UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branches 'arm/renesas', 'arm/smmu', 'arm/omap', 'ppc/pamu', 'x86/amd' and 'core' into next 

Conflicts:
	drivers/iommu/Kconfig
	drivers/iommu/Makefile
This commit is contained in:
Joerg Roedel 2015-02-04 16:53:44 +01:00
parent bb590c9011 a4188beee5 1d7f449c89 cd70d4659f ae0cbbb1cd 63ce3ae889
commit a20cc76b9e
255 changed files with 2797 additions and 1695 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Documentation/devicetree/bindings/i2c/i2c-st.txt
View File

@ -31,7 +31,7 @@ i2c0: i2c@fed40000 {
compatible = "st,comms-ssc4-i2c";
reg = <0xfed40000 0x110>;
interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&CLK_S_ICN_REG_0>;
clocks = <&clk_s_a0_ls CLK_ICN_REG>;
clock-names = "ssc";
clock-frequency = <400000>;
pinctrl-names = "default";

1
Documentation/devicetree/bindings/i2c/trivial-devices.txt
View File

@ -47,6 +47,7 @@ dallas,ds3232 Extremely Accurate I²C RTC with Integrated Crystal and SRAM
dallas,ds4510 CPU Supervisor with Nonvolatile Memory and Programmable I/O
dallas,ds75 Digital Thermometer and Thermostat
dlg,da9053 DA9053: flexible system level PMIC with multicore support
dlg,da9063 DA9063: system PMIC for quad-core application processors
epson,rx8025 High-Stability. I2C-Bus INTERFACE REAL TIME CLOCK MODULE
epson,rx8581 I2C-BUS INTERFACE REAL TIME CLOCK MODULE
fsl,mag3110 MAG3110: Xtrinsic High Accuracy, 3D Magnetometer

11
MAINTAINERS
View File

@ -708,6 +708,16 @@ X: drivers/iio/*/adjd*
F: drivers/staging/iio/*/ad*
F: staging/iio/trigger/iio-trig-bfin-timer.c
ANDROID DRIVERS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
M: Arve Hjønnevåg <arve@android.com>
M: Riley Andrews <riandrews@android.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/gregkh/staging.git
L: devel@driverdev.osuosl.org
S: Supported
F: drivers/android/
F: drivers/staging/android/
AOA (Apple Onboard Audio) ALSA DRIVER
M: Johannes Berg <johannes@sipsolutions.net>
L: linuxppc-dev@lists.ozlabs.org
@ -10167,6 +10177,7 @@ USERSPACE I/O (UIO)
M: "Hans J. Koch" <hjk@hansjkoch.de>
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
F: Documentation/DocBook/uio-howto.tmpl
F: drivers/uio/
F: include/linux/uio*.h

2
Makefile
View File

@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 19
SUBLEVEL = 0
EXTRAVERSION = -rc6
EXTRAVERSION = -rc7
NAME = Diseased Newt
# *DOCUMENTATION*

2
arch/alpha/mm/fault.c
View File

@ -156,6 +156,8 @@ retry:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/arc/mm/fault.c
View File

@ -161,6 +161,8 @@ good_area:
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;

8
arch/arm/boot/dts/imx6sx-sdb.dts
View File

@ -166,12 +166,12 @@
#address-cells = <1>;
#size-cells = <0>;
ethphy1: ethernet-phy@0 {
reg = <0>;
ethphy1: ethernet-phy@1 {
reg = <1>;
};
ethphy2: ethernet-phy@1 {
reg = <1>;
ethphy2: ethernet-phy@2 {
reg = <2>;
};
};
};

20
arch/arm/boot/dts/sun4i-a10.dtsi
View File

@ -17,14 +17,6 @@
aliases {
ethernet0 = &emac;
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
serial3 = &uart3;
serial4 = &uart4;
serial5 = &uart5;
serial6 = &uart6;
serial7 = &uart7;
};
chosen {
@ -39,6 +31,14 @@
<&ahb_gates 44>;
status = "disabled";
};
framebuffer@1 {
compatible = "allwinner,simple-framebuffer", "simple-framebuffer";
allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi";
clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>,
<&ahb_gates 44>, <&ahb_gates 46>;
status = "disabled";
};
};
cpus {
@ -438,8 +438,8 @@
reg-names = "phy_ctrl", "pmu1", "pmu2";
clocks = <&usb_clk 8>;
clock-names = "usb_phy";
resets = <&usb_clk 1>, <&usb_clk 2>;
reset-names = "usb1_reset", "usb2_reset";
resets = <&usb_clk 0>, <&usb_clk 1>, <&usb_clk 2>;
reset-names = "usb0_reset", "usb1_reset", "usb2_reset";
status = "disabled";
};

6
arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
View File

@ -55,6 +55,12 @@
model = "Olimex A10s-Olinuxino Micro";
compatible = "olimex,a10s-olinuxino-micro", "allwinner,sun5i-a10s";
aliases {
serial0 = &uart0;
serial1 = &uart2;
serial2 = &uart3;
};
soc@01c00000 {
emac: ethernet@01c0b000 {
pinctrl-names = "default";

8
arch/arm/boot/dts/sun5i-a10s.dtsi
View File

@ -18,10 +18,6 @@
aliases {
ethernet0 = &emac;
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
serial3 = &uart3;
};
chosen {
@ -390,8 +386,8 @@
reg-names = "phy_ctrl", "pmu1";
clocks = <&usb_clk 8>;
clock-names = "usb_phy";
resets = <&usb_clk 1>;
reset-names = "usb1_reset";
resets = <&usb_clk 0>, <&usb_clk 1>;
reset-names = "usb0_reset", "usb1_reset";
status = "disabled";
};

4
arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
View File

@ -53,6 +53,10 @@
model = "HSG H702";
compatible = "hsg,h702", "allwinner,sun5i-a13";
aliases {
serial0 = &uart1;
};
soc@01c00000 {
mmc0: mmc@01c0f000 {
pinctrl-names = "default";

4
arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts
View File

@ -54,6 +54,10 @@
model = "Olimex A13-Olinuxino Micro";
compatible = "olimex,a13-olinuxino-micro", "allwinner,sun5i-a13";
aliases {
serial0 = &uart1;
};
soc@01c00000 {
mmc0: mmc@01c0f000 {
pinctrl-names = "default";

4
arch/arm/boot/dts/sun5i-a13-olinuxino.dts
View File

@ -55,6 +55,10 @@
model = "Olimex A13-Olinuxino";
compatible = "olimex,a13-olinuxino", "allwinner,sun5i-a13";
aliases {
serial0 = &uart1;
};
soc@01c00000 {
mmc0: mmc@01c0f000 {
pinctrl-names = "default";

9
arch/arm/boot/dts/sun5i-a13.dtsi
View File

@ -16,11 +16,6 @@
/ {
interrupt-parent = <&intc>;
aliases {
serial0 = &uart1;
serial1 = &uart3;
};
cpus {
#address-cells = <1>;
#size-cells = <0>;
@ -349,8 +344,8 @@
reg-names = "phy_ctrl", "pmu1";
clocks = <&usb_clk 8>;
clock-names = "usb_phy";
resets = <&usb_clk 1>;
reset-names = "usb1_reset";
resets = <&usb_clk 0>, <&usb_clk 1>;
reset-names = "usb0_reset", "usb1_reset";
status = "disabled";
};

6
arch/arm/boot/dts/sun6i-a31.dtsi
View File

@ -53,12 +53,6 @@
interrupt-parent = <&gic>;
aliases {
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
serial3 = &uart3;
serial4 = &uart4;
serial5 = &uart5;
ethernet0 = &gmac;
};

6
arch/arm/boot/dts/sun7i-a20-bananapi.dts
View File

@ -55,6 +55,12 @@
model = "LeMaker Banana Pi";
compatible = "lemaker,bananapi", "allwinner,sun7i-a20";
aliases {
serial0 = &uart0;
serial1 = &uart3;
serial2 = &uart7;
};
soc@01c00000 {
spi0: spi@01c05000 {
pinctrl-names = "default";

8
arch/arm/boot/dts/sun7i-a20-hummingbird.dts
View File

@ -19,6 +19,14 @@
model = "Merrii A20 Hummingbird";
compatible = "merrii,a20-hummingbird", "allwinner,sun7i-a20";
aliases {
serial0 = &uart0;
serial1 = &uart2;
serial2 = &uart3;
serial3 = &uart4;
serial4 = &uart5;
};
soc@01c00000 {
mmc0: mmc@01c0f000 {
pinctrl-names = "default";

3
arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
View File

@ -20,6 +20,9 @@
compatible = "olimex,a20-olinuxino-micro", "allwinner,sun7i-a20";
aliases {
serial0 = &uart0;
serial1 = &uart6;
serial2 = &uart7;
spi0 = &spi1;
spi1 = &spi2;
};

8
arch/arm/boot/dts/sun7i-a20.dtsi
View File

@ -54,14 +54,6 @@
aliases {
ethernet0 = &gmac;
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
serial3 = &uart3;
serial4 = &uart4;
serial5 = &uart5;
serial6 = &uart6;
serial7 = &uart7;
};
chosen {

4
arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
View File

@ -55,6 +55,10 @@
model = "Ippo Q8H Dual Core Tablet (v5)";
compatible = "ippo,q8h-v5", "allwinner,sun8i-a23";
aliases {
serial0 = &r_uart;
};
chosen {
bootargs = "earlyprintk console=ttyS0,115200";
};

9
arch/arm/boot/dts/sun8i-a23.dtsi
View File

@ -52,15 +52,6 @@
/ {
interrupt-parent = <&gic>;
aliases {
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
serial3 = &uart3;
serial4 = &uart4;
serial5 = &r_uart;
};
cpus {
#address-cells = <1>;
#size-cells = <0>;

5
arch/arm/boot/dts/sun9i-a80-optimus.dts
View File

@ -54,6 +54,11 @@
model = "Merrii A80 Optimus Board";
compatible = "merrii,a80-optimus", "allwinner,sun9i-a80";
aliases {
serial0 = &uart0;
serial1 = &uart4;
};
chosen {
bootargs = "earlyprintk console=ttyS0,115200";
};

