* [PATCH 4/8] powerpc/8xx: remove unused _PAGE_WRITETHRU
From: Christophe Leroy @ 2018-01-12 12:45 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Scott Wood
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <bb30d80cc985d7307fa1286c9e6824230698919b.1515759812.git.christophe.leroy@c-s.fr>
_PAGE_WRITETHRU is only used in:
* AMIGA_Z2RAM block driver which is never activated on powerPC
* Video/FB driver which is for PPC_PMAC
Therefore, no need to spend time in 8xx TLB miss handlers for
handling it.
And by removing it, we free up bit 20 which then avoids having
to clear it on each TLB miss.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/nohash/32/pte-8xx.h | 3 +--
arch/powerpc/include/asm/nohash/pgtable.h | 2 ++
arch/powerpc/kernel/head_8xx.S | 5 -----
3 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 6dc0180fd5c7..19a5ecaef265 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -41,8 +41,7 @@
#define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */
#define _PAGE_USER 0x0020 /* Copied to L1 APG lsb */
#define _PAGE_EXEC 0x0040 /* Copied to L1 APG */
-#define _PAGE_WRITETHRU 0x0080 /* software: caching is write through */
-#define _PAGE_ACCESSED 0x0800 /* software: page referenced */
+#define _PAGE_ACCESSED 0x0080 /* software: page referenced */
#define _PAGE_RO 0x0600 /* Supervisor RO, User no access */
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 5c68f4a59f75..84120d65d0e9 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -212,8 +212,10 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre
#define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
_PAGE_COHERENT))
+#if _PAGE_WRITETHRU != 0
#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
_PAGE_COHERENT | _PAGE_WRITETHRU))
+#endif
#define pgprot_cached_noncoherent(prot) \
(__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL))
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 641c9a9d4db2..6399dcadf51d 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -486,10 +486,6 @@ _ENTRY(DTLBMiss_jmp)
* above.
*/
rlwimi r11, r10, 0, 26, 27
- /* Insert the WriteThru flag into the TWC from the Linux PTE.
- * It is bit 25 in the Linux PTE and bit 30 in the TWC
- */
- rlwimi r11, r10, 32-5, 30, 30
mtspr SPRN_MD_TWC, r11
/* In 4k pages mode, SPS (bit 28) in RPN must match PS[1] (bit 29)
@@ -523,7 +519,6 @@ _ENTRY(DTLBMiss_jmp)
#else
rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */
#endif
- rlwimi r10, r11, 0, 20, 20 /* clear 20 */
mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
/* Restore registers */
--
2.13.3
^ permalink raw reply related
* [PATCH 3/8] powerpc/8xx: Only perform perf counting when perf is in use.
From: Christophe Leroy @ 2018-01-12 12:45 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Scott Wood
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <bb30d80cc985d7307fa1286c9e6824230698919b.1515759812.git.christophe.leroy@c-s.fr>
In TLB miss handlers, updating the perf counter is only useful
when performing a perf analysis. As it has a noticeable overhead,
let's only do it when needed.
In order to do so, the exit of the miss handlers will be patched
when starting/stopping 'perf': the first register restore
instruction of each exit point will be replaced by a jump to
the counting code.
Once this is done, CONFIG_PPC_8xx_PERF_EVENT becomes useless as
this feature doesn't add any overhead.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/ppc-opcode.h | 2 ++
arch/powerpc/kernel/entry_32.S | 10 +++----
arch/powerpc/kernel/head_8xx.S | 47 ++++++++++++++++++++----------
arch/powerpc/perf/8xx-pmu.c | 52 +++++++++++++++++++++++++++++++---
arch/powerpc/perf/Makefile | 2 +-
arch/powerpc/platforms/Kconfig.cputype | 7 -----
6 files changed, 88 insertions(+), 32 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index ce0930d68857..ab5c1588b487 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -236,6 +236,7 @@
#define PPC_INST_RFCI 0x4c000066
#define PPC_INST_RFDI 0x4c00004e
#define PPC_INST_RFMCI 0x4c00004c
+#define PPC_INST_MFSPR 0x7c0002a6
#define PPC_INST_MFSPR_DSCR 0x7c1102a6
#define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe
#define PPC_INST_MTSPR_DSCR 0x7c1103a6
@@ -383,6 +384,7 @@
#define __PPC_ME64(s) __PPC_MB64(s)
#define __PPC_BI(s) (((s) & 0x1f) << 16)
#define __PPC_CT(t) (((t) & 0x0f) << 21)
+#define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11))
/*
* Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e780e1fbf6c2..eb8d01bae8c6 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -211,7 +211,7 @@ transfer_to_handler_cont:
mflr r9
lwz r11,0(r9) /* virtual address of handler */
lwz r9,4(r9) /* where to go when done */
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -301,7 +301,7 @@ stack_ovf:
lis r9,StackOverflow@ha
addi r9,r9,StackOverflow@l
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
mtspr SPRN_SRR0,r9
@@ -430,7 +430,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
lwz r7,_NIP(r1)
lwz r2,GPR2(r1)
lwz r1,GPR1(r1)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
mtspr SPRN_SRR0,r7
@@ -727,7 +727,7 @@ fast_exception_return:
lwz r10,_LINK(r11)
mtlr r10
REST_GPR(10, r11)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
mtspr SPRN_SRR1,r9
@@ -978,7 +978,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
.globl exc_exit_restart
exc_exit_restart:
lwz r12,_NIP(r1)
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
mtspr SPRN_SRR0,r12
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index eda582b96dbf..641c9a9d4db2 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -304,12 +304,6 @@ InstructionTLBMiss:
#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
mtspr SPRN_SPRG_SCRATCH2, r12
#endif
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
- lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha
- lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
- addi r11, r11, 1
- stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
-#endif
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
@@ -392,6 +386,20 @@ _ENTRY(ITLBMiss_cmp)
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
/* Restore registers */
+_ENTRY(itlb_miss_exit_1)
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
+ mfspr r12, SPRN_SPRG_SCRATCH2
+#endif
+ rfi
+#ifdef CONFIG_PERF_EVENTS
+_ENTRY(itlb_miss_perf)
+ lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha
+ lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
+ addi r11, r11, 1
+ stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
+#endif
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
@@ -429,12 +437,6 @@ DataStoreTLBMiss:
mtspr SPRN_SPRG_SCRATCH0, r10
mtspr SPRN_SPRG_SCRATCH1, r11
mtspr SPRN_SPRG_SCRATCH2, r12
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
- lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha
- lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
- addi r11, r11, 1
- stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
-#endif
mfcr r12
/* If we are faulting a kernel address, we have to use the
@@ -526,6 +528,18 @@ _ENTRY(DTLBMiss_jmp)
/* Restore registers */
mtspr SPRN_DAR, r11 /* Tag DAR */
+_ENTRY(dtlb_miss_exit_1)
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r12, SPRN_SPRG_SCRATCH2
+ rfi
+#ifdef CONFIG_PERF_EVENTS
+_ENTRY(dtlb_miss_perf)
+ lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha
+ lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
+ addi r11, r11, 1
+ stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
+#endif
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r12, SPRN_SPRG_SCRATCH2
@@ -635,7 +649,7 @@ DataBreakpoint:
mfspr r11, SPRN_SPRG_SCRATCH1
rfi
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#ifdef CONFIG_PERF_EVENTS
. = 0x1d00
InstructionBreakpoint:
mtspr SPRN_SPRG_SCRATCH0, r10
@@ -675,6 +689,7 @@ DTLBMissIMMR:
li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
+_ENTRY(dtlb_miss_exit_2)
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r12, SPRN_SPRG_SCRATCH2
@@ -692,6 +707,7 @@ DTLBMissLinear:
li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
+_ENTRY(dtlb_miss_exit_3)
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r12, SPRN_SPRG_SCRATCH2
@@ -708,6 +724,7 @@ ITLBMissLinear:
_PAGE_PRESENT
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
+_ENTRY(itlb_miss_exit_2)
mfspr r10, SPRN_SPRG_SCRATCH0
mfspr r11, SPRN_SPRG_SCRATCH1
mfspr r12, SPRN_SPRG_SCRATCH2
@@ -1039,7 +1056,7 @@ initial_mmu:
#endif
/* Disable debug mode entry on breakpoints */
mfspr r8, SPRN_DER
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#ifdef CONFIG_PERF_EVENTS
rlwinm r8, r8, 0, ~0xc
#else
rlwinm r8, r8, 0, ~0x8
@@ -1072,7 +1089,7 @@ swapper_pg_dir:
abatron_pteptrs:
.space 8
-#ifdef CONFIG_PPC_8xx_PERF_EVENT
+#ifdef CONFIG_PERF_EVENTS
.globl itlb_miss_counter
itlb_miss_counter:
.space 4
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 3c39f05f0af3..6c0020d1c561 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -18,6 +18,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/ptrace.h>
+#include <asm/code-patching.h>
#define PERF_8xx_ID_CPU_CYCLES 1
#define PERF_8xx_ID_HW_INSTRUCTIONS 2
@@ -30,8 +31,13 @@
extern unsigned long itlb_miss_counter, dtlb_miss_counter;
extern atomic_t instruction_counter;
+extern unsigned int itlb_miss_perf, dtlb_miss_perf;
+extern unsigned int itlb_miss_exit_1, itlb_miss_exit_2;
+extern unsigned int dtlb_miss_exit_1, dtlb_miss_exit_2, dtlb_miss_exit_3;
static atomic_t insn_ctr_ref;
+static atomic_t itlb_miss_ref;
+static atomic_t dtlb_miss_ref;
static s64 get_insn_ctr(void)
{
@@ -96,9 +102,24 @@ static int mpc8xx_pmu_add(struct perf_event *event, int flags)
val = get_insn_ctr();
break;
case PERF_8xx_ID_ITLB_LOAD_MISS:
+ if (atomic_inc_return(&itlb_miss_ref) == 1) {
+ unsigned long target = (unsigned long)&itlb_miss_perf;
+
+ patch_branch(&itlb_miss_exit_1, target, 0);
+#ifndef CONFIG_PIN_TLB_TEXT
+ patch_branch(&itlb_miss_exit_2, target, 0);
+#endif
+ }
val = itlb_miss_counter;
break;
case PERF_8xx_ID_DTLB_LOAD_MISS:
+ if (atomic_inc_return(&dtlb_miss_ref) == 1) {
+ unsigned long target = (unsigned long)&dtlb_miss_perf;
+
+ patch_branch(&dtlb_miss_exit_1, target, 0);
+ patch_branch(&dtlb_miss_exit_2, target, 0);
+ patch_branch(&dtlb_miss_exit_3, target, 0);
+ }
val = dtlb_miss_counter;
break;
}
@@ -143,13 +164,36 @@ static void mpc8xx_pmu_read(struct perf_event *event)
static void mpc8xx_pmu_del(struct perf_event *event, int flags)
{
+ /* mfspr r10, SPRN_SPRG_SCRATCH0 */
+ unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
+ __PPC_SPR(SPRN_SPRG_SCRATCH0);
+
mpc8xx_pmu_read(event);
- if (event_type(event) != PERF_8xx_ID_HW_INSTRUCTIONS)
- return;
/* If it was the last user, stop counting to avoid useles overhead */
- if (atomic_dec_return(&insn_ctr_ref) == 0)
- mtspr(SPRN_ICTRL, 7);
+ switch (event_type(event)) {
+ case PERF_8xx_ID_CPU_CYCLES:
+ break;
+ case PERF_8xx_ID_HW_INSTRUCTIONS:
+ if (atomic_dec_return(&insn_ctr_ref) == 0)
+ mtspr(SPRN_ICTRL, 7);
+ break;
+ case PERF_8xx_ID_ITLB_LOAD_MISS:
+ if (atomic_dec_return(&itlb_miss_ref) == 0) {
+ patch_instruction(&itlb_miss_exit_1, insn);
+#ifndef CONFIG_PIN_TLB_TEXT
+ patch_instruction(&itlb_miss_exit_2, insn);
+#endif
+ }
+ break;
+ case PERF_8xx_ID_DTLB_LOAD_MISS:
+ if (atomic_dec_return(&dtlb_miss_ref) == 0) {
+ patch_instruction(&dtlb_miss_exit_1, insn);
+ patch_instruction(&dtlb_miss_exit_2, insn);
+ patch_instruction(&dtlb_miss_exit_3, insn);
+ }
+ break;
+ }
}
static struct pmu mpc8xx_pmu = {
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 225c9c86d7c0..57ebc655d2ac 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
-obj-$(CONFIG_PPC_8xx_PERF_EVENT) += 8xx-pmu.o
+obj-$(CONFIG_PPC_8xx) += 8xx-pmu.o
obj-$(CONFIG_PPC64) += $(obj64-y)
obj-$(CONFIG_PPC32) += $(obj32-y)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 73a7ea333e9e..8944b24d2218 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -168,13 +168,6 @@ config PPC_FPU
bool
default y if PPC64
-config PPC_8xx_PERF_EVENT
- bool "PPC 8xx perf events"
- depends on PPC_8xx && PERF_EVENTS
- help
- This is Performance Events support for PPC 8xx. The 8xx doesn't
- have a PMU but some events are emulated using 8xx features.
