13 and SPRG_PACA */
powerpc/64: Prevent stack protection in early boot The previous commit reduced the amount of code that is run before we setup a paca. However there are still a few remaining functions that run with no paca, or worse, with an arbitrary value in r13 that will be used as a paca pointer. In particular the stack protector canary is stored in the paca, so if stack protector is activated for any of these functions we will read the stack canary from wherever r13 points. If r13 happens to point outside of memory we will get a machine check / checkstop. For example if we modify initialise_paca() to trigger stack protection, and then boot in the mambo simulator with r13 poisoned in skiboot before calling the kernel: DEBUG: 19952232: (19952232): INSTRUCTION: PC=0xC0000000191FC1E8: [0x3C4C006D]: addis r2,r12,0x6D [fetch] DEBUG: 19952236: (19952236): INSTRUCTION: PC=0xC00000001807EAD8: [0x7D8802A6]: mflr r12 [fetch] FATAL ERROR: 19952276: (19952276): Check Stop for 0:0: Machine Check with ME bit of MSR off DEBUG: 19952276: (19952276): INSTRUCTION: PC=0xC0000000191FCA7C: [0xE90D0CF8]: ld r8,0xCF8(r13) [Instruction Failed] INFO: 19952276: (19952277): ** Execution stopped: Mambo Error, Machine Check Stop, ** systemsim % bt pc: 0xC0000000191FCA7C initialise_paca+0x54 lr: 0xC0000000191FC22C early_setup+0x44 stack:0x00000000198CBED0 0x0 +0x0 stack:0x00000000198CBF00 0xC0000000191FC22C early_setup+0x44 stack:0x00000000198CBF90 0x1801C968 +0x1801C968 So annotate the relevant functions to ensure stack protection is never enabled for them. Fixes: 06ec27aea9fc ("powerpc/64: add stack protector support") Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200320032116.1024773-2-mpe@ellerman.id.au
2020-03-20 11:21:16 +08:00
void __nostackprotector setup_paca(struct paca_struct *new_paca)
{
/* Setup r13 */
local_paca = new_paca;
#ifdef CONFIG_PPC_BOOK3E
/* On Book3E, initialize the TLB miss exception frames */
mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
#else
powerpc/64: Setup a paca before parsing device tree etc. Currently we set up the paca after parsing the device tree for CPU features. Prior to that, r13 contains random data, which means there is random data in r13 while we're running the generic dt parsing code. This random data varies depending on whether we boot through a vmlinux or a zImage: for the vmlinux case it's usually around zero, but for zImages we see random values like 912a72603d420015. This is poor practice, and can also lead to difficult-to-debug crashes. For example, when kcov is enabled, the kcov instrumentation attempts to read preempt_count out of the current task, which goes via the paca. This then crashes in the zImage case. Similarly stack protector can cause crashes if r13 is bogus, by reading from the stack canary in the paca. To resolve this: - move the paca setup to before the CPU feature parsing. - because we no longer have access to CPU feature flags in paca setup, change the HV feature test in the paca setup path to consider the actual value of the MSR rather than the CPU feature. Translations get switched on once we leave early_setup, so I think we'd already catch any other cases where the paca or task aren't set up. Boot tested on a P9 guest and host. Fixes: fb0b0a73b223 ("powerpc: Enable kcov") Fixes: 06ec27aea9fc ("powerpc/64: add stack protector support") Cc: stable@vger.kernel.org # v4.20+ Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com> Suggested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Daniel Axtens <dja@axtens.net> [mpe: Reword comments & change log a bit to mention stack protector] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200320032116.1024773-1-mpe@ellerman.id.au
2020-03-20 11:21:15 +08:00
/*
* In HV mode, we setup both HPACA and PACA to avoid problems
* if we do a GET_PACA() before the feature fixups have been
powerpc/64: Setup a paca before parsing device tree etc. Currently we set up the paca after parsing the device tree for CPU features. Prior to that, r13 contains random data, which means there is random data in r13 while we're running the generic dt parsing code. This random data varies depending on whether we boot through a vmlinux or a zImage: for the vmlinux case it's usually around zero, but for zImages we see random values like 912a72603d420015. This is poor practice, and can also lead to difficult-to-debug crashes. For example, when kcov is enabled, the kcov instrumentation attempts to read preempt_count out of the current task, which goes via the paca. This then crashes in the zImage case. Similarly stack protector can cause crashes if r13 is bogus, by reading from the stack canary in the paca. To resolve this: - move the paca setup to before the CPU feature parsing. - because we no longer have access to CPU feature flags in paca setup, change the HV feature test in the paca setup path to consider the actual value of the MSR rather than the CPU feature. Translations get switched on once we leave early_setup, so I think we'd already catch any other cases where the paca or task aren't set up. Boot tested on a P9 guest and host. Fixes: fb0b0a73b223 ("powerpc: Enable kcov") Fixes: 06ec27aea9fc ("powerpc/64: add stack protector support") Cc: stable@vger.kernel.org # v4.20+ Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com> Suggested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Daniel Axtens <dja@axtens.net> [mpe: Reword comments & change log a bit to mention stack protector] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200320032116.1024773-1-mpe@ellerman.id.au
2020-03-20 11:21:15 +08:00
* applied.