10
arch/arm/boot/dts/sun9i-a80.dtsi
View File

@ -52,16 +52,6 @@
/ {
interrupt-parent = <&gic>;
aliases {
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
serial3 = &uart3;
serial4 = &uart4;
serial5 = &uart5;
serial6 = &r_uart;
};
cpus {
#address-cells = <1>;
#size-cells = <0>;

10
arch/arm/include/asm/kvm_emulate.h
View File

@ -38,6 +38,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
vcpu->arch.hcr = HCR_GUEST_MASK;
}
static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
{
return vcpu->arch.hcr;
}
static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
{
vcpu->arch.hcr = hcr;
}
static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
{
return 1;

3
arch/arm/include/asm/kvm_host.h
View File

@ -125,9 +125,6 @@ struct kvm_vcpu_arch {
* Anything that is not used directly from assembly code goes
* here.
*/
/* dcache set/way operation pending */
int last_pcpu;
cpumask_t require_dcache_flush;
/* Don't run the guest on this vcpu */
bool pause;

77
arch/arm/include/asm/kvm_mmu.h
View File

@ -44,6 +44,7 @@
#ifndef __ASSEMBLY__
#include <linux/highmem.h>
#include <asm/cacheflush.h>
#include <asm/pgalloc.h>
@ -161,13 +162,10 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
}
static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
unsigned long size,
bool ipa_uncached)
static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
unsigned long size,
bool ipa_uncached)
{
if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
kvm_flush_dcache_to_poc((void *)hva, size);
/*
* If we are going to insert an instruction page and the icache is
* either VIPT or PIPT, there is a potential problem where the host
@ -179,18 +177,77 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
*
* VIVT caches are tagged using both the ASID and the VMID and doesn't
* need any kind of flushing (DDI 0406C.b - Page B3-1392).
*
* We need to do this through a kernel mapping (using the
* user-space mapping has proved to be the wrong
* solution). For that, we need to kmap one page at a time,
* and iterate over the range.
*/
if (icache_is_pipt()) {
__cpuc_coherent_user_range(hva, hva + size);
} else if (!icache_is_vivt_asid_tagged()) {
bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
VM_BUG_ON(size & PAGE_MASK);
if (!need_flush && !icache_is_pipt())
goto vipt_cache;
while (size) {
void *va = kmap_atomic_pfn(pfn);
if (need_flush)
kvm_flush_dcache_to_poc(va, PAGE_SIZE);
if (icache_is_pipt())
__cpuc_coherent_user_range((unsigned long)va,
(unsigned long)va + PAGE_SIZE);
size -= PAGE_SIZE;
pfn++;
kunmap_atomic(va);
}
vipt_cache:
if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
/* any kind of VIPT cache */
__flush_icache_all();
}
}
static inline void __kvm_flush_dcache_pte(pte_t pte)
{
void *va = kmap_atomic(pte_page(pte));
kvm_flush_dcache_to_poc(va, PAGE_SIZE);
kunmap_atomic(va);
}
static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
{
unsigned long size = PMD_SIZE;
pfn_t pfn = pmd_pfn(pmd);
while (size) {
void *va = kmap_atomic_pfn(pfn);
kvm_flush_dcache_to_poc(va, PAGE_SIZE);
pfn++;
size -= PAGE_SIZE;
kunmap_atomic(va);
}
}
static inline void __kvm_flush_dcache_pud(pud_t pud)
{
}
#define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x))
void stage2_flush_vm(struct kvm *kvm);
void kvm_set_way_flush(struct kvm_vcpu *vcpu);
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
#endif /* !__ASSEMBLY__ */

10
arch/arm/kvm/arm.c
View File

@ -281,15 +281,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vcpu->cpu = cpu;
vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
/*
* Check whether this vcpu requires the cache to be flushed on
* this physical CPU. This is a consequence of doing dcache
* operations by set/way on this vcpu. We do it here to be in
* a non-preemptible section.
*/
if (cpumask_test_and_clear_cpu(cpu, &vcpu->arch.require_dcache_flush))
flush_cache_all(); /* We'd really want v7_flush_dcache_all() */
kvm_arm_set_running_vcpu(vcpu);
}
@ -541,7 +532,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->arch.last_pcpu = smp_processor_id();
kvm_guest_exit();
trace_kvm_exit(*vcpu_pc(vcpu));
/*

70
arch/arm/kvm/coproc.c
View File

@ -189,82 +189,40 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu,
return true;
}
/* See note at ARM ARM B1.14.4 */
/*
* See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
*/
static bool access_dcsw(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r)
{
unsigned long val;
int cpu;
if (!p->is_write)
return read_from_write_only(vcpu, p);
cpu = get_cpu();
cpumask_setall(&vcpu->arch.require_dcache_flush);
cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
/* If we were already preempted, take the long way around */
if (cpu != vcpu->arch.last_pcpu) {
flush_cache_all();
goto done;
}
val = *vcpu_reg(vcpu, p->Rt1);
switch (p->CRm) {
case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */
case 14: /* DCCISW */
asm volatile("mcr p15, 0, %0, c7, c14, 2" : : "r" (val));
break;
case 10: /* DCCSW */
asm volatile("mcr p15, 0, %0, c7, c10, 2" : : "r" (val));
break;
}
done:
put_cpu();
kvm_set_way_flush(vcpu);
return true;
}
/*
* Generic accessor for VM registers. Only called as long as HCR_TVM
* is set.
* is set. If the guest enables the MMU, we stop trapping the VM
* sys_regs and leave it in complete control of the caches.
*
* Used by the cpu-specific code.
*/
static bool access_vm_reg(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r)
bool access_vm_reg(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r)
{
bool was_enabled = vcpu_has_cache_enabled(vcpu);
BUG_ON(!p->is_write);
vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
if (p->is_64bit)
vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
return true;
}
/*
* SCTLR accessor. Only called as long as HCR_TVM is set. If the
* guest enables the MMU, we stop trapping the VM sys_regs and leave
* it in complete control of the caches.
*
* Used by the cpu-specific code.
*/
bool access_sctlr(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r)
{
access_vm_reg(vcpu, p, r);
if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */
vcpu->arch.hcr &= ~HCR_TVM;
stage2_flush_vm(vcpu->kvm);
}
kvm_toggle_cache(vcpu, was_enabled);
return true;
}

6
arch/arm/kvm/coproc.h
View File

@ -153,8 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
#define is64 .is_64 = true
#define is32 .is_64 = false
bool access_sctlr(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r);
bool access_vm_reg(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
const struct coproc_reg *r);
#endif /* __ARM_KVM_COPROC_LOCAL_H__ */

2
arch/arm/kvm/coproc_a15.c
View File

@ -34,7 +34,7 @@
static const struct coproc_reg a15_regs[] = {
/* SCTLR: swapped by interrupt.S. */
{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 },
};
static struct kvm_coproc_target_table a15_target_table = {

2
arch/arm/kvm/coproc_a7.c
View File

@ -37,7 +37,7 @@
static const struct coproc_reg a7_regs[] = {
/* SCTLR: swapped by interrupt.S. */
{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
access_sctlr, reset_val, c1_SCTLR, 0x00C50878 },
access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 },
};
static struct kvm_coproc_target_table a7_target_table = {