-
config FSL_EMB_PERFMON
bool "Freescale Embedded Perfmon"
depends on E500 || PPC_83xx
--
2.13.3
^ permalink raw reply related
* [PATCH 2/8] powerpc/8xx: remove EXCEPTION_PROLOG/EPILOG_0 and change r3 to r12
From: Christophe Leroy @ 2018-01-12 12:45 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Scott Wood
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <bb30d80cc985d7307fa1286c9e6824230698919b.1515759812.git.christophe.leroy@c-s.fr>
EXCEPTION_PROLOG_0 and EXCEPTION_EPILOG_0 were added some
time ago in order to regroup the two mtspr/mfspr to SCRATCH0 and
SCRATCH1 and the mfcr/mtcr in order to ease entry and exit of
function not using the full EXCEPTION_PROLOG.
Since then, the mfcr/mtcr has been taken out, hence just leaving
the two mtspr/mfspr in the macro.
In order to improve readability of the exception functions, we
remove those two macros and copy back the two mtspr/mfspr instead.
As r10 and r11 are used for SCRATCH0 and SCRATCH1, lets also use
r12 for SCRATCH2. It will also improve the readability/maintenance.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/kernel/head_8xx.S | 78 ++++++++++++++++++++++--------------------
1 file changed, 40 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 728b513c07b8..eda582b96dbf 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -117,15 +117,12 @@ turn_on_mmu:
* task's thread_struct.
*/
#define EXCEPTION_PROLOG \
- EXCEPTION_PROLOG_0; \
+ mtspr SPRN_SPRG_SCRATCH0, r10; \
+ mtspr SPRN_SPRG_SCRATCH1, r11; \
mfcr r10; \
EXCEPTION_PROLOG_1; \
EXCEPTION_PROLOG_2
-#define EXCEPTION_PROLOG_0 \
- mtspr SPRN_SPRG_SCRATCH0,r10; \
- mtspr SPRN_SPRG_SCRATCH1,r11
-
#define EXCEPTION_PROLOG_1 \
mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \
andi. r11,r11,MSR_PR; \
@@ -160,13 +157,6 @@ turn_on_mmu:
SAVE_2GPRS(7, r11)
/*
- * Exception exit code.
- */
-#define EXCEPTION_EPILOG_0 \
- mfspr r10,SPRN_SPRG_SCRATCH0; \
- mfspr r11,SPRN_SPRG_SCRATCH1
-
-/*
* Note: code which follows this uses cr0.eq (set if from kernel),
* r11, r12 (SRR0), and r9 (SRR1).
*
@@ -309,10 +299,11 @@ SystemCall:
#endif
InstructionTLBMiss:
+ mtspr SPRN_SPRG_SCRATCH0, r10
+ mtspr SPRN_SPRG_SCRATCH1, r11
#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
- mtspr SPRN_SPRG_SCRATCH2, r3
+ mtspr SPRN_SPRG_SCRATCH2, r12
#endif
- EXCEPTION_PROLOG_0
#ifdef CONFIG_PPC_8xx_PERF_EVENT
lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha
lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
@@ -328,7 +319,7 @@ InstructionTLBMiss:
/* Only modules will cause ITLB Misses as we always
* pin the first 8MB of kernel memory */
#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
- mfcr r3
+ mfcr r12
#endif
#ifdef ITLB_MISS_KERNEL
#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
@@ -371,7 +362,7 @@ _ENTRY(ITLBMiss_cmp)
lwz r10, 0(r10) /* Get the pte */
4:
#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
- mtcr r3
+ mtcr r12
#endif
/* Insert the APG into the TWC from the Linux PTE. */
rlwimi r11, r10, 0, 25, 26
@@ -401,10 +392,11 @@ _ENTRY(ITLBMiss_cmp)
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
/* Restore registers */
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
- mfspr r3, SPRN_SPRG_SCRATCH2
+ mfspr r12, SPRN_SPRG_SCRATCH2
#endif
- EXCEPTION_EPILOG_0
rfi
#ifdef CONFIG_HUGETLB_PAGE
@@ -434,15 +426,16 @@ _ENTRY(ITLBMiss_cmp)
. = 0x1200
DataStoreTLBMiss:
- mtspr SPRN_SPRG_SCRATCH2, r3
- EXCEPTION_PROLOG_0
+ mtspr SPRN_SPRG_SCRATCH0, r10
+ mtspr SPRN_SPRG_SCRATCH1, r11
+ mtspr SPRN_SPRG_SCRATCH2, r12
#ifdef CONFIG_PPC_8xx_PERF_EVENT
lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha
lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
addi r11, r11, 1
stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
#endif
- mfcr r3
+ mfcr r12
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
@@ -482,7 +475,7 @@ _ENTRY(DTLBMiss_jmp)
rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */
lwz r10, 0(r10) /* Get the pte */
4:
- mtcr r3
+ mtcr r12
/* Insert the Guarded flag and APG into the TWC from the Linux PTE.
* It is bit 26-27 of both the Linux PTE and the TWC (at least
@@ -532,9 +525,10 @@ _ENTRY(DTLBMiss_jmp)
mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
/* Restore registers */
- mfspr r3, SPRN_SPRG_SCRATCH2
mtspr SPRN_DAR, r11 /* Tag DAR */
- EXCEPTION_EPILOG_0
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r12, SPRN_SPRG_SCRATCH2
rfi
#ifdef CONFIG_HUGETLB_PAGE
@@ -584,7 +578,8 @@ itlbie:
*/
. = 0x1400
DataTLBError:
- EXCEPTION_PROLOG_0
+ mtspr SPRN_SPRG_SCRATCH0, r10
+ mtspr SPRN_SPRG_SCRATCH1, r11
mfcr r10
mfspr r11, SPRN_DAR
@@ -619,7 +614,8 @@ dtlbie:
*/
. = 0x1c00
DataBreakpoint:
- EXCEPTION_PROLOG_0
+ mtspr SPRN_SPRG_SCRATCH0, r10
+ mtspr SPRN_SPRG_SCRATCH1, r11
mfcr r10
mfspr r11, SPRN_SRR0
cmplwi cr0, r11, (dtlbie - PAGE_OFFSET)@l
@@ -635,13 +631,15 @@ DataBreakpoint:
EXC_XFER_EE(0x1c00, do_break)
11:
mtcr r10
- EXCEPTION_EPILOG_0
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
rfi
#ifdef CONFIG_PPC_8xx_PERF_EVENT
. = 0x1d00
InstructionBreakpoint:
- EXCEPTION_PROLOG_0
+ mtspr SPRN_SPRG_SCRATCH0, r10
+ mtspr SPRN_SPRG_SCRATCH1, r11
lis r10, (instruction_counter - PAGE_OFFSET)@ha
lwz r11, (instruction_counter - PAGE_OFFSET)@l(r10)
addi r11, r11, -1
@@ -649,7 +647,8 @@ InstructionBreakpoint:
lis r10, 0xffff
ori r10, r10, 0x01
mtspr SPRN_COUNTA, r10
- EXCEPTION_EPILOG_0
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
rfi
#else
EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE)
@@ -664,7 +663,7 @@ InstructionBreakpoint:
* not enough space in the DataStoreTLBMiss area.