*
* Normally you should test against CPU_FTR_HVMODE, but CPU features
* are not yet set up when we first reach here.
*/
powerpc/64: Setup a paca before parsing device tree etc. Currently we set up the paca after parsing the device tree for CPU features. Prior to that, r13 contains random data, which means there is random data in r13 while we're running the generic dt parsing code. This random data varies depending on whether we boot through a vmlinux or a zImage: for the vmlinux case it's usually around zero, but for zImages we see random values like 912a72603d420015. This is poor practice, and can also lead to difficult-to-debug crashes. For example, when kcov is enabled, the kcov instrumentation attempts to read preempt_count out of the current task, which goes via the paca. This then crashes in the zImage case. Similarly stack protector can cause crashes if r13 is bogus, by reading from the stack canary in the paca. To resolve this: - move the paca setup to before the CPU feature parsing. - because we no longer have access to CPU feature flags in paca setup, change the HV feature test in the paca setup path to consider the actual value of the MSR rather than the CPU feature. Translations get switched on once we leave early_setup, so I think we'd already catch any other cases where the paca or task aren't set up. Boot tested on a P9 guest and host. Fixes: fb0b0a73b223 ("powerpc: Enable kcov") Fixes: 06ec27aea9fc ("powerpc/64: add stack protector support") Cc: stable@vger.kernel.org # v4.20+ Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com> Suggested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Daniel Axtens <dja@axtens.net> [mpe: Reword comments & change log a bit to mention stack protector] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200320032116.1024773-1-mpe@ellerman.id.au
2020-03-20 11:21:15 +08:00
if (mfmsr() & MSR_HV)
mtspr(SPRN_SPRG_HPACA, local_paca);
#endif
mtspr(SPRN_SPRG_PACA, local_paca);
}
static int __initdata paca_nr_cpu_ids;
static int __initdata paca_ptrs_size;
static int __initdata paca_struct_size;
void __init allocate_paca_ptrs(void)
{
paca_nr_cpu_ids = nr_cpu_ids;
paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
powerpc: use memblock functions returning virtual address Since only the virtual address of allocated blocks is used, lets use functions returning directly virtual address. Those functions have the advantage of also zeroing the block. [rppt@linux.ibm.com: powerpc: remove duplicated alloc_stack() function] Link: http://lkml.kernel.org/r/20190226064032.GA5873@rapoport-lnx [rppt@linux.ibm.com: updated error message in alloc_stack() to be more verbose] [rppt@linux.ibm.com: convereted several additional call sites ] Link: http://lkml.kernel.org/r/1548057848-15136-3-git-send-email-rppt@linux.ibm.com Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Burton <paul.burton@mips.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:29:00 +08:00
paca_ptrs = memblock_alloc_raw(paca_ptrs_size, SMP_CACHE_BYTES);
if (!paca_ptrs)
panic("Failed to allocate %d bytes for paca pointers\n",
paca_ptrs_size);
memset(paca_ptrs, 0x88, paca_ptrs_size);
}
void __init allocate_paca(int cpu)
{
u64 limit;
struct paca_struct *paca;
BUG_ON(cpu >= paca_nr_cpu_ids);
#ifdef CONFIG_PPC_BOOK3S_64
/*
* We access pacas in real mode, and cannot take SLB faults
* on them when in virtual mode, so allocate them accordingly.