164
arch/arm/kvm/mmu.c
View File

@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
}
/*
* D-Cache management functions. They take the page table entries by
* value, as they are flushing the cache using the kernel mapping (or
* kmap on 32bit).
*/
static void kvm_flush_dcache_pte(pte_t pte)
{
__kvm_flush_dcache_pte(pte);
}
static void kvm_flush_dcache_pmd(pmd_t pmd)
{
__kvm_flush_dcache_pmd(pmd);
}
static void kvm_flush_dcache_pud(pud_t pud)
{
__kvm_flush_dcache_pud(pud);
}
static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
int min, int max)
{
@ -119,6 +139,26 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
put_page(virt_to_page(pmd));
}
/*
* Unmapping vs dcache management:
*
* If a guest maps certain memory pages as uncached, all writes will
* bypass the data cache and go directly to RAM. However, the CPUs
* can still speculate reads (not writes) and fill cache lines with
* data.
*
* Those cache lines will be *clean* cache lines though, so a
* clean+invalidate operation is equivalent to an invalidate
* operation, because no cache lines are marked dirty.
*
* Those clean cache lines could be filled prior to an uncached write
* by the guest, and the cache coherent IO subsystem would therefore
* end up writing old data to disk.
*
* This is why right after unmapping a page/section and invalidating
* the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
* the IO subsystem will never hit in the cache.
*/
static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
@ -128,9 +168,16 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
start_pte = pte = pte_offset_kernel(pmd, addr);
do {
if (!pte_none(*pte)) {
pte_t old_pte = *pte;
kvm_set_pte(pte, __pte(0));
put_page(virt_to_page(pte));
kvm_tlb_flush_vmid_ipa(kvm, addr);
/* No need to invalidate the cache for device mappings */
if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
kvm_flush_dcache_pte(old_pte);
put_page(virt_to_page(pte));
}
} while (pte++, addr += PAGE_SIZE, addr != end);
@ -149,8 +196,13 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
next = kvm_pmd_addr_end(addr, end);
if (!pmd_none(*pmd)) {
if (kvm_pmd_huge(*pmd)) {
pmd_t old_pmd = *pmd;
pmd_clear(pmd);
kvm_tlb_flush_vmid_ipa(kvm, addr);
kvm_flush_dcache_pmd(old_pmd);
put_page(virt_to_page(pmd));
} else {
unmap_ptes(kvm, pmd, addr, next);
@ -173,8 +225,13 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
next = kvm_pud_addr_end(addr, end);
if (!pud_none(*pud)) {
if (pud_huge(*pud)) {
pud_t old_pud = *pud;
pud_clear(pud);
kvm_tlb_flush_vmid_ipa(kvm, addr);
kvm_flush_dcache_pud(old_pud);
put_page(virt_to_page(pud));
} else {
unmap_pmds(kvm, pud, addr, next);
@ -209,10 +266,9 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
pte = pte_offset_kernel(pmd, addr);
do {
if (!pte_none(*pte)) {
hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
}
if (!pte_none(*pte) &&
(pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
kvm_flush_dcache_pte(*pte);
} while (pte++, addr += PAGE_SIZE, addr != end);
}
@ -226,12 +282,10 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
do {
next = kvm_pmd_addr_end(addr, end);
if (!pmd_none(*pmd)) {
if (kvm_pmd_huge(*pmd)) {
hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
} else {
if (kvm_pmd_huge(*pmd))
kvm_flush_dcache_pmd(*pmd);
else
stage2_flush_ptes(kvm, pmd, addr, next);
}
}
} while (pmd++, addr = next, addr != end);
}
@ -246,12 +300,10 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
do {
next = kvm_pud_addr_end(addr, end);
if (!pud_none(*pud)) {
if (pud_huge(*pud)) {
hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
} else {
if (pud_huge(*pud))
kvm_flush_dcache_pud(*pud);
else
stage2_flush_pmds(kvm, pud, addr, next);
}
}
} while (pud++, addr = next, addr != end);
}
@ -278,7 +330,7 @@ static void stage2_flush_memslot(struct kvm *kvm,
* Go through the stage 2 page tables and invalidate any cache lines
* backing memory already mapped to the VM.
*/
void stage2_flush_vm(struct kvm *kvm)
static void stage2_flush_vm(struct kvm *kvm)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
@ -905,6 +957,12 @@ static bool kvm_is_device_pfn(unsigned long pfn)
return !pfn_valid(pfn);
}
static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
unsigned long size, bool uncached)
{
__coherent_cache_guest_page(vcpu, pfn, size, uncached);
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_memory_slot *memslot, unsigned long hva,
unsigned long fault_status)
@ -994,8 +1052,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
kvm_set_s2pmd_writable(&new_pmd);
kvm_set_pfn_dirty(pfn);
}
coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE,
fault_ipa_uncached);
coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = pfn_pte(pfn, mem_type);
@ -1003,8 +1060,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
kvm_set_s2pte_writable(&new_pte);
kvm_set_pfn_dirty(pfn);
}
coherent_cache_guest_page(vcpu, hva, PAGE_SIZE,
fault_ipa_uncached);
coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
}
@ -1411,3 +1467,71 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
unmap_stage2_range(kvm, gpa, size);
spin_unlock(&kvm->mmu_lock);
}
/*
* See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
*
* Main problems:
* - S/W ops are local to a CPU (not broadcast)
* - We have line migration behind our back (speculation)
* - System caches don't support S/W at all (damn!)
*
* In the face of the above, the best we can do is to try and convert
* S/W ops to VA ops. Because the guest is not allowed to infer the
* S/W to PA mapping, it can only use S/W to nuke the whole cache,
* which is a rather good thing for us.
*
* Also, it is only used when turning caches on/off ("The expected
* usage of the cache maintenance instructions that operate by set/way
* is associated with the cache maintenance instructions associated
* with the powerdown and powerup of caches, if this is required by
* the implementation.").
*
* We use the following policy:
*
* - If we trap a S/W operation, we enable VM trapping to detect
* caches being turned on/off, and do a full clean.
*
* - We flush the caches on both caches being turned on and off.
*
* - Once the caches are enabled, we stop trapping VM ops.
*/
void kvm_set_way_flush(struct kvm_vcpu *vcpu)
{
unsigned long hcr = vcpu_get_hcr(vcpu);
/*
* If this is the first time we do a S/W operation
* (i.e. HCR_TVM not set) flush the whole memory, and set the
* VM trapping.
*
* Otherwise, rely on the VM trapping to wait for the MMU +
* Caches to be turned off. At that point, we'll be able to
* clean the caches again.
*/
if (!(hcr & HCR_TVM)) {
trace_kvm_set_way_flush(*vcpu_pc(vcpu),
vcpu_has_cache_enabled(vcpu));
stage2_flush_vm(vcpu->kvm);
vcpu_set_hcr(vcpu, hcr | HCR_TVM);
}
}
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
{
bool now_enabled = vcpu_has_cache_enabled(vcpu);
/*
* If switching the MMU+caches on, need to invalidate the caches.
* If switching it off, need to clean the caches.
* Clean + invalidate does the trick always.
*/
if (now_enabled != was_enabled)
stage2_flush_vm(vcpu->kvm);
/* Caches are now on, stop trapping VM ops (until a S/W op) */
if (now_enabled)
vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) & ~HCR_TVM);
trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
}

39
arch/arm/kvm/trace.h
View File

@ -223,6 +223,45 @@ TRACE_EVENT(kvm_hvc,
__entry->vcpu_pc, __entry->r0, __entry->imm)
);
TRACE_EVENT(kvm_set_way_flush,
TP_PROTO(unsigned long vcpu_pc, bool cache),
TP_ARGS(vcpu_pc, cache),
TP_STRUCT__entry(
__field( unsigned long, vcpu_pc )
__field( bool, cache )
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->cache = cache;
),
TP_printk("S/W flush at 0x%016lx (cache %s)",
__entry->vcpu_pc, __entry->cache ? "on" : "off")
);
TRACE_EVENT(kvm_toggle_cache,
TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
TP_ARGS(vcpu_pc, was, now),
TP_STRUCT__entry(
__field( unsigned long, vcpu_pc )
__field( bool, was )
__field( bool, now )
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->was = was;
__entry->now = now;
),
TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
__entry->vcpu_pc, __entry->was ? "on" : "off",
__entry->now ? "on" : "off")
);
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH

7
arch/arm/mach-mvebu/coherency.c
View File

@ -189,6 +189,13 @@ static void __init armada_375_380_coherency_init(struct device_node *np)
coherency_cpu_base = of_iomap(np, 0);
arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
/*
* We should switch the PL310 to I/O coherency mode only if
* I/O coherency is actually enabled.
*/
if (!coherency_available())
return;
/*
* Add the PL310 property "arm,io-coherent". This makes sure the
* outer sync operation is not used, which allows to

20
arch/arm/mach-shmobile/board-ape6evm.c
View File

@ -18,6 +18,8 @@
#include <linux/gpio_keys.h>
#include <linux/input.h>
#include <linux/interrupt.h>
#include <linux/irqchip.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/kernel.h>
#include <linux/mfd/tmio.h>
#include <linux/mmc/host.h>
@ -273,6 +275,22 @@ static void __init ape6evm_add_standard_devices(void)
sizeof(ape6evm_leds_pdata));
}
static void __init ape6evm_legacy_init_time(void)
{
/* Do not invoke DT-based timers via clocksource_of_init() */
}
static void __init ape6evm_legacy_init_irq(void)
{
void __iomem *gic_dist_base = ioremap_nocache(0xf1001000, 0x1000);
void __iomem *gic_cpu_base = ioremap_nocache(0xf1002000, 0x1000);
gic_init(0, 29, gic_dist_base, gic_cpu_base);
/* Do not invoke DT-based interrupt code via irqchip_init() */
}
static const char *ape6evm_boards_compat_dt[] __initdata = {
"renesas,ape6evm",
NULL,
@ -280,7 +298,9 @@ static const char *ape6evm_boards_compat_dt[] __initdata = {
DT_MACHINE_START(APE6EVM_DT, "ape6evm")
.init_early = shmobile_init_delay,
.init_irq = ape6evm_legacy_init_irq,
.init_machine = ape6evm_add_standard_devices,
.init_late = shmobile_init_late,
.dt_compat = ape6evm_boards_compat_dt,
.init_time = ape6evm_legacy_init_time,
MACHINE_END

13
arch/arm/mach-shmobile/board-lager.c
View File

@ -21,6 +21,8 @@
#include <linux/input.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqchip.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/kernel.h>
#include <linux/leds.h>
#include <linux/mfd/tmio.h>
@ -811,6 +813,16 @@ static void __init lager_init(void)
lager_ksz8041_fixup);
}
static void __init lager_legacy_init_irq(void)
{
void __iomem *gic_dist_base = ioremap_nocache(0xf1001000, 0x1000);
void __iomem *gic_cpu_base = ioremap_nocache(0xf1002000, 0x1000);
gic_init(0, 29, gic_dist_base, gic_cpu_base);
/* Do not invoke DT-based interrupt code via irqchip_init() */
}
static const char * const lager_boards_compat_dt[] __initconst = {
"renesas,lager",
NULL,
@ -819,6 +831,7 @@ static const char * const lager_boards_compat_dt[] __initconst = {
DT_MACHINE_START(LAGER_DT, "lager")
.smp = smp_ops(r8a7790_smp_ops),
.init_early = shmobile_init_delay,
.init_irq = lager_legacy_init_irq,
.init_time = rcar_gen2_timer_init,
.init_machine = lager_init,
.init_late = shmobile_init_late,

2
arch/arm/mach-shmobile/setup-rcar-gen2.c
View File

@ -133,7 +133,9 @@ void __init rcar_gen2_timer_init(void)
#ifdef CONFIG_COMMON_CLK
rcar_gen2_clocks_init(mode);
#endif
#ifdef CONFIG_ARCH_SHMOBILE_MULTI
clocksource_of_init();
#endif
}
struct memory_reserve_config {

12
arch/arm/mach-shmobile/timer.c
View File

@ -70,6 +70,18 @@ void __init shmobile_init_delay(void)
if (!max_freq)
return;
#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
/* Non-multiplatform r8a73a4 SoC cannot use arch timer due
* to GIC being initialized from C and arch timer via DT */
if (of_machine_is_compatible("renesas,r8a73a4"))
has_arch_timer = false;
/* Non-multiplatform r8a7790 SoC cannot use arch timer due
* to GIC being initialized from C and arch timer via DT */
if (of_machine_is_compatible("renesas,r8a7790"))
has_arch_timer = false;
#endif
if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) {
if (is_a7_a8_a9)
shmobile_setup_delay_hz(max_freq, 1, 3);