*/
DTLBMissIMMR:
- mtcr r3
+ mtcr r12
/* Set 512k byte guarded page and mark it valid */
li r10, MD_PS512K | MD_GUARDED | MD_SVALID
mtspr SPRN_MD_TWC, r10
@@ -676,12 +675,13 @@ DTLBMissIMMR:
li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
- mfspr r3, SPRN_SPRG_SCRATCH2
- EXCEPTION_EPILOG_0
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r12, SPRN_SPRG_SCRATCH2
rfi
DTLBMissLinear:
- mtcr r3
+ mtcr r12
/* Set 8M byte page and mark it valid */
li r11, MD_PS8MEG | MD_SVALID
mtspr SPRN_MD_TWC, r11
@@ -692,13 +692,14 @@ DTLBMissLinear:
li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
- mfspr r3, SPRN_SPRG_SCRATCH2
- EXCEPTION_EPILOG_0
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r12, SPRN_SPRG_SCRATCH2
rfi
#ifndef CONFIG_PIN_TLB_TEXT
ITLBMissLinear:
- mtcr r3
+ mtcr r12
/* Set 8M byte page and mark it valid */
li r11, MI_PS8MEG | MI_SVALID | _PAGE_EXEC
mtspr SPRN_MI_TWC, r11
@@ -707,8 +708,9 @@ ITLBMissLinear:
_PAGE_PRESENT
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
- mfspr r3, SPRN_SPRG_SCRATCH2
- EXCEPTION_EPILOG_0
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r12, SPRN_SPRG_SCRATCH2
rfi
#endif
--
2.13.3
^ permalink raw reply related
* [PATCH 1/8] powerpc/8xx: Remove CPU6 ERRATA Workaround
From: Christophe Leroy @ 2018-01-12 12:45 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Scott Wood
Cc: linux-kernel, linuxppc-dev
CPU6 ERRATA affects only MPC860 revisions prior to C.0. Manufacturing
of those revisiosn was stopped in 1999-2000.
Therefore, it has been almost 20 years since this ERRATA has been
fixed in the silicon.
This patch removes the workaround for that ERRATA.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/configs/mpc866_ads_defconfig | 1 -
arch/powerpc/include/asm/reg_8xx.h | 82 -------------------------------
arch/powerpc/kernel/head_8xx.S | 54 +++++---------------
arch/powerpc/platforms/8xx/Kconfig | 12 -----
4 files changed, 12 insertions(+), 137 deletions(-)
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index f1f176c29fa3..5320735395e7 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -13,7 +13,6 @@ CONFIG_EXPERT=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_MPC86XADS=y
CONFIG_8xx_COPYBACK=y
-CONFIG_8xx_CPU6=y
CONFIG_GEN_RTC=y
CONFIG_HZ_1000=y
CONFIG_MATH_EMULATION=y
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index 53a7e2955d3e..7192eece6c3e 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -66,86 +66,4 @@
#define DC_DFWT 0x40000000 /* Data cache is forced write through */
#define DC_LES 0x20000000 /* Caches are little endian mode */
-#ifdef CONFIG_8xx_CPU6
-#define do_mtspr_cpu6(rn, rn_addr, v) \
- do { \
- int _reg_cpu6 = rn_addr, _tmp_cpu6; \
- asm volatile("stw %0, %1;" \
- "lwz %0, %1;" \
- "mtspr " __stringify(rn) ",%2" : \
- : "r" (_reg_cpu6), "m"(_tmp_cpu6), \
- "r" ((unsigned long)(v)) \
- : "memory"); \
- } while (0)
-
-#define do_mtspr(rn, v) asm volatile("mtspr " __stringify(rn) ",%0" : \
- : "r" ((unsigned long)(v)) \
- : "memory")
-#define mtspr(rn, v) \
- do { \
- if (rn == SPRN_IMMR) \
- do_mtspr_cpu6(rn, 0x3d30, v); \
- else if (rn == SPRN_IC_CST) \
- do_mtspr_cpu6(rn, 0x2110, v); \
- else if (rn == SPRN_IC_ADR) \
- do_mtspr_cpu6(rn, 0x2310, v); \
- else if (rn == SPRN_IC_DAT) \
- do_mtspr_cpu6(rn, 0x2510, v); \
- else if (rn == SPRN_DC_CST) \
- do_mtspr_cpu6(rn, 0x3110, v); \
- else if (rn == SPRN_DC_ADR) \
- do_mtspr_cpu6(rn, 0x3310, v); \
- else if (rn == SPRN_DC_DAT) \
- do_mtspr_cpu6(rn, 0x3510, v); \
- else if (rn == SPRN_MI_CTR) \
- do_mtspr_cpu6(rn, 0x2180, v); \
- else if (rn == SPRN_MI_AP) \
- do_mtspr_cpu6(rn, 0x2580, v); \
- else if (rn == SPRN_MI_EPN) \
- do_mtspr_cpu6(rn, 0x2780, v); \
- else if (rn == SPRN_MI_TWC) \
- do_mtspr_cpu6(rn, 0x2b80, v); \
- else if (rn == SPRN_MI_RPN) \
- do_mtspr_cpu6(rn, 0x2d80, v); \
- else if (rn == SPRN_MI_CAM) \
- do_mtspr_cpu6(rn, 0x2190, v); \
- else if (rn == SPRN_MI_RAM0) \
- do_mtspr_cpu6(rn, 0x2390, v); \
- else if (rn == SPRN_MI_RAM1) \
- do_mtspr_cpu6(rn, 0x2590, v); \
- else if (rn == SPRN_MD_CTR) \
- do_mtspr_cpu6(rn, 0x3180, v); \
- else if (rn == SPRN_M_CASID) \
- do_mtspr_cpu6(rn, 0x3380, v); \
- else if (rn == SPRN_MD_AP) \
- do_mtspr_cpu6(rn, 0x3580, v); \
- else if (rn == SPRN_MD_EPN) \
- do_mtspr_cpu6(rn, 0x3780, v); \
- else if (rn == SPRN_M_TWB) \
- do_mtspr_cpu6(rn, 0x3980, v); \
- else if (rn == SPRN_MD_TWC) \
- do_mtspr_cpu6(rn, 0x3b80, v); \
- else if (rn == SPRN_MD_RPN) \
- do_mtspr_cpu6(rn, 0x3d80, v); \
- else if (rn == SPRN_M_TW) \
- do_mtspr_cpu6(rn, 0x3f80, v); \
- else if (rn == SPRN_MD_CAM) \
- do_mtspr_cpu6(rn, 0x3190, v); \
- else if (rn == SPRN_MD_RAM0) \
- do_mtspr_cpu6(rn, 0x3390, v); \
- else if (rn == SPRN_MD_RAM1) \
- do_mtspr_cpu6(rn, 0x3590, v); \
- else if (rn == SPRN_DEC) \
- do_mtspr_cpu6(rn, 0x2c00, v); \
- else if (rn == SPRN_TBWL) \
- do_mtspr_cpu6(rn, 0x3880, v); \
- else if (rn == SPRN_TBWU) \
- do_mtspr_cpu6(rn, 0x3a80, v); \
- else if (rn == SPRN_DPDR) \
- do_mtspr_cpu6(rn, 0x2d30, v); \
- else \
- do_mtspr(rn, v); \
- } while (0)
-#endif
-
#endif /* _ASM_POWERPC_REG_8xx_H */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 4fee00d414e8..728b513c07b8 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -33,23 +33,6 @@
#include <asm/fixmap.h>
#include <asm/export.h>
-/* Macro to make the code more readable. */
-#ifdef CONFIG_8xx_CPU6
-#define SPRN_MI_TWC_ADDR 0x2b80
-#define SPRN_MI_RPN_ADDR 0x2d80
-#define SPRN_MD_TWC_ADDR 0x3b80
-#define SPRN_MD_RPN_ADDR 0x3d80
-
-#define MTSPR_CPU6(spr, reg, treg) \
- li treg, spr##_ADDR; \
- stw treg, 12(r0); \
- lwz treg, 12(r0); \
- mtspr spr, reg
-#else
-#define MTSPR_CPU6(spr, reg, treg) \
- mtspr spr, reg
-#endif
-
#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
/* By simply checking Address >= 0x80000000, we know if its a kernel address */
#define SIMPLE_KERNEL_ADDRESS 1
@@ -326,7 +309,7 @@ SystemCall:
#endif
InstructionTLBMiss:
-#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
mtspr SPRN_SPRG_SCRATCH2, r3
#endif
EXCEPTION_PROLOG_0
@@ -393,7 +376,7 @@ _ENTRY(ITLBMiss_cmp)
/* Insert the APG into the TWC from the Linux PTE. */
rlwimi r11, r10, 0, 25, 26
/* Load the MI_TWC with the attributes for this "segment." */
- MTSPR_CPU6(SPRN_MI_TWC, r11, r3) /* Set segment attributes */
+ mtspr SPRN_MI_TWC, r11 /* Set segment attributes */
#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES)
rlwimi r10, r11, 1, MI_SPS16K
@@ -415,10 +398,10 @@ _ENTRY(ITLBMiss_cmp)
#else
rlwimi r10, r11, 0, 0x0ff8 /* Set 24-27, clear 20-23,28 */
#endif
- MTSPR_CPU6(SPRN_MI_RPN, r10, r3) /* Update TLB entry */
+ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
/* Restore registers */
-#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
mfspr r3, SPRN_SPRG_SCRATCH2
#endif
EXCEPTION_EPILOG_0
@@ -512,7 +495,7 @@ _ENTRY(DTLBMiss_jmp)
* It is bit 25 in the Linux PTE and bit 30 in the TWC
*/
rlwimi r11, r10, 32-5, 30, 30
- MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
+ mtspr SPRN_MD_TWC, r11
/* In 4k pages mode, SPS (bit 28) in RPN must match PS[1] (bit 29)
* In 16k pages mode, SPS is always 1 */
@@ -546,7 +529,7 @@ _ENTRY(DTLBMiss_jmp)
rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */
#endif
rlwimi r10, r11, 0, 20, 20 /* clear 20 */
- MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */
+ mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
/* Restore registers */
mfspr r3, SPRN_SPRG_SCRATCH2
@@ -684,12 +667,12 @@ DTLBMissIMMR:
mtcr r3
/* Set 512k byte guarded page and mark it valid */
li r10, MD_PS512K | MD_GUARDED | MD_SVALID
- MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
+ mtspr SPRN_MD_TWC, r10
mfspr r10, SPRN_IMMR /* Get current IMMR */
rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */
ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
_PAGE_PRESENT | _PAGE_NO_CACHE
- MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */
+ mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
@@ -701,11 +684,11 @@ DTLBMissLinear:
mtcr r3
/* Set 8M byte page and mark it valid */
li r11, MD_PS8MEG | MD_SVALID
- MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
+ mtspr SPRN_MD_TWC, r11
rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */
ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
_PAGE_PRESENT
- MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */
+ mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
@@ -718,11 +701,11 @@ ITLBMissLinear:
mtcr r3
/* Set 8M byte page and mark it valid */
li r11, MI_PS8MEG | MI_SVALID | _PAGE_EXEC
- MTSPR_CPU6(SPRN_MI_TWC, r11, r3)
+ mtspr SPRN_MI_TWC, r11
rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */
ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
_PAGE_PRESENT
- MTSPR_CPU6(SPRN_MI_RPN, r10, r11) /* Update TLB entry */
+ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
mfspr r3, SPRN_SPRG_SCRATCH2
EXCEPTION_EPILOG_0
@@ -933,13 +916,6 @@ start_here:
*/
lis r6, swapper_pg_dir@ha
tophys(r6,r6)
-#ifdef CONFIG_8xx_CPU6
- lis r4, cpu6_errata_word@h
- ori r4, r4, cpu6_errata_word@l
- li r3, 0x3f80
- stw r3, 12(r4)
- lwz r3, 12(r4)
-#endif
mtspr SPRN_M_TW, r6
lis r4,2f@h
ori r4,r4,2f@l
@@ -1094,12 +1070,6 @@ swapper_pg_dir:
abatron_pteptrs:
.space 8
-#ifdef CONFIG_8xx_CPU6
- .globl cpu6_errata_word
-cpu6_errata_word:
- .space 16
-#endif
-
#ifdef CONFIG_PPC_8xx_PERF_EVENT
.globl itlb_miss_counter
itlb_miss_counter:
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index e7f33e96b395..e417988eaef9 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -124,18 +124,6 @@ config 8xx_GPIO
If in doubt, say Y here.