*/
limit = min(ppc64_bolted_size(), ppc64_rma_size);
#else
limit = ppc64_rma_size;
#endif
paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
limit, cpu);
paca_ptrs[cpu] = paca;
initialise_paca(paca, cpu);
#ifdef CONFIG_PPC_PSERIES
paca->lppaca_ptr = new_lppaca(cpu, limit);
#endif
#ifdef CONFIG_PPC_BOOK3S_64
paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
powerpc/rtas: Implement reentrant rtas call Implement rtas_call_reentrant() for reentrant rtas-calls: "ibm,int-on", "ibm,int-off",ibm,get-xive" and "ibm,set-xive". On LoPAPR Version 1.1 (March 24, 2016), from 7.3.10.1 to 7.3.10.4, items 2 and 3 say: 2 - For the PowerPC External Interrupt option: The * call must be reentrant to the number of processors on the platform. 3 - For the PowerPC External Interrupt option: The * argument call buffer for each simultaneous call must be physically unique. So, these rtas-calls can be called in a lockless way, if using a different buffer for each cpu doing such rtas call. For this, it was suggested to add the buffer (struct rtas_args) in the PACA struct, so each cpu can have it's own buffer. The PACA struct received a pointer to rtas buffer, which is allocated in the memory range available to rtas 32-bit. Reentrant rtas calls are useful to avoid deadlocks in crashing, where rtas-calls are needed, but some other thread crashed holding the rtas.lock. This is a backtrace of a deadlock from a kdump testing environment: #0 arch_spin_lock #1 lock_rtas () #2 rtas_call (token=8204, nargs=1, nret=1, outputs=0x0) #3 ics_rtas_mask_real_irq (hw_irq=4100) #4 machine_kexec_mask_interrupts #5 default_machine_crash_shutdown #6 machine_crash_shutdown #7 __crash_kexec #8 crash_kexec #9 oops_end Signed-off-by: Leonardo Bras <leobras.c@gmail.com> [mpe: Move under #ifdef PSERIES to avoid build breakage] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200518234245.200672-3-leobras.c@gmail.com
2020-05-19 07:42:45 +08:00
#endif
#ifdef CONFIG_PPC_PSERIES
paca->rtas_args_reentrant = new_rtas_args(cpu, limit);
#endif
paca_struct_size += sizeof(struct paca_struct);
}
void __init free_unused_pacas(void)
{
int new_ptrs_size;
new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
if (new_ptrs_size < paca_ptrs_size)
memblock_free(__pa(paca_ptrs) + new_ptrs_size,
paca_ptrs_size - new_ptrs_size);
paca_nr_cpu_ids = nr_cpu_ids;
paca_ptrs_size = new_ptrs_size;
#ifdef CONFIG_PPC_BOOK3S_64
if (early_radix_enabled()) {
/* Ugly fixup, see new_slb_shadow() */
memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr),
sizeof(struct slb_shadow));
paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
}
#endif
printk(KERN_DEBUG "Allocated %u bytes for %u pacas\n",
paca_ptrs_size + paca_struct_size, nr_cpu_ids);
}
void copy_mm_to_paca(struct mm_struct *mm)
{
#ifdef CONFIG_PPC_BOOK3S
mm_context_t *context = &mm->context;
get_paca()->mm_ctx_id = context->id;
#ifdef CONFIG_PPC_MM_SLICES
VM_BUG_ON(!mm_ctx_slb_addr_limit(context));
get_paca()->mm_ctx_slb_addr_limit = mm_ctx_slb_addr_limit(context);
memcpy(&get_paca()->mm_ctx_low_slices_psize, mm_ctx_low_slices(context),
LOW_SLICE_ARRAY_SZ);
memcpy(&get_paca()->mm_ctx_high_slices_psize, mm_ctx_high_slices(context),
TASK_SLICE_ARRAY_SZ(context));
#else /* CONFIG_PPC_MM_SLICES */
get_paca()->mm_ctx_user_psize = context->user_psize;
get_paca()->mm_ctx_sllp = context->sllp;
#endif
#else /* !CONFIG_PPC_BOOK3S */
return;
#endif
}