59
arch/arm/mm/dma-mapping.c
View File

@ -1940,18 +1940,8 @@ void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
}
EXPORT_SYMBOL_GPL(arm_iommu_release_mapping);
/**
* arm_iommu_attach_device
* @dev: valid struct device pointer
* @mapping: io address space mapping structure (returned from
* arm_iommu_create_mapping)
*
* Attaches specified io address space mapping to the provided device,
* More than one client might be attached to the same io address space
* mapping.
*/
int arm_iommu_attach_device(struct device *dev,
struct dma_iommu_mapping *mapping)
static int __arm_iommu_attach_device(struct device *dev,
struct dma_iommu_mapping *mapping)
{
int err;
@ -1965,15 +1955,35 @@ int arm_iommu_attach_device(struct device *dev,
pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
return 0;
}
EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
/**
* arm_iommu_detach_device
* arm_iommu_attach_device
* @dev: valid struct device pointer
* @mapping: io address space mapping structure (returned from
* arm_iommu_create_mapping)
*
* Detaches the provided device from a previously attached map.
* Attaches specified io address space mapping to the provided device.
* This replaces the dma operations (dma_map_ops pointer) with the
* IOMMU aware version.
*
* More than one client might be attached to the same io address space
* mapping.
*/
void arm_iommu_detach_device(struct device *dev)
int arm_iommu_attach_device(struct device *dev,
struct dma_iommu_mapping *mapping)
{
int err;
err = __arm_iommu_attach_device(dev, mapping);
if (err)
return err;
set_dma_ops(dev, &iommu_ops);
return 0;
}
EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
static void __arm_iommu_detach_device(struct device *dev)
{
struct dma_iommu_mapping *mapping;
@ -1989,6 +1999,19 @@ void arm_iommu_detach_device(struct device *dev)
pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
}
/**
* arm_iommu_detach_device
* @dev: valid struct device pointer
*
* Detaches the provided device from a previously attached map.
* This voids the dma operations (dma_map_ops pointer)
*/
void arm_iommu_detach_device(struct device *dev)
{
__arm_iommu_detach_device(dev);
set_dma_ops(dev, NULL);
}
EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
static struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
@ -2011,7 +2034,7 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
return false;
}
if (arm_iommu_attach_device(dev, mapping)) {
if (__arm_iommu_attach_device(dev, mapping)) {
pr_warn("Failed to attached device %s to IOMMU_mapping\n",
dev_name(dev));
arm_iommu_release_mapping(mapping);
@ -2025,7 +2048,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
{
struct dma_iommu_mapping *mapping = dev->archdata.mapping;
arm_iommu_detach_device(dev);
__arm_iommu_detach_device(dev);
arm_iommu_release_mapping(mapping);
}

10
arch/arm64/include/asm/kvm_emulate.h
View File

@ -45,6 +45,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
vcpu->arch.hcr_el2 &= ~HCR_RW;
}
static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
{
return vcpu->arch.hcr_el2;
}
static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
{
vcpu->arch.hcr_el2 = hcr;
}
static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
{
return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;

3
arch/arm64/include/asm/kvm_host.h
View File

@ -116,9 +116,6 @@ struct kvm_vcpu_arch {
* Anything that is not used directly from assembly code goes
* here.
*/
/* dcache set/way operation pending */
int last_pcpu;
cpumask_t require_dcache_flush;
/* Don't run the guest */
bool pause;

34
arch/arm64/include/asm/kvm_mmu.h
View File

@ -243,24 +243,46 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
}
static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
unsigned long size,
bool ipa_uncached)
static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
unsigned long size,
bool ipa_uncached)
{
void *va = page_address(pfn_to_page(pfn));
if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
kvm_flush_dcache_to_poc((void *)hva, size);
kvm_flush_dcache_to_poc(va, size);
if (!icache_is_aliasing()) { /* PIPT */
flush_icache_range(hva, hva + size);
flush_icache_range((unsigned long)va,
(unsigned long)va + size);
} else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */
/* any kind of VIPT cache */
__flush_icache_all();
}
}
static inline void __kvm_flush_dcache_pte(pte_t pte)
{
struct page *page = pte_page(pte);
kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
}
static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
{
struct page *page = pmd_page(pmd);
kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
}
static inline void __kvm_flush_dcache_pud(pud_t pud)
{
struct page *page = pud_page(pud);
kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
}
#define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x))
void stage2_flush_vm(struct kvm *kvm);
void kvm_set_way_flush(struct kvm_vcpu *vcpu);
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */

75
arch/arm64/kvm/sys_regs.c
View File

@ -69,68 +69,31 @@ static u32 get_ccsidr(u32 csselr)
return ccsidr;
}
static void do_dc_cisw(u32 val)
{
asm volatile("dc cisw, %x0" : : "r" (val));
dsb(ish);
}
static void do_dc_csw(u32 val)
{
asm volatile("dc csw, %x0" : : "r" (val));
dsb(ish);
}
/* See note at ARM ARM B1.14.4 */
/*
* See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
*/
static bool access_dcsw(struct kvm_vcpu *vcpu,
const struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
unsigned long val;
int cpu;
if (!p->is_write)
return read_from_write_only(vcpu, p);
cpu = get_cpu();
cpumask_setall(&vcpu->arch.require_dcache_flush);
cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
/* If we were already preempted, take the long way around */
if (cpu != vcpu->arch.last_pcpu) {
flush_cache_all();
goto done;
}
val = *vcpu_reg(vcpu, p->Rt);
switch (p->CRm) {
case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */
case 14: /* DCCISW */
do_dc_cisw(val);
break;
case 10: /* DCCSW */
do_dc_csw(val);
break;
}
done:
put_cpu();
kvm_set_way_flush(vcpu);
return true;
}
/*
* Generic accessor for VM registers. Only called as long as HCR_TVM
* is set.
* is set. If the guest enables the MMU, we stop trapping the VM
* sys_regs and leave it in complete control of the caches.
*/
static bool access_vm_reg(struct kvm_vcpu *vcpu,
const struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
unsigned long val;
bool was_enabled = vcpu_has_cache_enabled(vcpu);
BUG_ON(!p->is_write);
@ -143,25 +106,7 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
}
return true;
}
/*
* SCTLR_EL1 accessor. Only called as long as HCR_TVM is set. If the
* guest enables the MMU, we stop trapping the VM sys_regs and leave
* it in complete control of the caches.
*/
static bool access_sctlr(struct kvm_vcpu *vcpu,
const struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
access_vm_reg(vcpu, p, r);
if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */
vcpu->arch.hcr_el2 &= ~HCR_TVM;
stage2_flush_vm(vcpu->kvm);
}
kvm_toggle_cache(vcpu, was_enabled);
return true;
}
@ -377,7 +322,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
NULL, reset_mpidr, MPIDR_EL1 },
/* SCTLR_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
/* CPACR_EL1 */
{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
NULL, reset_val, CPACR_EL1, 0 },
@ -657,7 +602,7 @@ static const struct sys_reg_desc cp14_64_regs[] = {
* register).
*/
static const struct sys_reg_desc cp15_regs[] = {
{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },

2
arch/avr32/mm/fault.c
View File

@ -142,6 +142,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/cris/mm/fault.c
View File

@ -176,6 +176,8 @@ retry:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/frv/mm/fault.c
View File

@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/ia64/mm/fault.c
View File

@ -172,6 +172,8 @@ retry:
*/
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
} else if (fault & VM_FAULT_SIGSEGV) {
goto bad_area;
} else if (fault & VM_FAULT_SIGBUS) {
signal = SIGBUS;
goto bad_area;

2
arch/m32r/mm/fault.c
View File

@ -200,6 +200,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/m68k/mm/fault.c
View File

@ -145,6 +145,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto map_err;
else if (fault & VM_FAULT_SIGBUS)
goto bus_err;
BUG();

2
arch/metag/mm/fault.c
View File

@ -141,6 +141,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/microblaze/mm/fault.c
View File

@ -224,6 +224,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/mips/mm/fault.c
View File

@ -158,6 +158,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/mn10300/mm/fault.c
View File

@ -262,6 +262,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/nios2/mm/fault.c
View File

@ -135,6 +135,8 @@ survive:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/openrisc/mm/fault.c
View File

@ -171,6 +171,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/parisc/mm/fault.c
View File

@ -256,6 +256,8 @@ good_area:
*/
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto bad_area;
BUG();

4
arch/powerpc/include/asm/fsl_pamu_stash.h
View File

@ -32,8 +32,8 @@ enum pamu_stash_target {
*/
struct pamu_stash_attribute {
u32 cpu; /* cpu number */
u32 cache; /* cache to stash to: L1,L2,L3 */
u32 cpu; /* cpu number */
u32 cache; /* cache to stash to: L1,L2,L3 */
};
#endif /* __FSL_PAMU_STASH_H */

2
arch/powerpc/mm/copro_fault.c
View File

@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
if (*flt & VM_FAULT_OOM) {
ret = -ENOMEM;
goto out_unlock;
} else if (*flt & VM_FAULT_SIGBUS) {
} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
ret = -EFAULT;
goto out_unlock;
}

2
arch/powerpc/mm/fault.c
View File

@ -437,6 +437,8 @@ good_area:
*/
fault = handle_mm_fault(mm, vma, address, flags);
if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
rc = mm_fault_error(regs, address, fault);
if (rc >= MM_FAULT_RETURN)
goto bail;

2
arch/powerpc/platforms/powernv/setup.c
View File

@ -304,7 +304,7 @@ int pnv_save_sprs_for_winkle(void)
* all cpus at boot. Get these reg values of current cpu and use the
* same accross all cpus.
*/
uint64_t lpcr_val = mfspr(SPRN_LPCR);
uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
uint64_t hid0_val = mfspr(SPRN_HID0);
uint64_t hid1_val = mfspr(SPRN_HID1);
uint64_t hid4_val = mfspr(SPRN_HID4);

1
arch/powerpc/xmon/xmon.c
View File

@ -337,6 +337,7 @@ static inline void disable_surveillance(void)
args.token = rtas_token("set-indicator");
if (args.token == RTAS_UNKNOWN_SERVICE)
return;
args.token = cpu_to_be32(args.token);
args.nargs = cpu_to_be32(3);
args.nret = cpu_to_be32(1);
args.rets = &args.args[3];

6
arch/s390/mm/fault.c
View File

@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
do_no_context(regs);
else
pagefault_out_of_memory();
} else if (fault & VM_FAULT_SIGSEGV) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
do_no_context(regs);
else
do_sigsegv(regs, SEGV_MAPERR);
} else if (fault & VM_FAULT_SIGBUS) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))

2
arch/score/mm/fault.c
View File

@ -114,6 +114,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/sh/mm/fault.c
View File

@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
} else {
if (fault & VM_FAULT_SIGBUS)
do_sigbus(regs, error_code, address);
else if (fault & VM_FAULT_SIGSEGV)
bad_area(regs, error_code, address);
else
BUG();
}

2
arch/sparc/mm/fault_32.c
View File

@ -249,6 +249,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/sparc/mm/fault_64.c
View File

@ -446,6 +446,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/tile/mm/fault.c
View File