-config 8xx_CPU6
- bool "CPU6 Silicon Errata (860 Pre Rev. C)"
- help
- MPC860 CPUs, prior to Rev C have some bugs in the silicon, which
- require workarounds for Linux (and most other OSes to work). If you
- get a BUG() very early in boot, this might fix the problem. For
- more details read the document entitled "MPC860 Family Device Errata
- Reference" on Freescale's website. This option also incurs a
- performance hit.
-
- If in doubt, say N here.
-
config 8xx_CPU15
bool "CPU15 Silicon Errata"
depends on !HUGETLB_PAGE
--
2.13.3
^ permalink raw reply related
* Re: [PATCH v6 1/2] powerpc/powernv: Enable tunneled operations
From: christophe lombard @ 2018-01-12 10:15 UTC (permalink / raw)
To: Philippe Bergheaud, linuxppc-dev; +Cc: fbarrat
In-Reply-To: <20180111150103.3137-1-felix@linux.vnet.ibm.com>
Le 11/01/2018 à 16:01, Philippe Bergheaud a écrit :
> P9 supports PCI tunneled operations (atomics and as_notify). This
> patch adds support for tunneled operations on powernv, with a new
> API, to be called by device drivers:
>
> pnv_pci_get_tunnel_ind()
> Tell driver the 16-bit ASN indication used by kernel.
>
> pnv_pci_set_tunnel_bar()
> Tell kernel the Tunnel BAR Response address used by driver.
> This function uses two new OPAL calls, as the PBCQ Tunnel BAR
> register is configured by skiboot.
>
> pnv_pci_get_as_notify_info()
> Return the ASN info of the thread to be woken up.
>
> Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
> ---
> Changelog:
>
> v2: Do not set the ASN indication. Get it from the device tree.
>
> v3: Make pnv_pci_get_phb_node() available when compiling without cxl.
>
> v4: Add pnv_pci_get_as_notify_info().
> Rebase opal call numbers on skiboot 5.9.6.
>
> v5: pnv_pci_get_tunnel_ind():
> - fix node reference count
> pnv_pci_get_as_notify_info():
> - fail if task == NULL
> - read pid from mm->context.id
> - explain that thread.tidr require CONFIG_PPC64
>
> v6: pnv_pci_get_tunnel_ind():
> - check if radix is enabled, or else return an error
> pnv_pci_get_as_notify_info():
> - remove a capi-specific comment, irrelevant for pci
>
> This patch depends on the following skiboot patches:
> https://patchwork.ozlabs.org/patch/858324/
> https://patchwork.ozlabs.org/patch/858325/
> ---
> arch/powerpc/include/asm/opal-api.h | 4 +-
> arch/powerpc/include/asm/opal.h | 2 +
> arch/powerpc/include/asm/pnv-pci.h | 5 ++
> arch/powerpc/platforms/powernv/opal-wrappers.S | 2 +
> arch/powerpc/platforms/powernv/pci-cxl.c | 8 --
> arch/powerpc/platforms/powernv/pci.c | 106 +++++++++++++++++++++++++
> 6 files changed, 118 insertions(+), 9 deletions(-)
>
Acked-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
^ permalink raw reply
* Re: [PATCH v6 2/2] cxl: read PHB indications from the device tree
From: christophe lombard @ 2018-01-12 10:14 UTC (permalink / raw)
To: Philippe Bergheaud, linuxppc-dev; +Cc: fbarrat
In-Reply-To: <20180111150103.3137-2-felix@linux.vnet.ibm.com>
Le 11/01/2018 à 16:01, Philippe Bergheaud a écrit :
> Configure the P9 XSL_DSNCTL register with PHB indications found
> in the device tree, or else use legacy hard-coded values.
>
> Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
> ---
> Changelog:
>
> v2: New patch. Use the new device tree property "ibm,phb-indications".
>
> v3: No change.
>
> v4: No functional change.
> Drop cosmetic fix in comment.
>
> v5: get_phb_indications():
> - make static variables local to function.
> - return static variable values by arguments.
>
> v6: get_phb_indications():
> - acquire a mutex before setting the phb indications.
>
> This patch depends on the following skiboot patch:
> https://patchwork.ozlabs.org/patch/858324/
> ---
> drivers/misc/cxl/cxl.h | 2 +-
> drivers/misc/cxl/cxllib.c | 2 +-
> drivers/misc/cxl/pci.c | 50 ++++++++++++++++++++++++++++++++++++++++++-----
> 3 files changed, 47 insertions(+), 7 deletions(-)
>
Acked-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
^ permalink raw reply
* Re: [PATCH] cpufreq: powernv: Dont assume distinct pstate values for nominal and pmin
From: Viresh Kumar @ 2018-01-12 9:07 UTC (permalink / raw)
To: Shilpasri G Bhat
Cc: rjw, mpe, linux-pm, linuxppc-dev, linux-kernel, ego, svaidy,
akshay.adiga, huntbag
In-Reply-To: <1515741233-1442-1-git-send-email-shilpa.bhat@linux.vnet.ibm.com>
On 12-01-18, 12:43, Shilpasri G Bhat wrote:
> Some OpenPOWER boxes can have same pstate values for nominal and
> pmin pstates. In these boxes the current code will not initialize
> 'powernv_pstate_info.min' variable and result in erroneous CPU
> frequency reporting. This patch fixes this problem.
>
> Fixes: 09ca4c9b5958 ("cpufreq: powernv: Replacing pstate_id with frequency table index")
> Reported-by: Alvin Wang <wangat@tw.ibm.com>
> Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
> ---
> drivers/cpufreq/powernv-cpufreq.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
> index b6d7c4c..da7fdb4 100644
> --- a/drivers/cpufreq/powernv-cpufreq.c
> +++ b/drivers/cpufreq/powernv-cpufreq.c
> @@ -288,9 +288,9 @@ static int init_powernv_pstates(void)
>
> if (id == pstate_max)
> powernv_pstate_info.max = i;
> - else if (id == pstate_nominal)
> + if (id == pstate_nominal)
> powernv_pstate_info.nominal = i;
> - else if (id == pstate_min)
> + if (id == pstate_min)
> powernv_pstate_info.min = i;
>
> if (powernv_pstate_info.wof_enabled && id == pstate_turbo) {
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
--
viresh
^ permalink raw reply
* Re: [PATCH V7] cxl: Add support for ASB_Notify on POWER9
From: Vaibhav Jain @ 2018-01-12 8:51 UTC (permalink / raw)
To: Christophe Lombard, linuxppc-dev, fbarrat, andrew.donnellan
In-Reply-To: <1515660925-10026-1-git-send-email-clombard@linux.vnet.ibm.com>
Christophe Lombard <clombard@linux.vnet.ibm.com> writes:
> The POWER9 core supports a new feature: ASB_Notify which requires the
> support of the Special Purpose Register: TIDR.
>
> The ASB_Notify command, generated by the AFU, will attempt to
> wake-up the host thread identified by the particular LPID:PID:TID.
>
> This patch assign a unique TIDR (thread id) for the current thread which
> will be used in the process element entry.
>
> Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
> Reviewed-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
>
Reviewed-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com>
^ permalink raw reply
* [PATCH 34/34] h8300: use dma-direct
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
Replace the bare-bones h8300 direct dma mapping implementation with
the fully featured generic dma-direct one.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/h8300/Kconfig | 1 +
arch/h8300/include/asm/Kbuild | 1 +
arch/h8300/include/asm/dma-mapping.h | 12 -------
arch/h8300/kernel/Makefile | 2 +-
arch/h8300/kernel/dma.c | 66 ------------------------------------
5 files changed, 3 insertions(+), 79 deletions(-)
delete mode 100644 arch/h8300/include/asm/dma-mapping.h
delete mode 100644 arch/h8300/kernel/dma.c
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index f8d3fde08190..091d6d04b5e5 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -23,6 +23,7 @@ config H8300
select HAVE_ARCH_KGDB
select HAVE_ARCH_HASH
select CPU_NO_EFFICIENT_FFS
+ select DMA_DIRECT_OPS
config CPU_BIG_ENDIAN
def_bool y
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index bc077491d299..642752c94306 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += delay.h
generic-y += device.h
generic-y += div64.h
generic-y += dma.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += exec.h
generic-y += extable.h
diff --git a/arch/h8300/include/asm/dma-mapping.h b/arch/h8300/include/asm/dma-mapping.h
deleted file mode 100644
index 21bb1fc3a6f1..000000000000
--- a/arch/h8300/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _H8300_DMA_MAPPING_H
-#define _H8300_DMA_MAPPING_H
-
-extern const struct dma_map_ops h8300_dma_map_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &h8300_dma_map_ops;
-}
-
-#endif
diff --git a/arch/h8300/kernel/Makefile b/arch/h8300/kernel/Makefile
index b62e830525c6..307aa51576dd 100644
--- a/arch/h8300/kernel/Makefile
+++ b/arch/h8300/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y := vmlinux.lds
obj-y := process.o traps.o ptrace.o \
signal.o setup.o syscalls.o \
- irq.o entry.o dma.o
+ irq.o entry.o
obj-$(CONFIG_ROMKERNEL) += head_rom.o
obj-$(CONFIG_RAMKERNEL) += head_ram.o
diff --git a/arch/h8300/kernel/dma.c b/arch/h8300/kernel/dma.c
deleted file mode 100644
index d44ba5db4ac3..000000000000
--- a/arch/h8300/kernel/dma.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/kernel.h>
-#include <linux/scatterlist.h>
-#include <linux/module.h>
-#include <asm/pgalloc.h>
-
-static void *dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp,
- unsigned long attrs)
-{
- void *ret;
-
- if (dev == NULL || (*dev->dma_mask < 0xffffffff))
- gfp |= GFP_DMA;
- ret = (void *)__get_free_pages(gfp, get_order(size));
-
- if (ret != NULL) {
- memset(ret, 0, size);
- *dma_handle = virt_to_phys(ret);
- }
- return ret;
-}
-
-static void dma_free(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle,
- unsigned long attrs)
-
-{
- free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static dma_addr_t map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction,
- unsigned long attrs)
-{
- return page_to_phys(page) + offset;
-}
-
-static int map_sg(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction direction,
- unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sgl, sg, nents, i) {
- sg->dma_address = sg_phys(sg);
- }
-
- return nents;
-}
-
-const struct dma_map_ops h8300_dma_map_ops = {
- .alloc = dma_alloc,
- .free = dma_free,
- .map_page = map_page,
- .map_sg = map_sg,
-};
-EXPORT_SYMBOL(h8300_dma_map_ops);
--
2.14.2
^ permalink raw reply related
* [PATCH 33/34] cris: use dma-direct
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
cris currently has an incomplete direct mapping dma_map_ops implementation
if PCI support is enabled. Replace it with the fully feature generic
dma-direct implementation.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
---
arch/cris/Kconfig | 4 ++
arch/cris/arch-v32/drivers/pci/Makefile | 2 +-
arch/cris/arch-v32/drivers/pci/dma.c | 77 ---------------------------------
arch/cris/include/asm/Kbuild | 1 +
arch/cris/include/asm/dma-mapping.h | 20 ---------
5 files changed, 6 insertions(+), 98 deletions(-)
delete mode 100644 arch/cris/arch-v32/drivers/pci/dma.c
delete mode 100644 arch/cris/include/asm/dma-mapping.h
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 54d3f426763b..cd5a0865c97f 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -33,6 +33,9 @@ config GENERIC_CALIBRATE_DELAY
config NO_IOPORT_MAP
def_bool y if !PCI
+config NO_DMA
+ def_bool y if !PCI
+
config FORCE_MAX_ZONEORDER
int
default 6
@@ -72,6 +75,7 @@ config CRIS
select GENERIC_SCHED_CLOCK if ETRAX_ARCH_V32
select HAVE_DEBUG_BUGVERBOSE if ETRAX_ARCH_V32
select HAVE_NMI
+ select DMA_DIRECT_OPS if PCI
config HZ
int
diff --git a/arch/cris/arch-v32/drivers/pci/Makefile b/arch/cris/arch-v32/drivers/pci/Makefile
index bff7482f2444..93c8be6170b1 100644
--- a/arch/cris/arch-v32/drivers/pci/Makefile
+++ b/arch/cris/arch-v32/drivers/pci/Makefile
@@ -2,4 +2,4 @@
# Makefile for Etrax cardbus driver
#
-obj-$(CONFIG_ETRAX_CARDBUS) += bios.o dma.o
+obj-$(CONFIG_ETRAX_CARDBUS) += bios.o
diff --git a/arch/cris/arch-v32/drivers/pci/dma.c b/arch/cris/arch-v32/drivers/pci/dma.c
deleted file mode 100644
index 8c3802244ef3..000000000000
--- a/arch/cris/arch-v32/drivers/pci/dma.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Dynamic DMA mapping support.
- *
- * On cris there is no hardware dynamic DMA address translation,
- * so consistent alloc/free are merely page allocation/freeing.
- * The rest of the dynamic DMA mapping interface is implemented
- * in asm/pci.h.
- *
- * Borrowed from i386.
- */
-
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/pci.h>
-#include <linux/gfp.h>
-#include <asm/io.h>
-
-static void *v32_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
- void *ret;
-
- if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
- gfp |= GFP_DMA;
-
- ret = (void *)__get_free_pages(gfp, get_order(size));
-
- if (ret != NULL) {
- memset(ret, 0, size);
- *dma_handle = virt_to_phys(ret);
- }
- return ret;
-}
-
-static void v32_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static inline dma_addr_t v32_dma_map_page(struct device *dev,
- struct page *page, unsigned long offset, size_t size,
- enum dma_data_direction direction, unsigned long attrs)
-{
- return page_to_phys(page) + offset;
-}
-
-static inline int v32_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction,
- unsigned long attrs)
-{
- printk("Map sg\n");
- return nents;
-}
-
-static inline int v32_dma_supported(struct device *dev, u64 mask)
-{
- /*
- * we fall back to GFP_DMA when the mask isn't all 1s,
- * so we can't guarantee allocations that must be
- * within a tighter range than GFP_DMA..
- */
- if (mask < 0x00ffffff)
- return 0;
- return 1;
-}
-
-const struct dma_map_ops v32_dma_ops = {
- .alloc = v32_dma_alloc,
- .free = v32_dma_free,
- .map_page = v32_dma_map_page,
- .map_sg = v32_dma_map_sg,
- .dma_supported = v32_dma_supported,
-};
-EXPORT_SYMBOL(v32_dma_ops);
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 460349cb147f..8cf45ac30c1b 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += cmpxchg.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += exec.h
generic-y += extable.h
diff --git a/arch/cris/include/asm/dma-mapping.h b/arch/cris/include/asm/dma-mapping.h
deleted file mode 100644
index 1553bdb30a0c..000000000000
--- a/arch/cris/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_CRIS_DMA_MAPPING_H
-#define _ASM_CRIS_DMA_MAPPING_H
-
-#ifdef CONFIG_PCI
-extern const struct dma_map_ops v32_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &v32_dma_ops;
-}
-#else
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- BUG();
- return NULL;
-}
-#endif
-
-#endif
--
2.14.2
^ permalink raw reply related
* [PATCH 32/34] dma-direct: reject too small dma masks
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
include/linux/dma-direct.h | 1 +
lib/dma-direct.c | 19 +++++++++++++++++++
2 files changed, 20 insertions(+)
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 4788bf0bf683..bcdb1a3e4b1f 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -42,5 +42,6 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp, unsigned long attrs);
void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t dma_addr, unsigned long attrs);
+int dma_direct_supported(struct device *dev, u64 mask);
#endif /* _LINUX_DMA_DIRECT_H */
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index 784a68dfdbe3..40b1f92f2214 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -122,6 +122,24 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
return nents;
}
+int dma_direct_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_ZONE_DMA
+ if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ return 0;
+#else
+ /*
+ * Because 32-bit DMA masks are so common we expect every architecture
+ * to be able to satisfy them - either by not supporting more physical
+ * memory, or by providing a ZONE_DMA32. If neither is the case, the
+ * architecture needs to use an IOMMU instead of the direct mapping.
+ */
+ if (mask < DMA_BIT_MASK(32))
+ return 0;
+#endif
+ return 1;
+}
+
static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return dma_addr == DIRECT_MAPPING_ERROR;
@@ -132,6 +150,7 @@ const struct dma_map_ops dma_direct_ops = {
.free = dma_direct_free,
.map_page = dma_direct_map_page,
.map_sg = dma_direct_map_sg,
+ .dma_supported = dma_direct_supported,
.mapping_error = dma_direct_mapping_error,
};
EXPORT_SYMBOL(dma_direct_ops);
--
2.14.2
^ permalink raw reply related
* [PATCH 31/34] dma-direct: make dma_direct_{alloc, free} available to other implementations
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
So that they don't need to indirect through the operation vector.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
arch/arm/mm/dma-mapping-nommu.c | 9 +++------
include/linux/dma-direct.h | 5 +++++
lib/dma-direct.c | 6 +++---
3 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 4d8042521e89..619f24a42d09 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -11,7 +11,7 @@
#include <linux/export.h>
#include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
#include <linux/scatterlist.h>
#include <asm/cachetype.h>
@@ -39,7 +39,6 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
unsigned long attrs)
{
- const struct dma_map_ops *ops = &dma_direct_ops;
void *ret;
/*
@@ -48,7 +47,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
*/
if (attrs & DMA_ATTR_NON_CONSISTENT)
- return ops->alloc(dev, size, dma_handle, gfp, attrs);
+ return dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
ret = dma_alloc_from_global_coherent(size, dma_handle);
@@ -70,10 +69,8 @@ static void arm_nommu_dma_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr,
unsigned long attrs)
{
- const struct dma_map_ops *ops = &dma_direct_ops;
-
if (attrs & DMA_ATTR_NON_CONSISTENT) {
- ops->free(dev, size, cpu_addr, dma_addr, attrs);
+ dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
} else {
int ret = dma_release_from_global_coherent(get_order(size),
cpu_addr);
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 10e924b7cba7..4788bf0bf683 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -38,4 +38,9 @@ static inline void dma_mark_clean(void *addr, size_t size)
}
#endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */
+void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs);
+void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_addr, unsigned long attrs);
+
#endif /* _LINUX_DMA_DIRECT_H */
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index 4e43c2bb7f5f..784a68dfdbe3 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -40,8 +40,8 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask;
}
-static void *dma_direct_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
{
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
int page_order = get_order(size);
@@ -84,7 +84,7 @@ static void *dma_direct_alloc(struct device *dev, size_t size,
return page_address(page);
}
-static void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
+void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t dma_addr, unsigned long attrs)
{
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
--
2.14.2
^ permalink raw reply related
* [PATCH 30/34] dma-direct: retry allocations using GFP_DMA for small masks
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
If an attempt to allocate memory succeeded, but isn't inside the
supported DMA mask, retry the allocation with GFP_DMA set as a
last resort.