@ -442,6 +442,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
arch/um/kernel/trap.c
View File

@ -80,6 +80,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
} else if (fault & VM_FAULT_SIGSEGV) {
goto out;
} else if (fault & VM_FAULT_SIGBUS) {
err = -EACCES;
goto out;

2
arch/x86/boot/compressed/Makefile
View File

@ -90,7 +90,7 @@ suffix-$(CONFIG_KERNEL_LZO) := lzo
suffix-$(CONFIG_KERNEL_LZ4) := lz4
RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
perl $(srctree)/arch/x86/tools/calc_run_size.pl)
$(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
quiet_cmd_mkpiggy = MKPIGGY $@
cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )

1
arch/x86/kernel/cpu/perf_event_intel.c
View File

@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
break;
case 55: /* 22nm Atom "Silvermont" */
case 76: /* 14nm Atom "Airmont" */
case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));

2
arch/x86/kernel/cpu/perf_event_intel_rapl.c
View File

@ -142,7 +142,7 @@ static inline u64 rapl_scale(u64 v)
* or use ldexp(count, -32).
* Watts = Joules/Time delta
*/
return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
}
static u64 rapl_event_update(struct perf_event *event)

9
arch/x86/kernel/cpu/perf_event_intel_uncore.c
View File

@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
box->phys_id = phys_id;
box->pci_dev = pdev;
box->pmu = pmu;
uncore_box_init(box);
pci_set_drvdata(pdev, box);
raw_spin_lock(&uncore_box_lock);
@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu)
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
/* called by uncore_cpu_init? */
if (box && box->phys_id >= 0) {
uncore_box_init(box);
if (box && box->phys_id >= 0)
continue;
}
for_each_online_cpu(k) {
exist = *per_cpu_ptr(pmu->box, k);
@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu)
}
}
if (box) {
if (box)
box->phys_id = phys_id;
uncore_box_init(box);
}
}
}
return 0;

18
arch/x86/kernel/cpu/perf_event_intel_uncore.h
View File

@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
return box->pmu->type->num_counters;
}
static inline void uncore_box_init(struct intel_uncore_box *box)
{
if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
if (box->pmu->type->ops->init_box)
box->pmu->type->ops->init_box(box);
}
}
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
static inline void uncore_enable_box(struct intel_uncore_box *box)
{
uncore_box_init(box);
if (box->pmu->type->ops->enable_box)
box->pmu->type->ops->enable_box(box);
}
@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
return box->pmu->type->ops->read_counter(box, event);
}
static inline void uncore_box_init(struct intel_uncore_box *box)
{
if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
if (box->pmu->type->ops->init_box)
box->pmu->type->ops->init_box(box);
}
}
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
return (box->phys_id < 0);

3
arch/x86/kvm/lapic.c
View File

@ -192,6 +192,9 @@ static void recalculate_apic_map(struct kvm *kvm)
u16 cid, lid;
u32 ldr, aid;
if (!kvm_apic_present(vcpu))
continue;
aid = kvm_apic_id(apic);
ldr = kvm_apic_get_reg(apic, APIC_LDR);
cid = apic_cluster_id(new, ldr);

2
arch/x86/mm/fault.c
View File

@ -898,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
do_sigbus(regs, error_code, address, fault);
else if (fault & VM_FAULT_SIGSEGV)
bad_area_nosemaphore(regs, error_code, address);
else
BUG();
}

39
arch/x86/tools/calc_run_size.pl
View File

@ -1,39 +0,0 @@
#!/usr/bin/perl
#
# Calculate the amount of space needed to run the kernel, including room for
# the .bss and .brk sections.
#
# Usage:
# objdump -h a.out | perl calc_run_size.pl
use strict;
my $mem_size = 0;
my $file_offset = 0;
my $sections=" *[0-9]+ \.(?:bss|brk) +";
while (<>) {
if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
my $size = hex($1);
my $offset = hex($2);
$mem_size += $size;
if ($file_offset == 0) {
$file_offset = $offset;
} elsif ($file_offset != $offset) {
# BFD linker shows the same file offset in ELF.
# Gold linker shows them as consecutive.
next if ($file_offset + $mem_size == $offset + $size);
printf STDERR "file_offset: 0x%lx\n", $file_offset;
printf STDERR "mem_size: 0x%lx\n", $mem_size;
printf STDERR "offset: 0x%lx\n", $offset;
printf STDERR "size: 0x%lx\n", $size;
die ".bss and .brk are non-contiguous\n";
}
}
}
if ($file_offset == 0) {
die "Never found .bss or .brk file offset\n";
}
printf("%d\n", $mem_size + $file_offset);

42
arch/x86/tools/calc_run_size.sh Normal file
View File

@ -0,0 +1,42 @@
#!/bin/sh
#
# Calculate the amount of space needed to run the kernel, including room for
# the .bss and .brk sections.
#
# Usage:
# objdump -h a.out | sh calc_run_size.sh
NUM='\([0-9a-fA-F]*[ \t]*\)'
OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p')
if [ -z "$OUT" ] ; then
echo "Never found .bss or .brk file offset" >&2
exit 1
fi
OUT=$(echo ${OUT# })
sizeA=$(printf "%d" 0x${OUT%% *})
OUT=${OUT#* }
offsetA=$(printf "%d" 0x${OUT%% *})
OUT=${OUT#* }
sizeB=$(printf "%d" 0x${OUT%% *})
OUT=${OUT#* }
offsetB=$(printf "%d" 0x${OUT%% *})
run_size=$(( $offsetA + $sizeA + $sizeB ))
# BFD linker shows the same file offset in ELF.
if [ "$offsetA" -ne "$offsetB" ] ; then
# Gold linker shows them as consecutive.
endB=$(( $offsetB + $sizeB ))
if [ "$endB" != "$run_size" ] ; then
printf "sizeA: 0x%x\n" $sizeA >&2
printf "offsetA: 0x%x\n" $offsetA >&2
printf "sizeB: 0x%x\n" $sizeB >&2
printf "offsetB: 0x%x\n" $offsetB >&2
echo ".bss and .brk are non-contiguous" >&2
exit 1
fi
fi
printf "%d\n" $run_size
exit 0

2
arch/xtensa/mm/fault.c
View File

@ -117,6 +117,8 @@ good_area:
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();

2
drivers/Kconfig
View File

@ -134,8 +134,6 @@ source "drivers/staging/Kconfig"
source "drivers/platform/Kconfig"
source "drivers/soc/Kconfig"
source "drivers/clk/Kconfig"
source "drivers/hwspinlock/Kconfig"

25
drivers/block/rbd.c
View File

@ -2098,32 +2098,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev)
* If an image has a non-zero parent overlap, get a reference to its
* parent.
*
* We must get the reference before checking for the overlap to
* coordinate properly with zeroing the parent overlap in
* rbd_dev_v2_parent_info() when an image gets flattened. We
* drop it again if there is no overlap.
*
* Returns true if the rbd device has a parent with a non-zero
* overlap and a reference for it was successfully taken, or
* false otherwise.
*/
static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
{
int counter;
int counter = 0;
if (!rbd_dev->parent_spec)
return false;
counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
if (counter > 0 && rbd_dev->parent_overlap)
return true;
/* Image was flattened, but parent is not yet torn down */
down_read(&rbd_dev->header_rwsem);
if (rbd_dev->parent_overlap)
counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
up_read(&rbd_dev->header_rwsem);
if (counter < 0)
rbd_warn(rbd_dev, "parent reference overflow");
return false;
return counter > 0;
}
/*
@ -4239,7 +4233,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
*/
if (rbd_dev->parent_overlap) {
rbd_dev->parent_overlap = 0;
smp_mb();
rbd_dev_parent_put(rbd_dev);
pr_info("%s: clone image has been flattened\n",
rbd_dev->disk->disk_name);
@ -4285,7 +4278,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
* treat it specially.
*/
rbd_dev->parent_overlap = overlap;
smp_mb();
if (!overlap) {
/* A null parent_spec indicates it's the initial probe */
@ -5114,10 +5106,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
{
struct rbd_image_header *header;
/* Drop parent reference unless it's already been done (or none) */
if (rbd_dev->parent_overlap)
rbd_dev_parent_put(rbd_dev);
rbd_dev_parent_put(rbd_dev);
/* Free dynamic fields from the header, then zero it out */

6
drivers/gpu/drm/amd/amdkfd/kfd_device.c
View File

@ -26,6 +26,7 @@
#include <linux/slab.h>
#include "kfd_priv.h"
#include "kfd_device_queue_manager.h"
#include "kfd_pm4_headers.h"
#define MQD_SIZE_ALIGNED 768
@ -169,9 +170,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
kfd->shared_resources = *gpu_resources;
/* calculate max size of mqds needed for queues */
size = max_num_of_processes *
max_num_of_queues_per_process *
kfd->device_info->mqd_size_aligned;
size = max_num_of_queues_per_device *
kfd->device_info->mqd_size_aligned;
/* add another 512KB for all other allocations on gart */
size += 512 * 1024;

78
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
View File

@ -183,6 +183,13 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
mutex_lock(&dqm->lock);
if (dqm->total_queue_count >= max_num_of_queues_per_device) {
pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
dqm->total_queue_count);
mutex_unlock(&dqm->lock);
return -EPERM;
}
if (list_empty(&qpd->queues_list)) {
retval = allocate_vmid(dqm, qpd, q);
if (retval != 0) {
@ -207,6 +214,14 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
list_add(&q->list, &qpd->queues_list);
dqm->queue_count++;
/*
* Unconditionally increment this counter, regardless of the queue's
* type or whether the queue is active.
*/
dqm->total_queue_count++;
pr_debug("Total of %d queues are accountable so far\n",
dqm->total_queue_count);
mutex_unlock(&dqm->lock);
return 0;
}
@ -326,6 +341,15 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
if (list_empty(&qpd->queues_list))
deallocate_vmid(dqm, qpd, q);
dqm->queue_count--;
/*
* Unconditionally decrement this counter, regardless of the queue's
* type
*/
dqm->total_queue_count--;
pr_debug("Total of %d queues are accountable so far\n",
dqm->total_queue_count);
out:
mutex_unlock(&dqm->lock);
return retval;
@ -541,10 +565,14 @@ static int init_pipelines(struct device_queue_manager *dqm,
for (i = 0; i < pipes_num; i++) {
inx = i + first_pipe;
/*
* HPD buffer on GTT is allocated by amdkfd, no need to waste
* space in GTT for pipelines we don't initialize
*/
pipe_hpd_addr = dqm->pipelines_addr + i * CIK_HPD_EOP_BYTES;
pr_debug("kfd: pipeline address %llX\n", pipe_hpd_addr);
/* = log2(bytes/4)-1 */
kfd2kgd->init_pipeline(dqm->dev->kgd, i,
kfd2kgd->init_pipeline(dqm->dev->kgd, inx,
CIK_HPD_EOP_BYTES_LOG2 - 3, pipe_hpd_addr);
}
@ -560,7 +588,7 @@ static int init_scheduler(struct device_queue_manager *dqm)
pr_debug("kfd: In %s\n", __func__);
retval = init_pipelines(dqm, get_pipes_num(dqm), KFD_DQM_FIRST_PIPE);
retval = init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm));
if (retval != 0)
return retval;
@ -752,6 +780,21 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
pr_debug("kfd: In func %s\n", __func__);
mutex_lock(&dqm->lock);
if (dqm->total_queue_count >= max_num_of_queues_per_device) {
pr_warn("amdkfd: Can't create new kernel queue because %d queues were already created\n",
dqm->total_queue_count);
mutex_unlock(&dqm->lock);
return -EPERM;
}
/*
* Unconditionally increment this counter, regardless of the queue's
* type or whether the queue is active.
*/
dqm->total_queue_count++;
pr_debug("Total of %d queues are accountable so far\n",
dqm->total_queue_count);
list_add(&kq->list, &qpd->priv_queue_list);
dqm->queue_count++;
qpd->is_debug = true;
@ -775,6 +818,13 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
dqm->queue_count--;
qpd->is_debug = false;
execute_queues_cpsch(dqm, false);
/*
* Unconditionally decrement this counter, regardless of the queue's
* type.
*/
dqm->total_queue_count++;
pr_debug("Total of %d queues are accountable so far\n",
dqm->total_queue_count);
mutex_unlock(&dqm->lock);
}
@ -793,6 +843,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
mutex_lock(&dqm->lock);
if (dqm->total_queue_count >= max_num_of_queues_per_device) {
pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
dqm->total_queue_count);
retval = -EPERM;
goto out;
}
mqd = dqm->get_mqd_manager(dqm, KFD_MQD_TYPE_CIK_CP);
if (mqd == NULL) {
mutex_unlock(&dqm->lock);
@ -810,6 +867,15 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
retval = execute_queues_cpsch(dqm, false);
}
/*
* Unconditionally increment this counter, regardless of the queue's
* type or whether the queue is active.
*/
dqm->total_queue_count++;
pr_debug("Total of %d queues are accountable so far\n",
dqm->total_queue_count);
out:
mutex_unlock(&dqm->lock);
return retval;
@ -930,6 +996,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
/*
* Unconditionally decrement this counter, regardless of the queue's
* type
*/
dqm->total_queue_count--;
pr_debug("Total of %d queues are accountable so far\n",
dqm->total_queue_count);
mutex_unlock(&dqm->lock);
return 0;

1
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
View File

@ -130,6 +130,7 @@ struct device_queue_manager {
struct list_head queues;
unsigned int processes_count;
unsigned int queue_count;
unsigned int total_queue_count;
unsigned int next_pipe_to_allocate;
unsigned int *allocated_queues;
unsigned int vmid_bitmap;

27
drivers/gpu/drm/amd/amdkfd/kfd_module.c
View File

@ -50,15 +50,10 @@ module_param(sched_policy, int, 0444);
MODULE_PARM_DESC(sched_policy,
"Kernel cmdline parameter that defines the amdkfd scheduling policy");
int max_num_of_processes = KFD_MAX_NUM_OF_PROCESSES_DEFAULT;
module_param(max_num_of_processes, int, 0444);
MODULE_PARM_DESC(max_num_of_processes,
"Kernel cmdline parameter that defines the amdkfd maximum number of supported processes");
int max_num_of_queues_per_process = KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT;
module_param(max_num_of_queues_per_process, int, 0444);
MODULE_PARM_DESC(max_num_of_queues_per_process,
"Kernel cmdline parameter that defines the amdkfd maximum number of supported queues per process");
int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
module_param(max_num_of_queues_per_device, int, 0444);
MODULE_PARM_DESC(max_num_of_queues_per_device,
"Maximum number of supported queues per device (1 = Minimum, 4096 = default)");
bool kgd2kfd_init(unsigned interface_version,
const struct kfd2kgd_calls *f2g,
@ -100,16 +95,10 @@ static int __init kfd_module_init(void)
}
/* Verify module parameters */
if ((max_num_of_processes < 0) ||
(max_num_of_processes > KFD_MAX_NUM_OF_PROCESSES)) {
pr_err("kfd: max_num_of_processes must be between 0 to KFD_MAX_NUM_OF_PROCESSES\n");
return -1;
}
if ((max_num_of_queues_per_process < 0) ||
(max_num_of_queues_per_process >
KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)) {
pr_err("kfd: max_num_of_queues_per_process must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_PROCESS\n");
if ((max_num_of_queues_per_device < 0) ||
(max_num_of_queues_per_device >
KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) {
pr_err("kfd: max_num_of_queues_per_device must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
return -1;
}

2
drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
View File

@ -30,7 +30,7 @@ static DEFINE_MUTEX(pasid_mutex);
int kfd_pasid_init(void)
{
pasid_limit = max_num_of_processes;
pasid_limit = KFD_MAX_NUM_OF_PROCESSES;
pasid_bitmap = kcalloc(BITS_TO_LONGS(pasid_limit), sizeof(long), GFP_KERNEL);
if (!pasid_bitmap)

17
drivers/gpu/drm/amd/amdkfd/kfd_priv.h
View File

@ -52,20 +52,19 @@
#define kfd_alloc_struct(ptr_to_struct) \
((typeof(ptr_to_struct)) kzalloc(sizeof(*ptr_to_struct), GFP_KERNEL))
/* Kernel module parameter to specify maximum number of supported processes */
extern int max_num_of_processes;
#define KFD_MAX_NUM_OF_PROCESSES_DEFAULT 32
#define KFD_MAX_NUM_OF_PROCESSES 512
#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
/*
* Kernel module parameter to specify maximum number of supported queues
* per process
* Kernel module parameter to specify maximum number of supported queues per
* device
*/
extern int max_num_of_queues_per_process;
extern int max_num_of_queues_per_device;
#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT 128
#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT 4096
#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE \
(KFD_MAX_NUM_OF_PROCESSES * \
KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
#define KFD_KERNEL_QUEUE_SIZE 2048

12
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
View File

@ -54,11 +54,11 @@ static int find_available_queue_slot(struct process_queue_manager *pqm,
pr_debug("kfd: in %s\n", __func__);
found = find_first_zero_bit(pqm->queue_slot_bitmap,
max_num_of_queues_per_process);
KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
pr_debug("kfd: the new slot id %lu\n", found);
if (found >= max_num_of_queues_per_process) {
if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
pr_info("amdkfd: Can not open more queues for process with pasid %d\n",
pqm->process->pasid);
return -ENOMEM;
@ -76,7 +76,7 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
INIT_LIST_HEAD(&pqm->queues);
pqm->queue_slot_bitmap =
kzalloc(DIV_ROUND_UP(max_num_of_queues_per_process,
kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS,
BITS_PER_BYTE), GFP_KERNEL);
if (pqm->queue_slot_bitmap == NULL)
return -ENOMEM;
@ -203,6 +203,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
pqn->kq = NULL;
retval = dev->dqm->create_queue(dev->dqm, q, &pdd->qpd,
&q->properties.vmid);
pr_debug("DQM returned %d for create_queue\n", retval);
print_queue(q);
break;
case KFD_QUEUE_TYPE_DIQ:
@ -222,7 +223,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
}
if (retval != 0) {
pr_err("kfd: error dqm create queue\n");
pr_debug("Error dqm create queue\n");
goto err_create_queue;
}
@ -241,7 +242,10 @@ int pqm_create_queue(struct process_queue_manager *pqm,
err_create_queue:
kfree(pqn);
err_allocate_pqn:
/* check if queues list is empty unregister process from device */
clear_bit(*qid, pqm->queue_slot_bitmap);
if (list_empty(&pqm->queues))
dev->dqm->unregister_process(dev->dqm, &pdd->qpd);
return retval;
}

30
drivers/gpu/drm/drm_fb_helper.c
View File

@ -145,6 +145,31 @@ int drm_fb_helper_add_one_connector(struct drm_fb_helper *fb_helper, struct drm_
}
EXPORT_SYMBOL(drm_fb_helper_add_one_connector);
static void remove_from_modeset(struct drm_mode_set *set,
struct drm_connector *connector)
{
int i, j;
for (i = 0; i < set->num_connectors; i++) {
if (set->connectors[i] == connector)
break;
}
if (i == set->num_connectors)
return;
for (j = i + 1; j < set->num_connectors; j++) {
set->connectors[j - 1] = set->connectors[j];
}
set->num_connectors--;
/* because i915 is pissy about this..
* TODO maybe need to makes sure we set it back to !=NULL somewhere?
*/
if (set->num_connectors == 0)
set->fb = NULL;
}
int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
struct drm_connector *connector)
{
@ -167,6 +192,11 @@ int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
}
fb_helper->connector_count--;
kfree(fb_helper_connector);
/* also cleanup dangling references to the connector: */
for (i = 0; i < fb_helper->crtc_count; i++)
remove_from_modeset(&fb_helper->crtc_info[i].mode_set, connector);
return 0;
}
EXPORT_SYMBOL(drm_fb_helper_remove_one_connector);