Based on the x86 code, but an off by one error in what is now
dma_coherent_ok has been fixed vs the x86 code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
lib/dma-direct.c | 25 ++++++++++++++++++++++++-
1 file changed, 24 insertions(+), 1 deletion(-)
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index 8f76032ebc3c..4e43c2bb7f5f 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -35,6 +35,11 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
return true;
}
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+{
+ return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask;
+}
+
static void *dma_direct_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
@@ -48,11 +53,29 @@ static void *dma_direct_alloc(struct device *dev, size_t size,
if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
gfp |= GFP_DMA32;
+again:
/* CMA can be used only in the context which permits sleeping */
- if (gfpflags_allow_blocking(gfp))
+ if (gfpflags_allow_blocking(gfp)) {
page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ dma_release_from_contiguous(dev, page, count);
+ page = NULL;
+ }
+ }
if (!page)
page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
+
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ __free_pages(page, page_order);
+ page = NULL;
+
+ if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+ !(gfp & GFP_DMA)) {
+ gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
+ goto again;
+ }
+ }
+
if (!page)
return NULL;
--
2.14.2
^ permalink raw reply related
* [PATCH 29/34] dma-direct: add support for allocation from ZONE_DMA and ZONE_DMA32
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
This allows to dip into zones for lower memory if they are available.
If one of the zones is not available the corresponding GFP_* flag
will evaluate to 0 so they won't change anything. We provide an
arch tunable for those architectures that do not use GFP_DMA for
the lowest 24-bits, given that there are a few.
Roughly based on the x86 code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
lib/dma-direct.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index f04a424f91fa..8f76032ebc3c 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -12,6 +12,14 @@
#define DIRECT_MAPPING_ERROR 0
+/*
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but
+ * some use it for entirely different regions:
+ */
+#ifndef ARCH_ZONE_DMA_BITS
+#define ARCH_ZONE_DMA_BITS 24
+#endif
+
static bool
check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
const char *caller)
@@ -34,6 +42,12 @@ static void *dma_direct_alloc(struct device *dev, size_t size,
int page_order = get_order(size);
struct page *page = NULL;
+ /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
+ if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ gfp |= GFP_DMA;
+ if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
+ gfp |= GFP_DMA32;
+
/* CMA can be used only in the context which permits sleeping */
if (gfpflags_allow_blocking(gfp))
page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
--
2.14.2
^ permalink raw reply related
* [PATCH 28/34] dma-direct: use node local allocations for coherent memory
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
To preserve the x86 behavior.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
lib/dma-direct.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index a9ae98be7af3..f04a424f91fa 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -38,7 +38,7 @@ static void *dma_direct_alloc(struct device *dev, size_t size,
if (gfpflags_allow_blocking(gfp))
page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
if (!page)
- page = alloc_pages(gfp, page_order);
+ page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
if (!page)
return NULL;
--
2.14.2
^ permalink raw reply related
* [PATCH 27/34] dma-direct: add support for CMA allocation
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
Try the CMA allocator for coherent allocations if supported.
Roughly modelled after the x86 code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
lib/dma-direct.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index 32fd4d9e4c47..a9ae98be7af3 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -7,6 +7,7 @@
#include <linux/mm.h>
#include <linux/dma-direct.h>
#include <linux/scatterlist.h>
+#include <linux/dma-contiguous.h>
#include <linux/pfn.h>
#define DIRECT_MAPPING_ERROR 0
@@ -29,19 +30,30 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
static void *dma_direct_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
- void *ret;
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ int page_order = get_order(size);
+ struct page *page = NULL;
- ret = (void *)__get_free_pages(gfp, get_order(size));
- if (ret)
- *dma_handle = phys_to_dma(dev, virt_to_phys(ret));
+ /* CMA can be used only in the context which permits sleeping */
+ if (gfpflags_allow_blocking(gfp))
+ page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
+ if (!page)
+ page = alloc_pages(gfp, page_order);
+ if (!page)
+ return NULL;
- return ret;
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+ memset(page_address(page), 0, size);
+ return page_address(page);
}
static void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t dma_addr, unsigned long attrs)
{
- free_pages((unsigned long)cpu_addr, get_order(size));
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
+ free_pages((unsigned long)cpu_addr, get_order(size));
}
static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
--
2.14.2
^ permalink raw reply related
* [PATCH 26/34] dma-direct: add dma address sanity checks
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
Roughly based on the x86 pci-nommu implementation.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
lib/dma-direct.c | 31 ++++++++++++++++++++++++++++++-
1 file changed, 30 insertions(+), 1 deletion(-)
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index 12ea9653781b..32fd4d9e4c47 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -9,6 +9,23 @@
#include <linux/scatterlist.h>
#include <linux/pfn.h>
+#define DIRECT_MAPPING_ERROR 0
+
+static bool
+check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
+ const char *caller)
+{
+ if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
+ if (*dev->dma_mask >= DMA_BIT_MASK(32)) {
+ dev_err(dev,
+ "%s: overflow %pad+%zu of device mask %llx\n",
+ caller, &dma_addr, size, *dev->dma_mask);
+ }
+ return false;
+ }
+ return true;
+}
+
static void *dma_direct_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
@@ -31,7 +48,11 @@ static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
- return phys_to_dma(dev, page_to_phys(page)) + offset;
+ dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset;
+
+ if (!check_addr(dev, dma_addr, size, __func__))
+ return DIRECT_MAPPING_ERROR;
+ return dma_addr;
}
static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
@@ -44,16 +65,24 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
BUG_ON(!sg_page(sg));
sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
+ if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__))
+ return 0;
sg_dma_len(sg) = sg->length;
}
return nents;
}
+static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr == DIRECT_MAPPING_ERROR;
+}
+
const struct dma_map_ops dma_direct_ops = {
.alloc = dma_direct_alloc,
.free = dma_direct_free,
.map_page = dma_direct_map_page,
.map_sg = dma_direct_map_sg,
+ .mapping_error = dma_direct_mapping_error,
};
EXPORT_SYMBOL(dma_direct_ops);
--
2.14.2
^ permalink raw reply related
* [PATCH 25/34] dma-direct: use phys_to_dma
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
This means it uses whatever linear remapping scheme that the architecture
provides is used in the generic dma_direct ops.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
lib/dma-direct.c | 18 +++++++-----------
1 file changed, 7 insertions(+), 11 deletions(-)
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index 0ec3262a3148..12ea9653781b 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -1,12 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * lib/dma-noop.c
- *
- * DMA operations that map to physical addresses without flushing memory.
+ * DMA operations that map physical memory directly without using an IOMMU or
+ * flushing caches.
*/
#include <linux/export.h>
#include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
#include <linux/scatterlist.h>
#include <linux/pfn.h>
@@ -17,7 +16,7 @@ static void *dma_direct_alloc(struct device *dev, size_t size,
ret = (void *)__get_free_pages(gfp, get_order(size));
if (ret)
- *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+ *dma_handle = phys_to_dma(dev, virt_to_phys(ret));
return ret;
}
@@ -32,7 +31,7 @@ static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
- return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset);
+ return phys_to_dma(dev, page_to_phys(page)) + offset;
}
static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
@@ -42,12 +41,9 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
struct scatterlist *sg;
for_each_sg(sgl, sg, nents, i) {
- dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset);
- void *va;
-
BUG_ON(!sg_page(sg));
- va = sg_virt(sg);
- sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va) - offset;
+
+ sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
sg_dma_len(sg) = sg->length;
}
--
2.14.2
^ permalink raw reply related
* [PATCH 24/34] dma-direct: rename dma_noop to dma_direct
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
The trivial direct mapping implementation already does a virtual to
physical translation which isn't strictly a noop, and will soon learn
to do non-direct but linear physical to dma translations through the
device offset and a few small tricks. Rename it to a better fitting
name.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
MAINTAINERS | 2 +-
arch/arm/Kconfig | 2 +-
arch/arm/include/asm/dma-mapping.h | 2 +-
arch/arm/mm/dma-mapping-nommu.c | 8 ++++----
arch/m32r/Kconfig | 2 +-
arch/riscv/Kconfig | 2 +-
arch/s390/Kconfig | 2 +-
include/asm-generic/dma-mapping.h | 2 +-
include/linux/dma-mapping.h | 2 +-
lib/Kconfig | 2 +-
lib/Makefile | 2 +-
lib/{dma-noop.c => dma-direct.c} | 35 +++++++++++++++--------------------
12 files changed, 29 insertions(+), 34 deletions(-)
rename lib/{dma-noop.c => dma-direct.c} (52%)
diff --git a/MAINTAINERS b/MAINTAINERS
index 234e642e7149..2d54e636d625 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4334,7 +4334,7 @@ T: git git://git.infradead.org/users/hch/dma-mapping.git
W: http://git.infradead.org/users/hch/dma-mapping.git
S: Supported
F: lib/dma-debug.c
-F: lib/dma-noop.c
+F: lib/dma-direct.c
F: lib/dma-virt.c
F: drivers/base/dma-mapping.c
F: drivers/base/dma-coherent.c
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 00d889a37965..430a0aa710d6 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -25,7 +25,7 @@ config ARM
select CLONE_BACKWARDS
select CPU_PM if (SUSPEND || CPU_IDLE)
select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
- select DMA_NOOP_OPS if !MMU
+ select DMA_DIRECT_OPS if !MMU
select EDAC_SUPPORT
select EDAC_ATOMIC_SCRUB
select GENERIC_ALLOCATOR
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index e5d9020c9ee1..8436f6ade57d 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -18,7 +18,7 @@ extern const struct dma_map_ops arm_coherent_dma_ops;
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
- return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_noop_ops;
+ return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops;
}
#ifdef __arch_page_to_dma
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 6db5fc26d154..4d8042521e89 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -22,7 +22,7 @@
#include "dma.h"
/*
- * dma_noop_ops is used if
+ * dma_direct_ops is used if
* - MMU/MPU is off
* - cpu is v7m w/o cache support
* - device is coherent
@@ -39,7 +39,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
unsigned long attrs)
{
- const struct dma_map_ops *ops = &dma_noop_ops;
+ const struct dma_map_ops *ops = &dma_direct_ops;
void *ret;
/*
@@ -70,7 +70,7 @@ static void arm_nommu_dma_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr,
unsigned long attrs)
{
- const struct dma_map_ops *ops = &dma_noop_ops;
+ const struct dma_map_ops *ops = &dma_direct_ops;
if (attrs & DMA_ATTR_NON_CONSISTENT) {
ops->free(dev, size, cpu_addr, dma_addr, attrs);
@@ -213,7 +213,7 @@ EXPORT_SYMBOL(arm_nommu_dma_ops);
static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
{
- return coherent ? &dma_noop_ops : &arm_nommu_dma_ops;
+ return coherent ? &dma_direct_ops : &arm_nommu_dma_ops;
}
void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 498398d915c1..dd84ee194579 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -19,7 +19,7 @@ config M32R
select MODULES_USE_ELF_RELA
select HAVE_DEBUG_STACKOVERFLOW
select CPU_NO_EFFICIENT_FFS
- select DMA_NOOP_OPS
+ select DMA_DIRECT_OPS
select ARCH_NO_COHERENT_DMA_MMAP if !MMU
config SBUS
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 2c6adf12713a..865e14f50c14 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -83,7 +83,7 @@ config PGTABLE_LEVELS
config HAVE_KPROBES
def_bool n
-config DMA_NOOP_OPS
+config DMA_DIRECT_OPS
def_bool y
menu "Platform type"
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 829c67986db7..9376637229c9 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -140,7 +140,7 @@ config S390
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
- select DMA_NOOP_OPS
+ select DMA_DIRECT_OPS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h
index 164031531d85..880a292d792f 100644
--- a/include/asm-generic/dma-mapping.h
+++ b/include/asm-generic/dma-mapping.h
@@ -4,7 +4,7 @@
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
- return &dma_noop_ops;
+ return &dma_direct_ops;
}
#endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index d67742dad904..b626028a3e47 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -136,7 +136,7 @@ struct dma_map_ops {
int is_phys;
};
-extern const struct dma_map_ops dma_noop_ops;
+extern const struct dma_map_ops dma_direct_ops;
extern const struct dma_map_ops dma_virt_ops;
#define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
diff --git a/lib/Kconfig b/lib/Kconfig
index c5e84fbcb30b..9d3d649c9dc9 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -409,7 +409,7 @@ config HAS_DMA
depends on !NO_DMA
default y
-config DMA_NOOP_OPS
+config DMA_DIRECT_OPS
bool
depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT)
default n
diff --git a/lib/Makefile b/lib/Makefile
index d11c48ec8ffd..749851abe85a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -28,7 +28,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
-lib-$(CONFIG_DMA_NOOP_OPS) += dma-noop.o
+lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
lib-y += kobject.o klist.o
diff --git a/lib/dma-noop.c b/lib/dma-direct.c
similarity index 52%
rename from lib/dma-noop.c
rename to lib/dma-direct.c
index a10185b0c2d4..0ec3262a3148 100644
--- a/lib/dma-noop.c
+++ b/lib/dma-direct.c
@@ -10,9 +10,8 @@
#include <linux/scatterlist.h>
#include <linux/pfn.h>
-static void *dma_noop_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp,
- unsigned long attrs)
+static void *dma_direct_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
void *ret;
@@ -23,24 +22,21 @@ static void *dma_noop_alloc(struct device *dev, size_t size,
return ret;
}
-static void dma_noop_free(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t dma_addr,
- unsigned long attrs)
+static void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_addr, unsigned long attrs)
{
free_pages((unsigned long)cpu_addr, get_order(size));
}
-static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
+static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
{
return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset);
}
-static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
- enum dma_data_direction dir,
- unsigned long attrs)
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
{
int i;
struct scatterlist *sg;
@@ -58,11 +54,10 @@ static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nent
return nents;
}
-const struct dma_map_ops dma_noop_ops = {
- .alloc = dma_noop_alloc,
- .free = dma_noop_free,
- .map_page = dma_noop_map_page,
- .map_sg = dma_noop_map_sg,
+const struct dma_map_ops dma_direct_ops = {
+ .alloc = dma_direct_alloc,
+ .free = dma_direct_free,
+ .map_page = dma_direct_map_page,
+ .map_sg = dma_direct_map_sg,
};
-
-EXPORT_SYMBOL(dma_noop_ops);
+EXPORT_SYMBOL(dma_direct_ops);
--
2.14.2
^ permalink raw reply related
* [PATCH 23/34] dma-mapping: provide a generic asm/dma-mapping.h
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
For architectures that just use the generic dma_noop_ops we can provide
a generic version of dma-mapping.h.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
MAINTAINERS | 1 +
arch/m32r/include/asm/Kbuild | 1 +
arch/m32r/include/asm/dma-mapping.h | 17 -----------------
arch/riscv/include/asm/Kbuild | 1 +
arch/riscv/include/asm/dma-mapping.h | 30 ------------------------------
arch/s390/include/asm/Kbuild | 1 +
arch/s390/include/asm/dma-mapping.h | 17 -----------------
include/asm-generic/dma-mapping.h | 10 ++++++++++
8 files changed, 14 insertions(+), 64 deletions(-)
delete mode 100644 arch/m32r/include/asm/dma-mapping.h
delete mode 100644 arch/riscv/include/asm/dma-mapping.h
delete mode 100644 arch/s390/include/asm/dma-mapping.h
create mode 100644 include/asm-generic/dma-mapping.h
diff --git a/MAINTAINERS b/MAINTAINERS
index d2cfdcce1db5..234e642e7149 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4338,6 +4338,7 @@ F: lib/dma-noop.c
F: lib/dma-virt.c
F: drivers/base/dma-mapping.c
F: drivers/base/dma-coherent.c
+F: include/asm-generic/dma-mapping.h
F: include/linux/dma-direct.h
F: include/linux/dma-mapping.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 7e11b125c35e..ca83fda8177b 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -1,5 +1,6 @@
generic-y += clkdev.h
generic-y += current.h
+generic-y += dma-mapping.h
generic-y += exec.h
generic-y += extable.h
generic-y += irq_work.h
diff --git a/arch/m32r/include/asm/dma-mapping.h b/arch/m32r/include/asm/dma-mapping.h
deleted file mode 100644
index 8967fb659691..000000000000
--- a/arch/m32r/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_M32R_DMA_MAPPING_H
-#define _ASM_M32R_DMA_MAPPING_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <linux/io.h>
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &dma_noop_ops;
-}
-
-#endif /* _ASM_M32R_DMA_MAPPING_H */
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 970460a0b492..197460ccbf21 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += device.h
generic-y += div64.h
generic-y += dma.h
generic-y += dma-contiguous.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h
deleted file mode 100644
index 73849e2cc761..000000000000
--- a/arch/riscv/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Copyright (C) 2003-2004 Hewlett-Packard Co
- * David Mosberger-Tang <davidm@hpl.hp.com>
- * Copyright (C) 2012 ARM Ltd.
- * Copyright (C) 2016 SiFive, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_RISCV_DMA_MAPPING_H
-#define __ASM_RISCV_DMA_MAPPING_H
-
-/* Use ops->dma_mapping_error (if it exists) or assume success */
-// #undef DMA_ERROR_CODE
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &dma_noop_ops;
-}
-
-#endif /* __ASM_RISCV_DMA_MAPPING_H */
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 048450869328..dade72be127b 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += cacheflush.h
generic-y += clkdev.h
generic-y += device.h
generic-y += dma-contiguous.h
+generic-y += dma-mapping.h
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += export.h
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
deleted file mode 100644
index bdc2455483f6..000000000000
--- a/arch/s390/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_S390_DMA_MAPPING_H
-#define _ASM_S390_DMA_MAPPING_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <linux/io.h>
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &dma_noop_ops;
-}
-
-#endif /* _ASM_S390_DMA_MAPPING_H */
diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h
new file mode 100644
index 000000000000..164031531d85
--- /dev/null
+++ b/include/asm-generic/dma-mapping.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_DMA_MAPPING_H
+#define _ASM_GENERIC_DMA_MAPPING_H
+
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
+{
+ return &dma_noop_ops;
+}
+
+#endif /* _ASM_GENERIC_DMA_MAPPING_H */
--
2.14.2
^ permalink raw reply related
* [PATCH 22/34] dma-mapping: add an arch_dma_supported hook
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
To implement the x86 forbid_dac and iommu_sac_force we want an arch hook
so that it can apply the global options across all dma_map_ops
implementations.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/x86/include/asm/dma-mapping.h | 3 +++
arch/x86/kernel/pci-dma.c | 19 ++++++++++++-------
include/linux/dma-mapping.h | 11 +++++++++++
3 files changed, 26 insertions(+), 7 deletions(-)
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index dfdc9357a349..6277c83c0eb1 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -30,6 +30,9 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
return dma_ops;
}
+int arch_dma_supported(struct device *dev, u64 mask);
+#define arch_dma_supported arch_dma_supported
+
bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
#define arch_dma_alloc_attrs arch_dma_alloc_attrs
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 61a8f1cb3829..df7ab02f959f 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -215,7 +215,7 @@ static __init int iommu_setup(char *p)
}
early_param("iommu", iommu_setup);
-int x86_dma_supported(struct device *dev, u64 mask)
+int arch_dma_supported(struct device *dev, u64 mask)
{
#ifdef CONFIG_PCI
if (mask > 0xffffffff && forbid_dac > 0) {
@@ -224,12 +224,6 @@ int x86_dma_supported(struct device *dev, u64 mask)
}
#endif
- /* Copied from i386. Doesn't make much sense, because it will
- only work for pci_alloc_coherent.
- The caller just has to use GFP_DMA in this case. */
- if (mask < DMA_BIT_MASK(24))
- return 0;
-
/* Tell the device to use SAC when IOMMU force is on. This
allows the driver to use cheaper accesses in some cases.
@@ -249,6 +243,17 @@ int x86_dma_supported(struct device *dev, u64 mask)
return 1;
}
+EXPORT_SYMBOL(arch_dma_supported);
+
+int x86_dma_supported(struct device *dev, u64 mask)
+{
+ /* Copied from i386. Doesn't make much sense, because it will
+ only work for pci_alloc_coherent.