52
drivers/gpu/drm/i2c/tda998x_drv.c
View File

@ -32,6 +32,8 @@
struct tda998x_priv {
struct i2c_client *cec;
struct i2c_client *hdmi;
struct mutex mutex;
struct delayed_work dwork;
uint16_t rev;
uint8_t current_page;
int dpms;
@ -402,9 +404,10 @@ reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt)
uint8_t addr = REG2ADDR(reg);
int ret;
mutex_lock(&priv->mutex);
ret = set_page(priv, reg);
if (ret < 0)
return ret;
goto out;
ret = i2c_master_send(client, &addr, sizeof(addr));
if (ret < 0)
@ -414,10 +417,12 @@ reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt)
if (ret < 0)
goto fail;
return ret;
goto out;
fail:
dev_err(&client->dev, "Error %d reading from 0x%x\n", ret, reg);
out:
mutex_unlock(&priv->mutex);
return ret;
}
@ -431,13 +436,16 @@ reg_write_range(struct tda998x_priv *priv, uint16_t reg, uint8_t *p, int cnt)
buf[0] = REG2ADDR(reg);
memcpy(&buf[1], p, cnt);
mutex_lock(&priv->mutex);
ret = set_page(priv, reg);
if (ret < 0)
return;
goto out;
ret = i2c_master_send(client, buf, cnt + 1);
if (ret < 0)
dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
out:
mutex_unlock(&priv->mutex);
}
static int
@ -459,13 +467,16 @@ reg_write(struct tda998x_priv *priv, uint16_t reg, uint8_t val)
uint8_t buf[] = {REG2ADDR(reg), val};
int ret;
mutex_lock(&priv->mutex);
ret = set_page(priv, reg);
if (ret < 0)
return;
goto out;
ret = i2c_master_send(client, buf, sizeof(buf));
if (ret < 0)
dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
out:
mutex_unlock(&priv->mutex);
}
static void
@ -475,13 +486,16 @@ reg_write16(struct tda998x_priv *priv, uint16_t reg, uint16_t val)
uint8_t buf[] = {REG2ADDR(reg), val >> 8, val};
int ret;
mutex_lock(&priv->mutex);
ret = set_page(priv, reg);
if (ret < 0)
return;
goto out;
ret = i2c_master_send(client, buf, sizeof(buf));
if (ret < 0)
dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
out:
mutex_unlock(&priv->mutex);
}
static void
@ -536,6 +550,17 @@ tda998x_reset(struct tda998x_priv *priv)
reg_write(priv, REG_MUX_VP_VIP_OUT, 0x24);
}
/* handle HDMI connect/disconnect */
static void tda998x_hpd(struct work_struct *work)
{
struct delayed_work *dwork = to_delayed_work(work);
struct tda998x_priv *priv =
container_of(dwork, struct tda998x_priv, dwork);
if (priv->encoder && priv->encoder->dev)
drm_kms_helper_hotplug_event(priv->encoder->dev);
}
/*
* only 2 interrupts may occur: screen plug/unplug and EDID read
*/
@ -559,8 +584,7 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data)
priv->wq_edid_wait = 0;
wake_up(&priv->wq_edid);
} else if (cec != 0) { /* HPD change */
if (priv->encoder && priv->encoder->dev)
drm_helper_hpd_irq_event(priv->encoder->dev);
schedule_delayed_work(&priv->dwork, HZ/10);
}
return IRQ_HANDLED;
}
@ -1170,8 +1194,10 @@ static void tda998x_destroy(struct tda998x_priv *priv)
/* disable all IRQs and free the IRQ handler */
cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
if (priv->hdmi->irq)
if (priv->hdmi->irq) {
free_irq(priv->hdmi->irq, priv);
cancel_delayed_work_sync(&priv->dwork);
}
i2c_unregister_device(priv->cec);
}
@ -1255,6 +1281,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
struct device_node *np = client->dev.of_node;
u32 video;
int rev_lo, rev_hi, ret;
unsigned short cec_addr;
priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3);
priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
@ -1262,12 +1289,16 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
priv->current_page = 0xff;
priv->hdmi = client;
priv->cec = i2c_new_dummy(client->adapter, 0x34);
/* CEC I2C address bound to TDA998x I2C addr by configuration pins */
cec_addr = 0x34 + (client->addr & 0x03);
priv->cec = i2c_new_dummy(client->adapter, cec_addr);
if (!priv->cec)
return -ENODEV;
priv->dpms = DRM_MODE_DPMS_OFF;
mutex_init(&priv->mutex); /* protect the page access */
/* wake up the device: */
cec_write(priv, REG_CEC_ENAMODS,
CEC_ENAMODS_EN_RXSENS | CEC_ENAMODS_EN_HDMI);
@ -1323,8 +1354,9 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
if (client->irq) {
int irqf_trigger;
/* init read EDID waitqueue */
/* init read EDID waitqueue and HDP work */
init_waitqueue_head(&priv->wq_edid);
INIT_DELAYED_WORK(&priv->dwork, tda998x_hpd);
/* clear pending interrupts */
reg_read(priv, REG_INT_FLAGS_0);

14
drivers/gpu/drm/i915/i915_drv.c
View File

@ -462,19 +462,13 @@ void intel_detect_pch(struct drm_device *dev)
} else if (id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
dev_priv->pch_type = PCH_LPT;
DRM_DEBUG_KMS("Found LynxPoint PCH\n");
WARN_ON(!IS_HASWELL(dev));
WARN_ON(IS_HSW_ULT(dev));
} else if (IS_BROADWELL(dev)) {
dev_priv->pch_type = PCH_LPT;
dev_priv->pch_id =
INTEL_PCH_LPT_LP_DEVICE_ID_TYPE;
DRM_DEBUG_KMS("This is Broadwell, assuming "
"LynxPoint LP PCH\n");
WARN_ON(!IS_HASWELL(dev) && !IS_BROADWELL(dev));
WARN_ON(IS_HSW_ULT(dev) || IS_BDW_ULT(dev));
} else if (id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
dev_priv->pch_type = PCH_LPT;
DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
WARN_ON(!IS_HASWELL(dev));
WARN_ON(!IS_HSW_ULT(dev));
WARN_ON(!IS_HASWELL(dev) && !IS_BROADWELL(dev));
WARN_ON(!IS_HSW_ULT(dev) && !IS_BDW_ULT(dev));
} else if (id == INTEL_PCH_SPT_DEVICE_ID_TYPE) {
dev_priv->pch_type = PCH_SPT;
DRM_DEBUG_KMS("Found SunrisePoint PCH\n");

3
drivers/gpu/drm/i915/i915_drv.h
View File

@ -2159,8 +2159,7 @@ struct drm_i915_cmd_table {
#define IS_HSW_EARLY_SDV(dev) (IS_HASWELL(dev) && \
(INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
#define IS_BDW_ULT(dev) (IS_BROADWELL(dev) && \
((INTEL_DEVID(dev) & 0xf) == 0x2 || \
(INTEL_DEVID(dev) & 0xf) == 0x6 || \
((INTEL_DEVID(dev) & 0xf) == 0x6 || \
(INTEL_DEVID(dev) & 0xf) == 0xe))
#define IS_BDW_GT3(dev) (IS_BROADWELL(dev) && \
(INTEL_DEVID(dev) & 0x00F0) == 0x0020)

26
drivers/gpu/drm/i915/i915_gem.c
View File

@ -3148,6 +3148,13 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
u32 size = i915_gem_obj_ggtt_size(obj);
uint64_t val;
/* Adjust fence size to match tiled area */
if (obj->tiling_mode != I915_TILING_NONE) {
uint32_t row_size = obj->stride *
(obj->tiling_mode == I915_TILING_Y ? 32 : 8);
size = (size / row_size) * row_size;
}
val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
0xfffff000) << 32;
val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
@ -4884,13 +4891,12 @@ i915_gem_init_hw(struct drm_device *dev)
for (i = 0; i < NUM_L3_SLICES(dev); i++)
i915_gem_l3_remap(&dev_priv->ring[RCS], i);
/*
* XXX: Contexts should only be initialized once. Doing a switch to the
* default context switch however is something we'd like to do after
* reset or thaw (the latter may not actually be necessary for HW, but
* goes with our code better). Context switching requires rings (for
* the do_switch), but before enabling PPGTT. So don't move this.
*/
ret = i915_ppgtt_init_hw(dev);
if (ret && ret != -EIO) {
DRM_ERROR("PPGTT enable failed %d\n", ret);
i915_gem_cleanup_ringbuffer(dev);
}
ret = i915_gem_context_enable(dev_priv);
if (ret && ret != -EIO) {
DRM_ERROR("Context enable failed %d\n", ret);
@ -4899,12 +4905,6 @@ i915_gem_init_hw(struct drm_device *dev)
return ret;
}
ret = i915_ppgtt_init_hw(dev);
if (ret && ret != -EIO) {
DRM_ERROR("PPGTT enable failed %d\n", ret);
i915_gem_cleanup_ringbuffer(dev);
}
return ret;
}

2
drivers/gpu/drm/i915/intel_panel.c
View File

@ -962,7 +962,7 @@ void intel_panel_enable_backlight(struct intel_connector *connector)
WARN_ON(panel->backlight.max == 0);
if (panel->backlight.level == 0) {
if (panel->backlight.level <= panel->backlight.min) {
panel->backlight.level = panel->backlight.max;
if (panel->backlight.device)
panel->backlight.device->props.brightness =

1
drivers/gpu/drm/radeon/cik_sdma.c
View File

@ -816,7 +816,6 @@ void cik_sdma_vm_write_pages(struct radeon_device *rdev,
for (; ndw > 0; ndw -= 2, --count, pe += 8) {
if (flags & R600_PTE_SYSTEM) {
value = radeon_vm_map_gart(rdev, addr);
value &= 0xFFFFFFFFFFFFF000ULL;
} else if (flags & R600_PTE_VALID) {
value = addr;
} else {

1
drivers/gpu/drm/radeon/ni_dma.c
View File

@ -372,7 +372,6 @@ void cayman_dma_vm_write_pages(struct radeon_device *rdev,
for (; ndw > 0; ndw -= 2, --count, pe += 8) {
if (flags & R600_PTE_SYSTEM) {
value = radeon_vm_map_gart(rdev, addr);
value &= 0xFFFFFFFFFFFFF000ULL;
} else if (flags & R600_PTE_VALID) {
value = addr;
} else {

10
drivers/gpu/drm/radeon/r100.c
View File

@ -644,6 +644,7 @@ int r100_pci_gart_init(struct radeon_device *rdev)
return r;
rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
rdev->asic->gart.set_page = &r100_pci_gart_set_page;
return radeon_gart_table_ram_alloc(rdev);
}
@ -681,11 +682,16 @@ void r100_pci_gart_disable(struct radeon_device *rdev)
WREG32(RADEON_AIC_HI_ADDR, 0);
}
uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags)
{
return addr;
}
void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags)
uint64_t entry)
{
u32 *gtt = rdev->gart.ptr;
gtt[i] = cpu_to_le32(lower_32_bits(addr));
gtt[i] = cpu_to_le32(lower_32_bits(entry));
}
void r100_pci_gart_fini(struct radeon_device *rdev)

16
drivers/gpu/drm/radeon/r300.c
View File

@ -73,11 +73,8 @@ void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev)
#define R300_PTE_WRITEABLE (1 << 2)
#define R300_PTE_READABLE (1 << 3)
void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags)
uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags)
{
void __iomem *ptr = rdev->gart.ptr;
addr = (lower_32_bits(addr) >> 8) |
((upper_32_bits(addr) & 0xff) << 24);
if (flags & RADEON_GART_PAGE_READ)
@ -86,10 +83,18 @@ void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
addr |= R300_PTE_WRITEABLE;
if (!(flags & RADEON_GART_PAGE_SNOOP))
addr |= R300_PTE_UNSNOOPED;
return addr;
}
void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t entry)
{
void __iomem *ptr = rdev->gart.ptr;
/* on x86 we want this to be CPU endian, on powerpc
* on powerpc without HW swappers, it'll get swapped on way
* into VRAM - so no need for cpu_to_le32 on VRAM tables */
writel(addr, ((void __iomem *)ptr) + (i * 4));
writel(entry, ((void __iomem *)ptr) + (i * 4));
}
int rv370_pcie_gart_init(struct radeon_device *rdev)
@ -109,6 +114,7 @@ int rv370_pcie_gart_init(struct radeon_device *rdev)
DRM_ERROR("Failed to register debugfs file for PCIE gart !\n");
rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
return radeon_gart_table_vram_alloc(rdev);
}

9
drivers/gpu/drm/radeon/radeon.h
View File

@ -242,6 +242,7 @@ bool radeon_get_bios(struct radeon_device *rdev);
* Dummy page
*/
struct radeon_dummy_page {
uint64_t entry;
struct page *page;
dma_addr_t addr;
};
@ -645,7 +646,7 @@ struct radeon_gart {
unsigned num_cpu_pages;
unsigned table_size;
struct page **pages;
dma_addr_t *pages_addr;
uint64_t *pages_entry;
bool ready;
};
@ -1847,8 +1848,9 @@ struct radeon_asic {
/* gart */
struct {
void (*tlb_flush)(struct radeon_device *rdev);
uint64_t (*get_page_entry)(uint64_t addr, uint32_t flags);
void (*set_page)(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags);
uint64_t entry);
} gart;
struct {
int (*init)(struct radeon_device *rdev);
@ -2852,7 +2854,8 @@ static inline void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
#define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
#define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
#define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
#define radeon_gart_set_page(rdev, i, p, f) (rdev)->asic->gart.set_page((rdev), (i), (p), (f))
#define radeon_gart_get_page_entry(a, f) (rdev)->asic->gart.get_page_entry((a), (f))
#define radeon_gart_set_page(rdev, i, e) (rdev)->asic->gart.set_page((rdev), (i), (e))
#define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
#define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
#define radeon_asic_vm_copy_pages(rdev, ib, pe, src, count) ((rdev)->asic->vm.copy_pages((rdev), (ib), (pe), (src), (count)))

24
drivers/gpu/drm/radeon/radeon_asic.c
View File

@ -159,11 +159,13 @@ void radeon_agp_disable(struct radeon_device *rdev)
DRM_INFO("Forcing AGP to PCIE mode\n");
rdev->flags |= RADEON_IS_PCIE;
rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
} else {
DRM_INFO("Forcing AGP to PCI mode\n");
rdev->flags |= RADEON_IS_PCI;
rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
rdev->asic->gart.set_page = &r100_pci_gart_set_page;
}
rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
@ -199,6 +201,7 @@ static struct radeon_asic r100_asic = {
.mc_wait_for_idle = &r100_mc_wait_for_idle,
.gart = {
.tlb_flush = &r100_pci_gart_tlb_flush,
.get_page_entry = &r100_pci_gart_get_page_entry,
.set_page = &r100_pci_gart_set_page,
},
.ring = {
@ -265,6 +268,7 @@ static struct radeon_asic r200_asic = {
.mc_wait_for_idle = &r100_mc_wait_for_idle,
.gart = {
.tlb_flush = &r100_pci_gart_tlb_flush,
.get_page_entry = &r100_pci_gart_get_page_entry,
.set_page = &r100_pci_gart_set_page,
},
.ring = {
@ -359,6 +363,7 @@ static struct radeon_asic r300_asic = {
.mc_wait_for_idle = &r300_mc_wait_for_idle,
.gart = {
.tlb_flush = &r100_pci_gart_tlb_flush,
.get_page_entry = &r100_pci_gart_get_page_entry,
.set_page = &r100_pci_gart_set_page,
},
.ring = {
@ -425,6 +430,7 @@ static struct radeon_asic r300_asic_pcie = {
.mc_wait_for_idle = &r300_mc_wait_for_idle,
.gart = {
.tlb_flush = &rv370_pcie_gart_tlb_flush,
.get_page_entry = &rv370_pcie_gart_get_page_entry,
.set_page = &rv370_pcie_gart_set_page,
},
.ring = {
@ -491,6 +497,7 @@ static struct radeon_asic r420_asic = {
.mc_wait_for_idle = &r300_mc_wait_for_idle,
.gart = {
.tlb_flush = &rv370_pcie_gart_tlb_flush,
.get_page_entry = &rv370_pcie_gart_get_page_entry,
.set_page = &rv370_pcie_gart_set_page,
},
.ring = {
@ -557,6 +564,7 @@ static struct radeon_asic rs400_asic = {
.mc_wait_for_idle = &rs400_mc_wait_for_idle,
.gart = {
.tlb_flush = &rs400_gart_tlb_flush,
.get_page_entry = &rs400_gart_get_page_entry,
.set_page = &rs400_gart_set_page,
},
.ring = {
@ -623,6 +631,7 @@ static struct radeon_asic rs600_asic = {
.mc_wait_for_idle = &rs600_mc_wait_for_idle,
.gart = {
.tlb_flush = &rs600_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -691,6 +700,7 @@ static struct radeon_asic rs690_asic = {
.mc_wait_for_idle = &rs690_mc_wait_for_idle,
.gart = {
.tlb_flush = &rs400_gart_tlb_flush,
.get_page_entry = &rs400_gart_get_page_entry,
.set_page = &rs400_gart_set_page,
},
.ring = {
@ -759,6 +769,7 @@ static struct radeon_asic rv515_asic = {
.mc_wait_for_idle = &rv515_mc_wait_for_idle,
.gart = {
.tlb_flush = &rv370_pcie_gart_tlb_flush,
.get_page_entry = &rv370_pcie_gart_get_page_entry,
.set_page = &rv370_pcie_gart_set_page,
},
.ring = {
@ -825,6 +836,7 @@ static struct radeon_asic r520_asic = {
.mc_wait_for_idle = &r520_mc_wait_for_idle,
.gart = {
.tlb_flush = &rv370_pcie_gart_tlb_flush,
.get_page_entry = &rv370_pcie_gart_get_page_entry,
.set_page = &rv370_pcie_gart_set_page,
},
.ring = {
@ -919,6 +931,7 @@ static struct radeon_asic r600_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &r600_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1004,6 +1017,7 @@ static struct radeon_asic rv6xx_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &r600_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1095,6 +1109,7 @@ static struct radeon_asic rs780_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &r600_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1199,6 +1214,7 @@ static struct radeon_asic rv770_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &r600_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1317,6 +1333,7 @@ static struct radeon_asic evergreen_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &evergreen_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1409,6 +1426,7 @@ static struct radeon_asic sumo_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &evergreen_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1500,6 +1518,7 @@ static struct radeon_asic btc_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &evergreen_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.ring = {
@ -1635,6 +1654,7 @@ static struct radeon_asic cayman_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &cayman_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.vm = {
@ -1738,6 +1758,7 @@ static struct radeon_asic trinity_asic = {
.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
.gart = {
.tlb_flush = &cayman_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.vm = {
@ -1871,6 +1892,7 @@ static struct radeon_asic si_asic = {
.get_gpu_clock_counter = &si_get_gpu_clock_counter,
.gart = {
.tlb_flush = &si_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.vm = {
@ -2032,6 +2054,7 @@ static struct radeon_asic ci_asic = {
.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
.gart = {
.tlb_flush = &cik_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.vm = {
@ -2139,6 +2162,7 @@ static struct radeon_asic kv_asic = {
.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
.gart = {
.tlb_flush = &cik_pcie_gart_tlb_flush,
.get_page_entry = &rs600_gart_get_page_entry,
.set_page = &rs600_gart_set_page,
},
.vm = {

12
drivers/gpu/drm/radeon/radeon_asic.h
View File

@ -67,8 +67,9 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
int r100_asic_reset(struct radeon_device *rdev);
u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc);
void r100_pci_gart_tlb_flush(struct radeon_device *rdev);
uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags);
void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags);
uint64_t entry);
void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
int r100_irq_set(struct radeon_device *rdev);
int r100_irq_process(struct radeon_device *rdev);
@ -172,8 +173,9 @@ extern void r300_fence_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
extern int r300_cs_parse(struct radeon_cs_parser *p);
extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
extern uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags);
extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags);
uint64_t entry);
extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
extern void r300_set_reg_safe(struct radeon_device *rdev);
@ -208,8 +210,9 @@ extern void rs400_fini(struct radeon_device *rdev);
extern int rs400_suspend(struct radeon_device *rdev);
extern int rs400_resume(struct radeon_device *rdev);
void rs400_gart_tlb_flush(struct radeon_device *rdev);
uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags);
void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags);
uint64_t entry);
uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg);
void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
int rs400_gart_init(struct radeon_device *rdev);
@ -232,8 +235,9 @@ int rs600_irq_process(struct radeon_device *rdev);
void rs600_irq_disable(struct radeon_device *rdev);
u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc);
void rs600_gart_tlb_flush(struct radeon_device *rdev);
uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags);
void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
uint64_t addr, uint32_t flags);
uint64_t entry);
uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg);
void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
void rs600_bandwidth_update(struct radeon_device *rdev);

Some files were not shown because too many files have changed in this diff Show More