+ The caller just has to use GFP_DMA in this case. */
+ if (mask < DMA_BIT_MASK(24))
+ return 0;
+ return 1;
+}
static int __init pci_iommu_init(void)
{
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 88bcb1a8211d..d67742dad904 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -576,6 +576,14 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
return 0;
}
+/*
+ * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please
+ * don't use this is new code.
+ */
+#ifndef arch_dma_supported
+#define arch_dma_supported(dev, mask) (1)
+#endif
+
static inline void dma_check_mask(struct device *dev, u64 mask)
{
if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
@@ -588,6 +596,9 @@ static inline int dma_supported(struct device *dev, u64 mask)
if (!ops)
return 0;
+ if (!arch_dma_supported(dev, mask))
+ return 0;
+
if (!ops->dma_supported)
return 1;
return ops->dma_supported(dev, mask);
--
2.14.2
^ permalink raw reply related
* [PATCH 21/34] dma-mapping: clear harmful GFP_* flags in common code
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
Lift the code from x86 so that we behave consistently. In the future we
should probably warn if any of these is set.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> [m68k]
---
arch/cris/arch-v32/drivers/pci/dma.c | 3 ---
arch/h8300/kernel/dma.c | 3 ---
arch/m68k/kernel/dma.c | 2 --
arch/mips/cavium-octeon/dma-octeon.c | 3 ---
arch/mips/loongson64/common/dma-swiotlb.c | 3 ---
arch/mips/mm/dma-default.c | 3 ---
arch/mips/netlogic/common/nlm-dma.c | 3 ---
arch/mn10300/mm/dma-alloc.c | 3 ---
arch/nios2/mm/dma-mapping.c | 3 ---
arch/powerpc/kernel/dma.c | 3 ---
arch/x86/kernel/pci-dma.c | 2 --
include/linux/dma-mapping.h | 7 +++++++
12 files changed, 7 insertions(+), 31 deletions(-)
diff --git a/arch/cris/arch-v32/drivers/pci/dma.c b/arch/cris/arch-v32/drivers/pci/dma.c
index dbbd3816cc0b..8c3802244ef3 100644
--- a/arch/cris/arch-v32/drivers/pci/dma.c
+++ b/arch/cris/arch-v32/drivers/pci/dma.c
@@ -22,9 +22,6 @@ static void *v32_dma_alloc(struct device *dev, size_t size,
{
void *ret;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
gfp |= GFP_DMA;
diff --git a/arch/h8300/kernel/dma.c b/arch/h8300/kernel/dma.c
index 225dd0a188dc..d44ba5db4ac3 100644
--- a/arch/h8300/kernel/dma.c
+++ b/arch/h8300/kernel/dma.c
@@ -16,9 +16,6 @@ static void *dma_alloc(struct device *dev, size_t size,
{
void *ret;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
if (dev == NULL || (*dev->dma_mask < 0xffffffff))
gfp |= GFP_DMA;
ret = (void *)__get_free_pages(gfp, get_order(size));
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 87ef73a93856..c01b9b8f97bf 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -76,8 +76,6 @@ static void *m68k_dma_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
void *ret;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
if (dev == NULL || (*dev->dma_mask < 0xffffffff))
gfp |= GFP_DMA;
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index c64bd87f0b6e..5baf79fce643 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -161,9 +161,6 @@ static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
{
void *ret;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
if (IS_ENABLED(CONFIG_ZONE_DMA) && dev == NULL)
gfp |= __GFP_DMA;
else if (IS_ENABLED(CONFIG_ZONE_DMA) &&
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
index ef07740cee61..15388c24a504 100644
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ b/arch/mips/loongson64/common/dma-swiotlb.c
@@ -15,9 +15,6 @@ static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
{
void *ret;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
if ((IS_ENABLED(CONFIG_ISA) && dev == NULL) ||
(IS_ENABLED(CONFIG_ZONE_DMA) &&
dev->coherent_dma_mask < DMA_BIT_MASK(32)))
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index e3e94d05f0fd..237532e89919 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -93,9 +93,6 @@ static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
{
gfp_t dma_flag;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
#ifdef CONFIG_ISA
if (dev == NULL)
dma_flag = __GFP_DMA;
diff --git a/arch/mips/netlogic/common/nlm-dma.c b/arch/mips/netlogic/common/nlm-dma.c
index 0ec9d9da6d51..49c975b6aa28 100644
--- a/arch/mips/netlogic/common/nlm-dma.c
+++ b/arch/mips/netlogic/common/nlm-dma.c
@@ -47,9 +47,6 @@ static char *nlm_swiotlb;
static void *nlm_dma_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
-
#ifdef CONFIG_ZONE_DMA32
if (dev->coherent_dma_mask <= DMA_BIT_MASK(32))
gfp |= __GFP_DMA32;
diff --git a/arch/mn10300/mm/dma-alloc.c b/arch/mn10300/mm/dma-alloc.c
index 86108d2496b3..e3910d4db102 100644
--- a/arch/mn10300/mm/dma-alloc.c
+++ b/arch/mn10300/mm/dma-alloc.c
@@ -37,9 +37,6 @@ static void *mn10300_dma_alloc(struct device *dev, size_t size,
goto done;
}
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
if (dev == NULL || dev->coherent_dma_mask < 0xffffffff)
gfp |= GFP_DMA;
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 7040c1adbb5e..4be815519dd4 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -63,9 +63,6 @@ static void *nios2_dma_alloc(struct device *dev, size_t size,
{
void *ret;
- /* ignore region specifiers */
- gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
/* optimized page clearing */
gfp |= __GFP_ZERO;
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 6d5d04ccf3b4..76079841d3d0 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -105,9 +105,6 @@ void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
};
#endif /* CONFIG_FSL_SOC */
- /* ignore region specifiers */
- flag &= ~(__GFP_HIGHMEM);
-
page = alloc_pages_node(node, flag, get_order(size));
if (page == NULL)
return NULL;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 8439e6de6156..61a8f1cb3829 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -87,7 +87,6 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_mask = dma_alloc_coherent_mask(dev, flag);
- flag &= ~__GFP_ZERO;
again:
page = NULL;
/* CMA can be used only in the context which permits sleeping */
@@ -139,7 +138,6 @@ bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
if (!*dev)
*dev = &x86_dma_fallback_dev;
- *gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
if (!is_device_dma_capable(*dev))
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 9f28b2fa329e..88bcb1a8211d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -518,6 +518,13 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
return cpu_addr;
+ /*
+ * Let the implementation decide on the zone to allocate from, and
+ * decide on the way of zeroing the memory given that the memory
+ * returned should always be zeroed.
+ */
+ flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM | __GFP_ZERO);
+
if (!arch_dma_alloc_attrs(&dev, &flag))
return NULL;
if (!ops->alloc)
--
2.14.2
^ permalink raw reply related
* [PATCH 20/34] dma-mapping: warn when there is no coherent_dma_mask
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
These days all devices should have a DMA coherent mask, and most dma_ops
implementations rely on that fact. But just to be sure add an assert to
ring the warning bell if that is not the case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
include/linux/dma-mapping.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index d84951865be7..9f28b2fa329e 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -513,6 +513,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
void *cpu_addr;
BUG_ON(!ops);
+ WARN_ON_ONCE(!dev->coherent_dma_mask);
if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
return cpu_addr;
--
2.14.2
^ permalink raw reply related
* [PATCH 19/34] s390: move s390_pci_dma_ops to asm/pci_dma.h
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
This is not needed in drivers, so move it to a private header.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/s390/include/asm/dma-mapping.h | 2 --
arch/s390/include/asm/pci_dma.h | 3 +++
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index 2ec7240c1ada..bdc2455483f6 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -9,8 +9,6 @@
#include <linux/dma-debug.h>
#include <linux/io.h>
-extern const struct dma_map_ops s390_pci_dma_ops;
-
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
return &dma_noop_ops;
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index e8d9161fa17a..419fac7a62c0 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -201,4 +201,7 @@ void dma_cleanup_tables(unsigned long *);
unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr);
void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags);
+extern const struct dma_map_ops s390_pci_dma_ops;
+
+
#endif
--
2.14.2
^ permalink raw reply related
* [PATCH 18/34] microblaze: remove the dead !NOT_COHERENT_CACHE dma code
From: Christoph Hellwig @ 2018-01-12 8:42 UTC (permalink / raw)
To: iommu
Cc: Konrad Rzeszutek Wilk, linux-alpha, linux-snps-arc,
linux-arm-kernel, linux-c6x-dev, linux-cris-kernel, linux-hexagon,
linux-ia64, linux-m68k, linux-metag, Michal Simek, linux-mips,
linux-parisc, linuxppc-dev, patches, linux-s390, linux-sh,
sparclinux, Guan Xuetao, x86, linux-arch, linux-kernel
In-Reply-To: <20180112084232.2857-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/microblaze/kernel/dma.c | 28 ----------------------------
1 file changed, 28 deletions(-)
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index b45d8f8967af..c91e8cef98dd 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -15,42 +15,18 @@
#include <linux/bug.h>
#include <asm/cacheflush.h>
-#define NOT_COHERENT_CACHE
-
static void *dma_nommu_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flag,
unsigned long attrs)
{
-#ifdef NOT_COHERENT_CACHE
return consistent_alloc(flag, size, dma_handle);
-#else
- void *ret;
- struct page *page;
- int node = dev_to_node(dev);
-
- /* ignore region specifiers */
- flag &= ~(__GFP_HIGHMEM);
-
- page = alloc_pages_node(node, flag, get_order(size));
- if (page == NULL)
- return NULL;
- ret = page_address(page);
- memset(ret, 0, size);
- *dma_handle = virt_to_phys(ret);
-
- return ret;
-#endif
}
static void dma_nommu_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t dma_handle,
unsigned long attrs)
{
-#ifdef NOT_COHERENT_CACHE
consistent_free(size, vaddr);
-#else
- free_pages((unsigned long)vaddr, get_order(size));
-#endif
}
static inline void __dma_sync(unsigned long paddr,
@@ -186,12 +162,8 @@ int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
if (off >= count || user_count > (count - off))
return -ENXIO;
-#ifdef NOT_COHERENT_CACHE
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
pfn = consistent_virt_to_pfn(cpu_addr);
-#else
- pfn = virt_to_pfn(cpu_addr);
-#endif
return remap_pfn_range(vma, vma->vm_start, pfn + off,
vma->vm_end - vma->vm_start, vma->vm_page_prot);
#else
--
2.14.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox